Institute of Management, Nirma University - Logo

Publications

Voice based pathology detection from respiratory sounds using optimized classifiers

Journal

Journal NameInternational Journal of Computing and Digital Systems

Title of PaperVoice based pathology detection from respiratory sounds using optimized classifiers

PublisherUniversity of Bahrain

Volume Number13

Page Number327 - 339

Published YearJanuary 2023

ISSN/ISBN No2210142X

Indexed INScopus

Abstract

Speech is an important tool for communication. When a person speaks, the vocal cords come closer and the glottis is partially closed. The airflow which passes through glottis is disturbed by vocal cords and speech waveform is produced. The person who suffers from the vocal cord paralysis or vocal cord blister, his lungs are filled with fluid and airway blockage cannot generate a similar waveform as a healthy person. In this work, we compare traditional approaches with deep learning based approaches for respiratory disease detection to distinguish between a healthy person and the victim of pathological voice disorder. Four conventional machine learning classifiers and a one-dimensional convolution neural network based classifier have been implemented on two benchmark datasets ICBHI 2017 and Coswara. Our experiments show that the CNN based approach and Random Forest algorithm exhibit superior performance over other approaches on ICBHI 2017 and Coswara datasets, respectively.

Swine Flu Predication Using Machine Learning

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer

Author NameDvijesh Bhatt, Malaram Kumhar, Daiwat Vyas, Ajay Patel

Page Number611-617

Chapter TitleSwine Flu Predication Using Machine Learning

Published YearDecember 2018

ISSN/ISBN No978-981-13-1746-0

Indexed INScopus

Comparative Performance Study of Various Content Based Image Retrieval Methods

Book Chapter

Book NameSmart Innovation, Systems and Technologies, VOLUME 50

PublisherSPRINGER

Author NameRushabh Shah, Jeetendra Vaghela, Khyati Surve, Rutvi Shah, Priyanka Sharma, Rasendu Mishra, Ajay Patel, Rajan Datt

Page Number397-407

Chapter TitleComparative Performance Study of Various Content Based Image Retrieval Methods

Published YearJuly 2016

ISSN/ISBN NoPrint ISBN 978-3-319-30932-3 Online ISBN 978-3-319-30933-0

Indexed INScopus

DATA EXCHANGE MODEL USING WEB SERVICE FOR HEROGENEOUS DATABASES

Journal

Journal NameINTERNATIONAL JOURNAL OF ADVANCED RESEARCH IN ENGINEERING AND TECHNOLOGY (IJARET)

Title of PaperDATA EXCHANGE MODEL USING WEB SERVICE FOR HEROGENEOUS DATABASES

PublisherIAEME

Volume Number6

Page Number107-111

Published YearApril 2015

ISSN/ISBN No0976 - 6499

VOICE ENABLE PORTAL

Journal

Journal NameNational Journal - Biannual Publication

Title of PaperVOICE ENABLE PORTAL

PublisherKSV-JSTR

Volume Number1

Page Number41-44

Published YearJune 2010

ISSN/ISBN No0974-9780

M-ticket- An M-commerce Application

Conference

Title of PaperM-ticket- An M-commerce Application

Proceeding NameGREEN-IT & OPEN SOURCE

OrganizationSinhgad Institute of Management (SIOM)

Year , VenueApril 2010 , Sinhgad Institute of Management (SIOM) , Pune

Page Number540-542

ISSN/ISBN No978-93- 80043-89-0

Applicability of Genetic Algorithms for Stock Market Prediction: A Systematic Survey of the Last Decade

Journal

Journal NameComputer Science Review

Title of PaperApplicability of Genetic Algorithms for Stock Market Prediction: A Systematic Survey of the Last Decade

PublisherElsevier

Volume Number53

Page Number1-26

Published YearJuly 2024

ISSN/ISBN No1574-0137

Indexed INScopus, Web of Science

Abstract

Stock market is one of the attractive domains for researchers as well as academicians. It represents highly complex non-linear fluctuating market behaviours where traders, investors, and organizers look forward to reliable future predictions of the market indices. Such prediction problems can be computationally addressed using various machine learning, deep learning, sentiment analysis, as well as mining approaches. However, the internal parameters configuration can play an important role in the prediction performance; also, feature selection is a crucial task. Therefore, to optimize such approaches, the evolutionary computation-based algorithms can be integrated in several ways. In this article, we systematically conduct a focused survey on genetic algorithm (GA) and its applications for stock market prediction; GAs are known for their parallel search mechanism to solve complex real-world problems; various genetic perspectives are also integrated with machine learning and deep learning methods to address financial forecasting. Thus, we aim to analyse the potential extensibility and adaptability of GAs for stock market prediction. We review stock price and stock trend prediction, as well as portfolio optimization, approaches over the recent years (2013–2022) to signify the state-of-the-art of GA-based optimization in financial markets. We broaden our discussion by briefly reviewing other genetic perspectives and their applications for stock market forecasting. We balance our survey with the consideration of competitiveness and complementation of GAs, followed by highlighting the challenges and potential future research directions of applying GAs for stock market prediction.

A Compendium on Risk Assessment of Phishing Attack Using Attack Modeling Techniques

Journal

Journal NameProcedia Computer Science

Title of PaperA Compendium on Risk Assessment of Phishing Attack Using Attack Modeling Techniques

PublisherElsevier

Volume Number235

Page Number1105-1114

Published YearMay 2024

ISSN/ISBN No1877-0509

Indexed INScopus

Abstract

With the advent of new attacking methodologies and types of attacks, it has become difficult to protect the systems. Therefore, it is necessary to decipher the impact of attacks before and after its occurrence to provide better security. It is hard to speculate future attacks, without understanding the network vulnerability and therefore, it is important to examine the network for identifying potential vulnerabilities using attack modeling. Phishing attacks is one of the prominent network attacks that pose continual threat to the network and organization. This article presents and discusses in brief attack modeling techniques that can be applied for risk assessment. The paper presents in detail modeling of phishing attack using attack graphs, cyber kill chain, diamond model, security incident response matrix, and data description model. Moreover, the article also discusses role of network defenders and system engineers in assessing risk and how attack models can be helpful to them for modeling attacks. The review presented in this paper can serve as a platform for researchers in the field of network security and risk assessment for developing effective and secure network environment.

Sentiment Analysis of Self Driving Car Dataset: A comparative study of Deep Learning approaches

Journal

Journal NameProcedia Computer Science

Title of PaperSentiment Analysis of Self Driving Car Dataset: A comparative study of Deep Learning approaches

PublisherElsevier

Volume Number235

Page Number12-21

Published YearMay 2024

ISSN/ISBN No1877-0509

Indexed INScopus

Abstract

Sentiment Analysis (SA) is a crucial task in understanding public opinions and perceptions towards emerging technologies. In this study, we focus on SA for a self-driving car dataset as it provides valuable insights into public perceptions and opinions towards a transformative technology. The dataset consists of textual reviews associated with sentiment labels, providing insights into how people perceive self-driving car technology. Our objective is to analyze the sentiments expressed in these reviews using Deep Learning (DL) models, namely, Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), and Bidirectional GRU (BiGRU). We compared our results with an existing technique in the field of self-driving car sentiment classification, that implemented various Machine Learning (ML) and DL models, including Support Vector Machines (SVM), Naïve Bayes (NB), Logistic Regression (LR), Random Forest (RF), CNN, and LSTM. In our study, we expanded upon this research by evaluating the performance of ANN, BiLSTM, GRU, and BiGRU. Results reveal that BiLSTM, GRU, and BiGRU exhibit superior performance in sentiment classification within the self-driving car dataset. These findings offer valuable insights into public sentiment towards self-driving cars, contributing significantly to the advancement of SA techniques in the domain of autonomous vehicles. Additionally, the results are statistically tested and are statistically significant.

Fusion of linear and non-linear dimensionality reduction techniques for feature reduction in LSTM-based Intrusion Detection System

Journal

Journal NameApplied Soft Computing

Title of PaperFusion of linear and non-linear dimensionality reduction techniques for feature reduction in LSTM-based Intrusion Detection System

PublisherElsevier

Volume Number154

Page Number1-9

Published YearMarch 2024

ISSN/ISBN No1568-4946

Indexed INScopus, Web of Science

Abstract

Securing networks is becoming increasingly crucial due to the widespread use of information technology. Intrusion Detection System (IDS) plays a crucial role in network security by detecting potential security threats in real-time. In order to create effective IDS, Deep Learning (DL) techniques like Auto Encoder (AE) and Long Short-Term Memory (LSTM) have been widely used. However, the high dimensionality and complexity of network traffic data make it challenging to extract meaningful information. The paper proposes a fusion-based approach that combines AE and Principal Component Analysis (PCA) techniques for dimensionality reduction in IDS. The proposed approach aims to capture both linear and non-linear relationships between features while reducing the dimensionality of the input data. NSL-KDD, UNSW-NB15, CIC-IDS-2017, and MSCAD datasets are used to evaluate this proposed method. The proposed approach has improved accuracy compared to the existing AE+LSTM-based approach by 3% for NSL-KDD and around 1% for UNSW-NB15 and CIC-IDS-2017, while the proposed approach gives comparable results for the MSCAD dataset. The Wilcoxon signed-rank test has been applied to confirm the statistical significance of the result.

A Review on Challenges and Future Research Directions for Machine Learning-Based Intrusion Detection System

Journal

Journal NameArchives of Computational Methods in Engineering

Title of PaperA Review on Challenges and Future Research Directions for Machine Learning-Based Intrusion Detection System

PublisherSpringer

Volume Number30

Page Number4245–4269

Published YearMay 2023

ISSN/ISBN No1886-1784

Indexed INScopus, Web of Science

Abstract

Research in the field of Intrusion Detection is focused on developing an efficient strategy that can identify network attacks. One of the important strategies is to supervise the network events for identifying attacks. Security mechanisms such as Intrusion Detection Systems (IDS) have been used for securing the network infrastructure and network communication against network attacks, wherein Machine Learning (ML) techniques have a notable contribution to design an efficient IDS. However, dependence on modern communication technology and collateral rise in the network attacks affect the performance of ML techniques. In this article, we discuss a detailed overview of intrusion detection using ML techniques. We discuss the steps performed by ML techniques for detecting and classifying intrusions. Moreover, our paper provides a comprehensive overview of state-of-the-art ML techniques used for intrusion detection and classification along with their advantages and limitations. The paper also summarizes research work performed in the field of ML-based IDS. In this paper, we aim to discuss various challenges faced by ML-based IDS. We further discuss future research directions that can be considered for enhancing the efficiency and effectiveness of IDS. Our review will serve as an incentive to novice researchers who aim to work in the field of ML-based IDS.

Attack Classification of Imbalanced Intrusion Data for IoT network Using Ensemble Learning-based Deep Neural Network

Journal

Journal NameIEEE Internet of Things Journal

Title of PaperAttack Classification of Imbalanced Intrusion Data for IoT network Using Ensemble Learning-based Deep Neural Network

PublisherIEEE

Volume Number10

Page Number11888 - 11895

Published YearFebruary 2023

ISSN/ISBN No2327-4662

Indexed INScopus, Web of Science

Abstract

With the increase in popularity of Internet of Things (IoT) and rise in interconnected devices, the need to foster effective security mechanism to handle vulnerabilities and risks in IoT networks has become evident. Security mechanisms such as Intrusion Detection System (IDS) are designed and deployed in IoT network environment to ensure security and prevent unauthorized access to system and resources. Moreover, there have been efforts to design IDS using various Deep Learning (DL) techniques, as these techniques possess intriguing characteristic of representing data with high abstraction. However, intrusion detection datasets used in literature possess imbalance class distribution, which is one of the challenging issue in developing coherent and potent intrusion detection and classification system. In this paper, we aim to address class imbalance problem using ensemble learning approach, namely, Bagging classifier, that uses Deep Neural Network (DNN) as base estimator. Here, in the proposed approach, the training process of DNN is influenced by including class weights that advocates to create balanced training subsets for DNN. The desirability and merit of the proposed approach can be considered as two-fold as it aims to achieve generalization along with addressing the class imbalance problem in intrusion detection datasets. The performance of the proposed approach is evaluated using four intrusion detection datasets, namely, NSL-KDD, UNSW_NB-15, CIC-IDS-2017, and BoT-IoT. Result analysis of the proposed approach is illustrated using various evaluation metrics, namely, accuracy, precision, recall, f-score, and False Positive Rate (FPR). Moreover, results of the proposed approach are also statistically tested using Wilcoxon signed-rank test.

Data fusion with factored quantization for stock trend prediction using neural networks

Journal

Journal NameInformation Processing & Management

Title of PaperData fusion with factored quantization for stock trend prediction using neural networks

PublisherElsevier

Volume Number60

Page Number1-18

Published YearFebruary 2023

ISSN/ISBN No0306-4573

Indexed INScopus, Web of Science

Abstract

As compared to the continuous temporal distributions, discrete data representations may be desired for simplified and faster data analysis and forecasting. Data compression can introduce one of the efficient ways to reduce continuous historical stock market data and present them in discrete forms; while predicting stock trend, a primary concern is towards up and down directions of the price movement and thus, data discretization for a focused approach can be beneficial. In this article, we propose a quantization-based data fusion approach with a primary motivation to reduce data complexity and hence, enhance the prediction ability of a model. Here, the continuous time-series values are transformed into discrete quantum values prior to applying them to a prediction model. We extend the proposed approach and factorize quantization by integrating different quantization step sizes. Such fused data can reduce the data to mainly concentrate on the stock price movement direction. To empirically evaluate the proposed approach for stock trend prediction, we adopt long short-term memory, deep neural network, and backpropagation neural network models and compare our prediction results with five existing approaches on several datasets using ten performance metrics. We analyze the impact of specific quantization factors and determine the individual best as well as overall best factor sizes; the results indicate a consistent performance enhancement in stock trend prediction accuracy as compared to the considered baseline methods with an improvement up to 7%. To evaluate the impact of quantization-based data fusion, we analyze time required to execute the experiments along with percentage reduction in the number of unique numeric terms. Further, these results are statistically evaluated using Wilcoxon signed-rank test. We discuss the superiority and applicability of factored quantization-based data fusion approach and conclude our work with potential future research directions.

Neural network systems with an integrated coefficient of variation-based feature selection for stock price and trend prediction

Journal

Journal NameExpert Systems with Applications

Title of PaperNeural network systems with an integrated coefficient of variation-based feature selection for stock price and trend prediction

PublisherElsevier

Volume Number219

Page Number1-20

Published YearJanuary 2023

ISSN/ISBN No1873-6793

Indexed INScopus, Web of Science

Abstract

Stock market forecasting has been a subject of interest for many researchers; the essential market analyses can be integrated with historical stock market data to derive a set of features. It is crucial to select features with useful in- formation about the specific aspect. In this article, we propose coefficient of variation (CV)-based feature selection for stock prediction. The unitless statis- tical method, CV, is widely used to obtain variability among data distributions. We calculate CV for each feature and integrate an existing method, k-means al- gorithm, as well as proposed methods, median range and top-M , to select a set of features with specific characteristics such as features belonging to the largest cluster, the defined range, and with the highest CV values, respectively. We apply the set of selected features to models such as backpropagation neural net- work (BPNN), long short-term memory (LSTM), gated recurrent unit (GRU), and convolutional neural network (CNN) for stock price and trend prediction. We demonstrate the applicability of our proposed approach using five of the existing feature selection methods, namely, correlation coefficient, Chi2, mutual information, principal component analysis, and variance threshold; comparison indicates remarkable performance enhancement using several accuracy-based, as well as error-based, metrics and the same is statistically supported using Wilcoxon signed-rank test.

Fusion of statistical importance for feature selection in Deep Neural Network-based Intrusion Detection System

Journal

Journal NameInformation Fusion

Title of PaperFusion of statistical importance for feature selection in Deep Neural Network-based Intrusion Detection System

PublisherElsevier

Volume Number90

Page Number353-363

Published YearOctober 2022

ISSN/ISBN No1566-2535

Indexed INScopus, Web of Science

Abstract

Intrusion Detection System (IDS) is an essential part of network as it contributes towards securing the network against various vulnerabilities and threats. Over the past decades, there has been comprehensive study in the field of IDS and various approaches have been developed to design intrusion detection and classification system. With the proliferation in the usage of Deep Learning (DL) techniques and their ability to learn data extensively, we aim to design Deep Neural Network (DNN)-based IDS. In this study, we aim to focus on enhancing the performance of DNN-based IDS by proposing a novel feature selection technique that selects features via fusion of statistical importance using Standard Deviation and Difference of Mean and Median. Here, in the proposed approach, features are pruned based on their rank derived using fusion of statistical importance. Moreover, fusion of statistical importance aims to derive relevant features that possess high discernibility and deviation, that assists in better learning of data. The performance of the proposed approach is evaluated using three intrusion detection datasets, namely, NSL-KDD, UNSW_NB-15, and CIC-IDS-2017. Performance analysis is presented in terms of different evaluation metrics such as accuracy, precision, recall, -score, and False Positive Rate (FPR) and the results are compared with existing feature selection techniques. Apart from evaluation metrics, performance comparison is also presented in terms of execution time. Moreover, results achieved are also statistically tested using Wilcoxon Signed Rank test.

Improving the performance of sentiment analysis using enhanced preprocessing technique and Artificial Neural Network

Journal

Journal NameIEEE Transactions on Affective Computing

Title of PaperImproving the performance of sentiment analysis using enhanced preprocessing technique and Artificial Neural Network

PublisherIEEE

Volume NumberYet to be assigned

Page Number1-12

Published YearSeptember 2022

ISSN/ISBN No1949-3045

Indexed INScopus, Web of Science

Abstract

With the presence of a massive amount of digitally recorded data, an automated computation can be preferable over the manual approach to evaluate sentiments within given textual fragments. Artificial neural network (ANN) is preferred for sentiment analysis (SA) because of its learning ability and adaptive nature towards diverse data. Handling negation in SA is a challenging task, and to address the same, we propose a specific order of preprocessing (PPR) steps to enhance the performance of SA using ANN. Typically, ANN weights are randomly initialized (R-ANN), which may not give the desired performance. As a potential solution, we propose a novel approach named Matching features with output label based Advanced Technique (MAT) to initialize the ANN weights (MAT-ANN). Simulation results conclude the superiority of the proposed approach PPR+MAT-ANN compared to the existing approach EPR+R-ANN i.e., integrating existing preprocessing (EPR) steps with R-ANN. Moreover, PPR+MAT-ANN architecture is significantly simpler than the existing deep learning-based approach named the NeuroSent tool and gives better performance when evaluated upon the Dranziera protocol.

Information fusion-based genetic algorithm with long short-term memory for stock price and trend prediction

Journal

Journal NameApplied Soft Computing

Title of PaperInformation fusion-based genetic algorithm with long short-term memory for stock price and trend prediction

PublisherElsevier

Volume Number128

Page Number1-20

Published YearAugust 2022

ISSN/ISBN No1568-4946

Indexed INScopus, Web of Science

Abstract

Information fusion is one of the critical aspects in diverse fields of applications; while the collected data may provide certain perspectives, a fusion of such data can be a useful way of exploring, expanding, enhancing, and extracting meaningful information for a better organization of the targeted domain. A nature-inspired evolutionary approach, namely, genetic algorithm (GA) is adopted for a variety of applications including stock market prediction. The complex, highly fluctuating financial market-related problems require optimized models for reliable forecasting. Also, it can be observed that stock market etiquettes are generally non-linear in nature and therefore, a broader understanding and analysis of such market behaviors necessitate the collection and fusion of relevant information based on different associated factors. In this article, we propose an information fusion-based GA approach with inter-intra crossover and adaptive mutation (ICAN) for stock price and trend prediction. Inspired by the genetic diversity and survival capability of various organisms, our proposed approach aims to optimize parameters of a long short-term memory prediction model, and selects a set of features; to address these problems of interest, we integrate inter-chromosome as well as conditional intra-chromosome crossover operations along with adaptive mutation to diversify the potential chromosome solutions. We illustrate the step-by-step procedure followed by GA with ICAN and evaluate its performance for one-day-ahead stock price and trend prediction. GA with ICAN-based optimization results in an average reduction of 43%, 27%, and 26% using mean squared error, mean absolute error, and mean absolute percentage error, respectively, as compared to the existing GA-based optimization approaches; further, an average improvement of 61% is encountered using R score. We also compare our work with Ant Lion Optimization approach and demonstrate the significance of GA with ICAN-based optimization. We analyze statistical significance, as well as convergence functions, for GA with ICAN and discuss remarkable performance enhancement; we provide necessary concluding remarks with potential future research directions.

An improved method for classifying depth-based human actions using self-adaptive evolutionary technique

Journal

Journal NameJournal of Ambient Intelligence and Humanized Computing

Title of PaperAn improved method for classifying depth-based human actions using self-adaptive evolutionary technique

PublisherSpringer Berlin Heidelberg

Volume NumberYet to be assigned

Page Number1-17

Published YearMay 2022

ISSN/ISBN No1868-5145

Indexed INScopus, Web of Science

Abstract

Automatic Human Action Recognition (HAR) using RGB-D (Red, Green, Blue, and Depth) videos captivated a lot of attention in the pattern classification field due to low-cost depth cameras. Feature extraction in action recognition is an important aspect. As compared to Depth Motion Maps (DMM), Depth Motion Maps–Local Binary Pattern (DMM–LBP) provides compact representation of features. After extracting features using DMM–LBP, Principal Component Analysis (PCA) is used for dimensionality reduction. For classification task, randomly generated input weights of Extreme Learning Machine (ELM) can lead to non-optimal results. Therefore, in this paper, we have used an improved learning algorithm named Self-adaptive Differential Evolution (SaDE) ELM for action classification. In the proposed approach, DMM–LBP is used for feature extraction and SaDE–ELM is used for action classification. To evaluate strength of the proposed approach, experiments are performed on four public datasets, namely, MSRAction3D, MSRDaily Activity3D, UTD–MHAD, and MSRGesture3D. The proposed approach gives better accuracy compared to existing approaches Kernel ELM (KELM), l2-Collaborative Representation Classifier (l2-CRC), and Probabilistic CRC (ProCRC) methods. We have also presented statistical significance of results in the paper.

Analyzing fusion of regularization techniques in the deep learning‐based intrusion detection system

Journal

Journal Name International Journal of Intelligent Systems

Title of PaperAnalyzing fusion of regularization techniques in the deep learning‐based intrusion detection system

PublisherWiley

Volume Number36

Page Number7340-7388

Published YearAugust 2021

ISSN/ISBN No1098-111X

Indexed INScopus, Web of Science

Abstract

The surge of constantly evolving network attacks can be addressed by designing an effective and efficient Intrusion Detection System (IDS). Various Deep Learning (DL) techniques have been used for designing intelligent IDS. However, DL techniques face an issue of overfitting because of complex network structure and high-dimensional data sets. Dropout and regularization are two competently perceived concepts of DL used for handling overfitting issue to enhance the performance of DL techniques. In this paper, we aim to apply fusion of various regularization techniques, namely, L1, L2, and elastic net regularization, with dropout regularization technique, for analyzing and enhancing the performance of Deep Neural Network (DNN)-based IDS. Experiments are performed using NSL-KDD, UNSW_NB-15, and CIC-IDS-2017 data sets. The value of dropout probability is derived using GridSearchCV-based hyperparameter optimization technique. Moreover, the paper also implements state-of-the-art Machine Learning techniques for the performance comparison. Apart from DNN, we have also presented performance analysis of various DL techniques, namely, Recurrent Neural Network, Long Short-Term Memory, Gated Recurrent Unit, and Convolutional Neural Network using a fusion of regularization techniques for intrusion detection and classification. The empirical study shows that among the techniques implemented, dropout has proved to be more effective compared with L1, L2, and elastic net regularization. Moreover, fusion of dropout with other regularization techniques achieved better results compared with L1 regularization, L2 regularization, and elastic net regularization, individually. The techniques implemented for DNN-based IDS are also statistically tested using the Wilcoxon signed-rank test.

Pearson Correlation Coefficient-based performance enhancement of Vanilla Neural Network for stock trend prediction

Journal

Journal NameNeural Computing and Applications

Title of PaperPearson Correlation Coefficient-based performance enhancement of Vanilla Neural Network for stock trend prediction

PublisherSpringer

Volume Number33

Page Number16985–17000

Published YearJuly 2021

ISSN/ISBN No1433-3058

Indexed INScopus, Web of Science, EBSCO

Abstract

The prediction of a volatile stock market is a challenging task. While various neural networks are integrated to address stock trend prediction problems, the weight initialization of such networks plays a crucial role. In this article, we adopt feed-forward Vanilla Neural Network (VNN) and propose a novel application of Pearson Correlation Coefficient (PCC) for weight initialization of VNN model. VNN consists of an input layer, a single hidden layer, and an output layer; the edges connecting neurons in the input layer and the hidden layer are generally initialized with random weights. While PCC is primarily used to find the correlation between two variables, we propose to apply PCC for weight initialization instead of random initialization (RI) for a VNN model to enhance the prediction performance. We also introduce the application of Absolute PCC (APCC) for weight initialization and analyze the effects of RI, PCC, and APCC values as weights for a VNN model. We conduct an empirical study using these concepts to predict the stock trend and evaluate these three weight initialization techniques on ten years of stock trading archival data of Reliance Industries, Infosys Ltd, HDFC Bank, and Dr. Reddy’s Laboratories for the duration of years 2008 to 2017 for continuous as well as discrete data representations. We further evaluate the applicability of these weight initialization techniques using an ablation study on the considered features and analyze the prediction performance. The results demonstrate that the proposed weight initialization techniques, PCC and APCC, provide higher or comparable results as compared to RI, and the statistical significance of the same is carried out.

iCREST: International Cross-Reference to Exchange-Based Stock Trend Prediction Using Long Short-Term Memory

Book Chapter

Book NameApplied Soft Computing and Communication Networks

PublisherSpringer

Author NameKinjal Chaudhari and Ankit Thakkar

Page Number323-338

Chapter TitleiCREST: International Cross-Reference to Exchange-Based Stock Trend Prediction Using Long Short-Term Memory

Published YearJuly 2021

ISSN/ISBN No978-981-33-6172-0

Indexed INScopus

Abstract

Stock market investments have been primarily aimed at gaining higher profits from the investment; a large number of companies get listed on various stock exchanges to initiate trading through the stock market. For the potential expansion of market tradings, several companies may choose to get listed on multiple exchanges which may be domestic and/or international. In this article, we propose an international cross-reference to exchange-based stock trend (iCREST) prediction approach to study how historical stock market data of a company listed on internationally-located stock exchanges can be integrated. We consider the timezone and currency variations in order to unify the data; we also incorporate data integration-based pre-processing to eliminate loss of useful stock price information. We calculate the difference between exchange prices of a company and adopt long short-term memory (LSTM) models to predict one-day-ahead stock trend on respective exchanges. Our work can be considered as one of the novel approaches that integrate the international stock exchanges to predict the stock trend of corresponding markets. For the experiment, we take datasets of five companies listed on National Stock Exchange (NSE), Bombay Stock Exchange (BSE), as well as New York Stock Exchange (NYSE); the prediction performance is evaluated using directional accuracy (DA), precision, recall, and F-measure metrics. The results using these metrics indicate performance improvement with international exchanges, and hence the potential adaptability of the proposed approach.

Intrusion Detection Using Deep Neural Network with AntiRectifier Layer

Book Chapter

Book NameApplied Soft Computing and Communication Networks

PublisherSpringer

Author NameRitika Lohiya and Ankit Thakkar

Page Number89-105

Chapter TitleIntrusion Detection Using Deep Neural Network with AntiRectifier Layer

Published YearJuly 2021

ISSN/ISBN No978-981-33-6172-0

Indexed INScopus

Abstract

Data security is regarded to be one of the crucial challenges in this fast-growing internet world. Data generated through internet is exposed to various types of vulnerabilities and exploits. Security mechanisms such as Intrusion Detection System (IDS) are designed to detect various types of vulnerabilities and attacks. Various Machine Learning (ML) and Deep Learning (DL) techniques are used for building IDS. In this paper, we aim to build Deep Neural Network (DNN)-based IDS for attack detection and classification. DNN technique has certain challenges such as complex network structure, co-adaptation of feature vectors, over-fitting, to name a few. We aim to address these challenges by using AntiRectifier layer and variants of dropout namely, Standard dropout, Gaussian dropout, and Gaussian Noise. In this paper, we have evaluated DNN-based IDS using NSL-KDD, UNSW_NB-15 and CIC-IDS-2017 dataset. The experimental results show that DNN-based IDS with AntiRectifier layer outperforms compared to ML techniques such as Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), Support Vector Machine (SVM), k-Nearest Neighbours (k-NN) and variants of dropout namely, Standard dropout, Gaussian dropout, and Gaussian noise in terms of accuracy, precision, recall, f-score, and false positive rate.

A survey on intrusion detection system: feature selection, model, performance measures, application perspective, challenges, and future research directions

Journal

Journal NameArtificial Intelligence Review

Title of PaperA survey on intrusion detection system: feature selection, model, performance measures, application perspective, challenges, and future research directions

PublisherSpringer

Volume NumberYet to be assigned

Page Number1-111

Published YearJuly 2021

ISSN/ISBN No1573-7462

Indexed INScopus, Web of Science, EBSCO

Abstract

With the increase in the usage of the Internet, a large amount of information is exchanged between different communicating devices. The data should be communicated securely between the communicating devices and therefore, network security is one of the dominant research areas for the current network scenario. Intrusion detection systems (IDSs) are therefore widely used along with other security mechanisms such as firewall and access control. Many research ideas have been proposed pertaining to the IDS using machine learning (ML) techniques, deep learning (DL) techniques, and swarm and evolutionary algorithms (SWEVO). These methods have been tested on the datasets such as DARPA, KDD CUP 99, and NSL-KDD using network features to classify attack types. This paper surveys the intrusion detection problem by considering algorithms from areas such as ML, DL, and SWEVO. The survey is a representative research work carried out in the field of IDS from the year 2008 to 2020. The paper focuses on the methods that have incorporated feature selection in their models for performance evaluation. The paper also discusses the different datasets of IDS and a detailed description of recent dataset CIC IDS-2017. The paper presents applications of IDS with challenges and potential future research directions. The study presented, can serve as a pedestal for research communities and novice researchers in the field of network security for understanding and developing efficient IDS models.

RGB-D based human action recognition using evolutionary self-adaptive extreme learning machine with knowledge-based control parameters

Journal

Journal NameJournal of Ambient Intelligence and Humanized Computing

Title of PaperRGB-D based human action recognition using evolutionary self-adaptive extreme learning machine with knowledge-based control parameters

PublisherSpringer

Volume NumberYet to be assigned

Page Number1-19

Published YearJune 2021

ISSN/ISBN No1868-5145

Indexed INScopus, Web of Science, EBSCO

Abstract

Human Action Recognition (HAR) has gained considerable attention due to its various applications such as monitoring activities, robotics, visual surveillance, to name a few. An action recognition task consists of feature extraction, dimensionality reduction, and action classification. The paper proposes an action recognition approach for depth-based input by designing Single Layer Feed forward Network (SLFN) using Self-adaptive Differential Evolution with knowledge-based control parameter-Extreme Learning Machine (SKPDE-ELM). To capture motion cues, we have used Depth Motion Map (DMM) wherein to obtain compact features, Local Binary Pattern (LBP) is applied. Thereafter, for dimensionality reduction, Principal Component Analysis (PCA) is applied to reduce the feature dimensions. For the action classification task, Extreme Learning Machine (ELM) achieves good performance for depth-based input due to its learning speed and good generalization performance. Further, to optimize the performance of ELM classifier, an evolutionary method named SKPDE is used to derive the hidden parameters of ELM classifier. The performance of the proposed approach is compared with the existing approaches Kernel ELM (KELM), L2-Collaborative Representation Classifier (CRC), and Probabilistic CRC (Pro-CRC) using datasets MSRAction3D (with 557 samples), MSRAction3D (with 567 samples), MSRDaily Activity3D, MSRGesture3D, and UTDMHAD. The proposed approach is also statistically tested using Wilcoxon signed rank-test.

A comprehensive survey on deep neural networks for stock market: The need, challenges, and future directions

Journal

Journal NameExpert Systems with Applications

Title of PaperA comprehensive survey on deep neural networks for stock market: The need, challenges, and future directions

PublisherElsevier

Volume Number177

Page Number1-17

Published YearMarch 2021

ISSN/ISBN No0957-4174

Indexed INScopus, Web of Science

Abstract

The stock market has been an attractive field for a large number of organizers and investors to derive useful predictions. Fundamental knowledge of stock market can be utilised with technical indicators to investigate different perspectives of the financial market; also, the influence of various events, financial news, and/or opinions on investors’ decisions and hence, market trends have been observed. Such information can be exploited to make reliable predictions and achieve higher profitability. Computational intelligence has emerged with various deep neural network (DNN) techniques to address complex stock market problems. In this article, we aim to review the significance and need of DNNs in the field of stock price and trend prediction; we discuss the applicability of DNN variations to the temporal stock market data and also extend our survey to include hybrid, as well as metaheuristic, approaches with DNNs. We observe the potential limitations for stock market prediction using various DNNs. To provide an experimental evaluation, we also conduct a series of experiments for stock market prediction using nine deep learning-based models; we analyse the impact of these models on forecasting the stock market data. We also evaluate the performance of individual models with different number of features. We discuss challenges, as well as potential future research directions, and conclude our survey with the experimental study. This survey can be referred for the recent perspectives of DNN-based stock market prediction, primarily covering research spanning over years 2017-2020

Fusion in stock market prediction: A decade survey on the necessity, recent developments, and potential future directions

Journal

Journal NameInformation Fusion

Title of PaperFusion in stock market prediction: A decade survey on the necessity, recent developments, and potential future directions

PublisherElsevier

Volume Number65

Page Number95-107

Published YearJanuary 2021

ISSN/ISBN No1566-2535

Indexed INScopus, Web of Science

Abstract

Investment in a financial market is aimed at getting higher benefits; this complex market is influenced by a large number of events wherein the prediction of future market dynamics is challenging. The investors’ etiquettes towards stock market may demand the need of studying various associated factors and extract the useful information for reliable forecasting. Fusion can be considered as an approach to integrate data or characteristics, in general, and enhance the prediction based on the combinational approach that can aid each other. We conduct a systematic approach to present a survey for the years 2011–2020 by considering articles that have used fusion techniques for various stock market applications and broadly categorize them into information fusion, feature fusion, and model fusion. The major applications of stock market include stock price and trend prediction, risk analysis and return forecasting, index prediction, as well as portfolio management. We also provide an infographic overview of fusion in stock market prediction and extend our survey for other finely addressed financial prediction problems. Based on our surveyed articles, we provide potential future directions and concluding remarks on the significance of applying fusion in stock market.

Application Domains, Evaluation Datasets, and Research Challenges of IoT: A Systematic Review

Journal

Journal NameIEEE Internet of Things Journal

Title of PaperApplication Domains, Evaluation Datasets, and Research Challenges of IoT: A Systematic Review

PublisherIEEE

Volume Number8

Page Number8774 - 8798

Published YearDecember 2020

ISSN/ISBN No2327-4662

Indexed INScopus, Web of Science

Abstract

We are at the brink of Internet of Things (IoT) era where smart devices and other wireless devices are redesigning our environment to make it more correlative, flexible, and communicative. IoT is now evolving to Internet of Everything, as it incorporates and builds a system that includes wireless networks, sensors, cloud servers, analytics, smart devices, and advanced technologies. The IoT systems are equipped with embedded devices having network connectivity and sensors to have a machine to machine interaction. The field of IoT is advancing to provide smart solutions to various applications such as transportation, healthcare, farming, to name a few. Considering the diverse perspective of IoT systems/network, the paper aims at discussing different applications of IoT across various research domains and to highlight the use of IoT in a variety of applications. We have systematically reviewed applications of IoT with the datasets to understand the characteristics of the data collected by the IoT devices. In this paper, a comprehensive survey on the role of IoT in various application domains is presented for the years 2015-2019. The paper lists different commercialized solutions developed in various IoT application domains. The aim to discuss commercialized IoT paradigms is to highlight research efforts performed in the field of IoT that have been transformed into real-life solutions. The paper also discussed research challenges in the field of IoT to strengthen the research for developing future IoT applications.

A Review on Machine Learning and Deep Learning Perspectives of IDS for IoT: Recent Updates, Security Issues, and Challenges

Journal

Journal NameArchives of Computational Methods in Engineering

Title of PaperA Review on Machine Learning and Deep Learning Perspectives of IDS for IoT: Recent Updates, Security Issues, and Challenges

PublisherSpringer Nature

Volume Number28

Page Number3211-3243

Published YearOctober 2020

ISSN/ISBN No1886-1784

Indexed INScopus, Web of Science, EBSCO

Abstract

Internet of Things (IoT) is widely accepted technology in both industrial as well as academic field. The objective of IoT is to combine the physical environment with the cyber world and create one big intelligent network. This technology has been applied to various application domains such as developing smart home, smart cities, healthcare applications, wireless sensor networks, cloud environment, enterprise network, web applications, and smart grid technologies. These wide emerging applications in variety of domains raise many security issues such as protecting devices and network, attacks in IoT networks, and managing resource-constrained IoT networks. To address the scalability and resource-constrained security issues, many security solutions have been proposed for IoT such as web application firewalls and intrusion detection systems. In this paper, a comprehensive survey on Intrusion Detection System (IDS) for IoT is presented for years 2015–2019. We have discussed various IDS placement strategies and IDS analysis strategies in IoT architecture. The paper discusses various intrusions in IoT, along with Machine Learning (ML) and Deep Learning (DL) techniques for detecting attacks in IoT networks. The paper also discusses security issues and challenges in IoT.

A survey on video-based Human Action Recognition: recent updates, datasets, challenges, and applications

Journal

Journal NameArtificial Intelligence Review

Title of PaperA survey on video-based Human Action Recognition: recent updates, datasets, challenges, and applications

PublisherSpringer Netherlands

Volume Number54

Page Number2259–2322

Published YearSeptember 2020

ISSN/ISBN No1573-7462

Indexed INScopus, Web of Science

Abstract

Human Action Recognition (HAR) involves human activity monitoring task in different areas of medical, education, entertainment, visual surveillance, video retrieval, as well as abnormal activity identification, to name a few. Due to an increase in the usage of cameras, automated systems are in demand for the classification of such activities using computationally intelligent techniques such as Machine Learning (ML) and Deep Learning (DL). In this survey, we have discussed various ML and DL techniques for HAR for the years 2011–2019. The paper discusses the characteristics of public datasets used for HAR. It also presents a survey of various action recognition techniques along with the HAR applications namely, content-based video summarization, human–computer interaction, education, healthcare, video surveillance, abnormal activity detection, sports, and entertainment. The advantages and disadvantages of action representation, dimensionality reduction, and action analysis methods are also provided. The paper discusses challenges and future directions for HAR.

Predicting stock trend using an integrated term frequency–inverse document frequency-based feature weight matrix with neural networks

Journal

Journal NameApplied Soft Computing

Title of PaperPredicting stock trend using an integrated term frequency–inverse document frequency-based feature weight matrix with neural networks

PublisherElsevier

Volume Number96

Page Number1-13

Published YearAugust 2020

ISSN/ISBN No1568-4946

Indexed INScopus, Web of Science

Abstract

The financial market consists of various money-making strategies wherein trading through a stock market is an important example. The complex non-linear behaviors of volatile stock markets attract researchers to study inherent patterns. As the primary motivation for investment in such markets is to gain higher profits, potential stocks are given considerable attention using various weighting strategies that can enhance future returns. Term frequency–inverse document frequency (TF–IDF) is a statistical approach with remarkable applications in the financial domain for information retrieval from textual data; it identifies the importance of a term in the given document of a corpus. However, the application of TF–IDF for the numerical data representation is explored to a limited extent. In this article, we propose to extend the applicability of TF–IDF for the numerical time-series stock market data; we process the data and prepare them to be suitable for TF–IDF. We utilize this statistical approach to derive feature weight matrix from the historical stock market data and further, integrate it with the widely explored neural network architectures namely, backpropagation neural network (BPNN), long short-term memory (LSTM), and gated recurrent unit (GRU) for predicting stock market trend. Simulation results show that the proposed integrated approach using TF–IDF-based feature weight matrix and neural networks outperforms the considered recent approaches. The results are statistically supported with p-value less than .01 using a Wilcoxon signed-rank test; our proposed approach is supported with illustrative examples to develop better understanding of the work. Also, remarks on the conclusions and potential future scope are discussed.

A Comprehensive Survey on Portfolio Optimization, Stock Price and Trend Prediction Using Particle Swarm Optimization

Journal

Journal NameArchives of Computational Methods in Engineering

Title of PaperA Comprehensive Survey on Portfolio Optimization, Stock Price and Trend Prediction Using Particle Swarm Optimization

PublisherSpringer Nature

Volume Number28

Page Number2133–2164

Published YearJune 2020

ISSN/ISBN No1886-1784

Indexed INScopus, Web of Science, EBSCO

Abstract

Stock market trading has been a subject of interest to investors, academicians, and researchers. Analysis of the inherent non-linear characteristics of stock market data is a challenging task. A large number of learning algorithms are developed to study market behaviours and enhance the prediction accuracy; they have been optimized using swarm and evolutionary computation such as particle swarm optimization (PSO); its global optimization ability with continuous data has been exploited in financial domains. Limitations in the existing approaches and potential future research directions for enhancing PSO-based stock market prediction are discussed. This article aims at balancing the economics and computational intelligence aspects; it also analyzes the superiority of PSO for stock portfolio optimization, stock price and trend prediction, and other related stock market aspects along with implications of PSO.

Attack classification using feature selection techniques: a comparative study

Journal

Journal NameJournal of Ambient Intelligence and Humanized Computing

Title of PaperAttack classification using feature selection techniques: a comparative study

PublisherSpringer

Volume Number12

Page Number1249–1266

Published YearJune 2020

ISSN/ISBN No1868-5145

Indexed INScopus, Web of Science, EBSCO

Abstract

The goal of securing a network is to protect the information flowing through the network and to ensure the security of intellectual as well as sensitive data for the underlying application. To accomplish this goal, security mechanism such as Intrusion Detection System (IDS) is used, that analyzes the network traffic and extract useful information for inspection. It identifies various patterns and signatures from the data and use them as features for attack detection and classification. Various Machine Learning (ML) techniques are used to design IDS for attack detection and classification. All the features captured from the network packets do not contribute in detecting or classifying attack. Therefore, the objective of our research work is to study the effect of various feature selection techniques on the performance of IDS. Feature selection techniques select relevant features and group them into subsets. This paper implements Chi-Square, Information Gain (IG), and Recursive Feature Elimination (RFE) feature selection techniques with ML classifiers namely Support Vector Machine, Naïve Bayes, Decision Tree Classifier, Random Forest Classifier, k-nearest neighbours, Logistic Regression, and Artificial Neural Networks. The methods are experimented on NSL-KDD dataset and comparative analysis of results is presented.

A Comprehensive Survey on Energy-Efficient Power Management Techniques

Journal

Journal NameProcedia Computer Science

Title of PaperA Comprehensive Survey on Energy-Efficient Power Management Techniques

PublisherScienceDirect

Volume Number167

Page Number1189-1199

Published YearApril 2020

ISSN/ISBN No1877-0509

Indexed INScopus, Others

Abstract

In the current age of machine intelligence, computer literacy has been achieved in terms of its knowledge and ability of utilization at various stages. As compared to the urge of demanding for high computer functionalities as well as performance, the concern towards the cost in attaining such goals has been limited. The developers try to empower a large number of operations which may consume a large amount of energy. The power consumption has been perceived as an important aspect for the stability and growth of an economy of the country; it has also been recognized as one of the factors that impact the environment. This article has considered the prime implication of energy-efficient power management techniques; it discusses the necessity of adopting the energy-aware computer and reviews the existing works on relevant components. This article may be helpful to attain the essentials of green computing.

A Review of the Advancement in Intrusion Detection Datasets

Journal

Journal NameProcedia Computer Science

Title of PaperA Review of the Advancement in Intrusion Detection Datasets

PublisherScienceDirect

Volume Number167

Page Number636-645

Published YearApril 2020

ISSN/ISBN No1877-0509

Indexed INScopus, Others

Abstract

The research in the field of Cyber Security has raised the need to address the issue of cybercrimes that have caused the requisition of the intellectual properties such as break down of computer systems, impairment of important data, compromising the confidentiality, authenticity, and integrity of the user. Considering these scenarios, it is essential to secure the computer systems and the user using an Intrusion Detection System (IDS). The performance of IDS studied by developing an IDS dataset, consisting of network traffic features to learn the attack patterns. Intrusion detection is a classification problem, wherein various Machine Learning (ML) and Data Mining (DM) techniques applied to classify the network data into normal and attack traffic. Moreover, the types of network attacks changed over the years, and therefore, there is a need to update the datasets used for evaluating IDS. This paper list the different IDS datasets used for the evaluation of IDS model. The paper presents an overview of the ML and DM techniques used for IDS along with the discussion on CIC-IDS-2017 and CSE-CIC-IDS-2018. These are recent datasets consisting of network attack features and include new attacks categories. This paper discusses the recent advancement in the IDS datasets that can be used by various research communities as the manifesto for using the new IDS datasets for developing efficient and effective ML and DM based IDS.

CREST: Cross-Reference to Exchange-based Stock Trend Prediction using Long Short-Term Memory

Journal

Journal NameProcedia Computer Science

Title of PaperCREST: Cross-Reference to Exchange-based Stock Trend Prediction using Long Short-Term Memory

PublisherScienceDirect

Volume Number167

Page Number616-625

Published YearApril 2020

ISSN/ISBN No1877-0509

Indexed INScopus, Others

Abstract

Due to a large number of tradings in the stock market, it generally experiences fluctuations throughout the day. Such oscillations influence market capitals of the companies listed on a stock exchange. Hence, in order to take suitable trading steps, prediction of the future stock price as well as trend direction becomes a crucial task. National Stock Exchange (NSE) and Bombay Stock Exchange (BSE) cover the largest market capitalization in India. A company’s shares are traded according to the stock exchange it is listed on; it can also be listed on multiple exchanges. Various approaches have tried to predict stock markets in terms of future indices, price movement, and returns perspectives, however, analyzing stocks of a company, which is listed on multiple exchanges, has been limited to the financial perspectives. In this article, a cross-reference to exchange-based stock trend (CREST) prediction method is proposed using long short-term memory (LSTM). The daily stock prices of Wipro Limited (WIPRO) company, which is listed on NSE as well as BSE, have been collected and the stock price movement of WIPRO in one exchange has been analyzed for predicting the trend in the other exchange. To identify the applicability of our approach, CREST has also experimented with Infosys Limited and Larsen & Toubro Infotech Limited companies. The performance is evaluated using root-mean-square error and directional accuracy along with precision, recall, and F-measure for the results of all three companies.

Role of swarm and evolutionary algorithms for intrusion detection system: A survey

Journal

Journal NameSwarm and Evolutionary Computation

Title of PaperRole of swarm and evolutionary algorithms for intrusion detection system: A survey

PublisherScienceDirect

Volume Number53

Page Number1-34

Published YearMarch 2020

ISSN/ISBN No2210-6502

Indexed INScopus, Web of Science

Abstract

The growth of data and categories of attacks, demand the use of Intrusion Detection System(IDS) effectively using Machine Learning (ML) and Deep Learning (DL) techniques. Apart from the ML and DL techniques, Swarm and Evolutionary (SWEVO) Algorithms have also shown significant performance to improve the efficiency of the IDS models. This survey covers SWEVO-based IDS approaches such as Genetic Algorithm(GA), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Artificial Bee Colony Optimization(ABC), Firefly Algorithm (FA), Bat Algorithm (BA), and Flower Pollination Algorithm (FPA). The paper also discusses applications of the SWEVO in the field of IDS along with challenges and possible future directions.

Sentiment analysis: an empirical comparison between various training algorithms for artificial neural network

Journal

Journal NameInternational Journal of Innovative Computing and Applications

Title of PaperSentiment analysis: an empirical comparison between various training algorithms for artificial neural network

PublisherInderscience Publishers (IEL)

Volume Number11

Page Number9-29

Published YearFebruary 2020

ISSN/ISBN No1751-6498

Indexed INScopus, Others

VIKAS: a new virtual keyboard-based simple and efficient text CAPTCHA verification scheme

Journal

Journal NameInternational Journal of Information and Computer Security

Title of PaperVIKAS: a new virtual keyboard-based simple and efficient text CAPTCHA verification scheme

PublisherINDERSCIENCE

Volume Number12

Page Number90-105

Published YearDecember 2019

ISSN/ISBN No1744-1773

Indexed INScopus, Others

A Comprehensive Survey on Travel Recommender Systems

Journal

Journal NameArchives of Computational Methods in Engineering

Title of PaperA Comprehensive Survey on Travel Recommender Systems

PublisherSpringer Netherlands

Volume Number27

Page Number1545–1571

Published YearOctober 2019

ISSN/ISBN No1886-1784

Indexed INScopus, EBSCO

Abstract

Travelling is a combination of journey, transportation, travel-time, accommodation, weather, events, and other aspects which are likely to be experienced by most of the people at some point in their life. To enhance such experience, we generally look for assistance in planning a tour. Today, the information available on tourism-related aspects on the Internet is boundless and exploring suitable travel package/product/service may be time-consuming. A recommender system (RS) can assist for various tour-related queries such as top destinations for summer vacation, preferable climate conditions for tracking, the fastest way to transport, or photography assistance for specific destinations. In this survey, we have presented a pervasive review on travel and associated factors such as hotels, restaurants, tourism package and planning, and attractions; we have also tailored recommendations on a tourist’s diverse requirements such as food, transportation, photography, outfits, safety, and seasonal preferences. We have classified travel-based RSs and presented selection criteria, features, and technical aspects with datasets, methods, and results. We have briefly supplemented research articles from diverse facets; various frameworks for a travel-based RS are discussed. We believe our survey would introduce a state-of-the-art travel RS; it may be utilized to solve the existing limitations and extend its applicability.

Travelling Salesman Problem: An Empirical Comparison Between ACO, PSO, ABC, FA and GA

Book Chapter

Book NameAdvances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Author Name Kinjal Chaudhari, Ankit Thakkar

Page Number397-405

Chapter TitleTravelling Salesman Problem: An Empirical Comparison Between ACO, PSO, ABC, FA and GA

Published YearSeptember 2019

ISSN/ISBN No978-981-13-6000-8

Indexed INScopus

A Voting-Based Sentiment Classification Model

Book Chapter

Book Name Advances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Author NameDhara Mungra, Anjali Agrawal, Ankit Thakkar

Page Number 551-558

Chapter TitleA Voting-Based Sentiment Classification Model

Published YearAugust 2019

ISSN/ISBN No978-981-13-8617-6

Indexed INScopus

Survey on handwriting-based personality trait identification

Journal

Journal NameExpert Systems with Applications

Title of PaperSurvey on handwriting-based personality trait identification

PublisherElsevier

Volume Number124

Page Number282-308

Published YearJune 2019

ISSN/ISBN No0957-4174

Indexed INScopus, Web of Science

Abstract

Personality is a combination of various characteristics and qualities of an individual. It may be affected by the growth and evolution of one’s values, attributes, relationships with the community, personal memories of life events, habits, and skills. Behaviours and decisions of an individual are largely directed by his/her personality. Identification of such a personality trait can be performed b

A Survey on Intelligent Transportation System Using Internet of Things

Book Chapter

Book Name Advances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Author NamePalak Patel, Zunnun Narmawala, Ankit Thakkar

Page Number231-240

Chapter TitleA Survey on Intelligent Transportation System Using Internet of Things

Published YearMay 2019

Indexed INScopus

Necessary Precautions in Cognitive Tutoring System

Book Chapter

Book Name Advances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Author NameKevin Vora, Shashvat Shah, Harshad Harsoda, Jeel Sheth, Ankit Thakkar

Page Number 445-452

Chapter TitleNecessary Precautions in Cognitive Tutoring System

Published YearJanuary 2019

ISSN/ISBN No978-981-13-8617-6

Indexed INScopus

The Fog Computing Paradigm: A Rising Need of IoT World

Book Chapter

Book NameAdvances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Author NameShivani Desai, Ankit Thakkar

Page Number387-393

Chapter TitleThe Fog Computing Paradigm: A Rising Need of IoT World

Published YearOctober 2018

ISSN/ISBN No978-981-13-1609-8

Indexed INScopus

Emotion Recognition from Sensory and Bio-Signals: A Survey

Book Chapter

Book Name Advances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Author NameKevin Vora, Shashvat Shah, Harshad Harsoda, Jeel Sheth, Seema Agarwal, Ankit Thakkar, Sapan H Mankad

Page Number345-355

Chapter TitleEmotion Recognition from Sensory and Bio-Signals: A Survey

Published YearOctober 2018

ISSN/ISBN No978-981-13-1609-8

Indexed INScopus

A Simple and Efficient Text-Based CAPTCHA Verification Scheme Using Virtual Keyboard

Book Chapter

Book Name Smart Innovation, Systems and Technologies

PublisherSpringer, Cham

Author NameKajol Patel and Ankit Thakkar

Page Number121-126

Chapter TitleA Simple and Efficient Text-Based CAPTCHA Verification Scheme Using Virtual Keyboard

Published YearAugust 2017

ISSN/ISBN No978-3-319-63644-3

Indexed INScopus, Others

DEAL: Distance and Energy Based Advanced LEACH Protocol

Book Chapter

Book Name Smart Innovation, Systems and Technologies

PublisherSpringer, Cham

Author NameAnkit Thakkar

Page Number370-376

Chapter TitleDEAL: Distance and Energy Based Advanced LEACH Protocol

Published YearAugust 2017

ISSN/ISBN No978-3-319-63644-3

Indexed INScopus, Others

An improved advanced low energy adaptive clustering hierarchy for a dense wireless sensor network

Conference

Title of PaperAn improved advanced low energy adaptive clustering hierarchy for a dense wireless sensor network

Proceeding Name2016 International Conference on Communication and Electronics Systems (ICCES), IEEE

PublisherIEEE

Author NameAnkit Thakkar

Page Number1-6

Published YearOctober 2016

ISSN/ISBN No978-1-5090-1066-0

Indexed INScopus, Others

An improved modified LEACH-C algorithm for energy efficient routing in Wireless Sensor Networks

Journal

Journal NameNirma University Journal of Engineering and Technology (NUJET)

Title of PaperAn improved modified LEACH-C algorithm for energy efficient routing in Wireless Sensor Networks

PublisherNirma University

Volume Number4

Page Number1-5

Published YearDecember 2015

ISSN/ISBN No2231-2870

Indexed INOthers

A new Bollinger Band based energy efficient routing for clustered wireless sensor network

Journal

Journal NameApplied Soft Computing

Title of PaperA new Bollinger Band based energy efficient routing for clustered wireless sensor network

PublisherElsevier

Volume Number32

Page Number144-153

Published YearJuly 2015

ISSN/ISBN No1568-4946

Indexed INScopus

Abstract

Designing of scalable routing protocol with prolonged network lifetime for a wireless sensor network (WSN) is a challenging task. WSN consists of large number of power, communication and computational constrained inexpensive nodes. It is difficult to replace or recharge battery of a WSN node when operated in a hostile environment. Cluster based routing is one of the techniques to provide prolonged network lifetime along with scalability. This paper proposes a technique for cluster formation derived from “Grid based method”. We have also proposed a new decentralized cluster head (CH) election method based on Bollinger Bands. Bollinger Bands are based on Upper Bollinger Band and Lower Bollinger Band, both of these bands are extremely reactive to any change in the inputs provided to them. We have used this property of Bollinger Bands to elect CH. Simulation result shows significant improvement in the network lifetime in comparison with other decentralized and ant based algorithms.

SKIP: a novel self-guided adaptive clustering approach to prolong lifetime of wireless sensor networks

Book Chapter

Book NameCommunication and Computing Systems

PublisherTaylor & Francis Group, London

Author NameAnkit Thakkar

Page Number335-340

Chapter TitleSKIP: a novel self-guided adaptive clustering approach to prolong lifetime of wireless sensor networks

Published YearFebruary 2015

ISSN/ISBN No978-1-138-02952-1

Indexed INScopus

Abstract

Wireless Sensor Network (WSN) consists of energy constraint sensor nodes, and it is difficult to replace or recharge batteries of these nodes when they operate in hostile environments. Hence, prolonging the lifetime of WSN nodes is an important issue for any WSN. Cluster based routing techniques improve the lifetime of WSNs, wherein longer stability and shorter instability periods are important aspects to measure network lifetime. Stable period ensures reliability of the data received from the network, as all nodes are alive during this period. This paper discusses a novel distributed adaptive clustering approach, Skip that guides every node to take part in the Cluster Head (CH) election process or not for the current epoch, based on residual energy of a node. Extensive simulations have been carried out to compare the proposed approach with prominent clustering techniques such as Low Energy Adaptive Clustering Hierarchy (LEACH), Stable Election Protocol (SEP) and enhanced Stable Election Protocol (SEP-E). Simulation results show that the proposed approach outperforms to LEACH, SEP and SEP-E protocols. The proposed approach Skip provides longer stability and does not deteriorate instability period. The performance of Skip is also validated using statistical test.

Cluster Head Election for Energy and Delay Constraint Applications of Wireless Sensor Network

Journal

Journal NameIEEE Sensors Journal

Title of PaperCluster Head Election for Energy and Delay Constraint Applications of Wireless Sensor Network

PublisherIEEE

Volume Number14

Page Number 2658 - 2664

Published YearAugust 2014

ISSN/ISBN No1530-437X

Indexed INScopus, Web of Science

Abstract

Designing of a multi-hop Wireless Sensor Network (WSN) depends upon the requirements of the underlying sensing application. The main objective of WSNs is to monitor physical phenomenon of interest in a given region of interest using sensors and provide collected data to sink. The WSN is made of a large number of energy, communication, and computational constraint nodes, to overcome energy constrains, replacing or recharging the batteries of the WSN nodes is an impossible task, once they are deployed in a hostile environment. Therefore, to keep the network alive as long as possible, communication between the WSN nodes must be done with load balancing. Time critical applications like forest fire detection, battle field monitoring demands reception of data by the sink with the bounded delay to avoid disasters. Hence, there is a need to design a protocol which enhances the network lifetime and provides information to the sink with a bounded delay. This paper will address this problem and solution. In this paper, a routing algorithm is proposed by introducing Energy Delay Index for Trade-off (EDIT) to optimize both objectives-energy and delay. The EDIT is used to select cluster heads and “next hop” by considering energy and/or delay requirements of a given application. Proposed approach is derived using two different aspects of distances between a node and the sink named Euclidean distance and Hop-count, and further prove using realistic parameters of radio to get data closest to the test bed implementation. The results aspire to give sufficient insights to others before doing test bed implementation.

Alive nodes based improved low energy adaptive clustering hierarchy for wireless sensor network

Book Chapter

Book Name Smart Innovation, Systems and Technologies

PublisherSpringer, Cham

Author NameAnkit Thakkar, Ketan Kotecha

Page Number51-58

Chapter TitleAlive nodes based improved low energy adaptive clustering hierarchy for wireless sensor network

Published YearApril 2014

ISSN/ISBN No978-3-319-07350-7

Indexed INScopus, Others

A new hybrid method for face recognition

Conference

Title of PaperA new hybrid method for face recognition

Proceeding NameEngineering (NUiCONE), 2013 Nirma University International Conference on

PublisherIEEE

Author NameAnkit Thakkar, N Jivani, J Padasumbiya, CI Patel

Published YearNovember 2013

ISSN/ISBN No2375-1282

Indexed INScopus, Others

Aggregate features approach for texture analysis

Conference

Title of PaperAggregate features approach for texture analysis

Proceeding Name2012 Nirma University International Conference on Engineering (NUiCONE)

PublisherIEEE

Author NameRipal Patel, Chirag I Patel, Ankit Thakkar

Published YearDecember 2012

ISSN/ISBN No2375-1282

Indexed INScopus, Others

Power Aware Scheduling for Adhoc sensor Network Nodes

Conference

Title of PaperPower Aware Scheduling for Adhoc sensor Network Nodes

Proceeding Name 2009 3rd International Conference on Signal Processing and Communication Systems

PublisherIEEE

Author NameAnkit Thakkar, SN Pradhan

Published YearSeptember 2009

ISSN/ISBN No978-1-4244-4473-1

Indexed INScopus, Others

Resource allocation in V2X communication: State-of-the-art and research challenges

Journal

Journal NamePhysical Communication, Elsevier [Impact Factor: 2.2]

Title of PaperResource allocation in V2X communication: State-of-the-art and research challenges

PublisherElsevier

Volume Number64

Published YearApril 2024

ISSN/ISBN No1874-4907

Indexed INScopus, Web of Science

Blockchain-Based Decentralized Application for Telesurgery in Metaverse Environment

Conference

Title of PaperBlockchain-Based Decentralized Application for Telesurgery in Metaverse Environment

Proceeding Name2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence)

PublisherIEEE

Author NameSatya Chaudhary, Yogi Patel, Sachi Chaudhary, Rajesh Gupta, Riya Kakkar, Sudeep Tanwar, Anuja Nair

Year , VenueJanuary 2024 , Noida, India

Page Number492-497

ISSN/ISBN No2766-421X

Indexed INScopus

Blockchain-Envisioned Onion Routing Framework for Internet of Vehicles Communication toward 6G

Journal

Journal NameIEEE Internet of Things Magazine

Title of PaperBlockchain-Envisioned Onion Routing Framework for Internet of Vehicles Communication toward 6G

PublisherIEEE

Volume Number7

Published YearJanuary 2024

AI-Based Accident Severity Detection Scheme for V2X Communication Beyond 5G Networks

Conference

Title of PaperAI-Based Accident Severity Detection Scheme for V2X Communication Beyond 5G Networks

Proceeding Name2023 IEEE International Conference on Communications Workshops (ICC Workshops)

PublisherIEEE

Author NameAnuja Nair, Dr. Sudeep Tanwar

Organization1002-1007

Year , VenueOctober 2023 , Rome, Italy

ISSN/ISBN No2694-2941

Indexed INScopus

EEG‐based biometric authentication system using convolutional neural network for military applications

Journal

Journal NameSecurity and Privacy, Wiley [ [Impact Factor: 1.9]

Title of PaperEEG‐based biometric authentication system using convolutional neural network for military applications

PublisherWiley

Volume Number7

Published YearOctober 2023

ISSN/ISBN No2475-6725

Indexed INScopus, Web of Science

MetaHate: AI‐based hate speech detection for secured online gaming in metaverse using blockchain

Journal

Journal NameSecurity and Privacy, Wiley [ [Impact Factor: 1.9]

Title of PaperMetaHate: AI‐based hate speech detection for secured online gaming in metaverse using blockchain

PublisherWiley

Volume Number7

Published YearSeptember 2023

ISSN/ISBN No2475-6725

Indexed INScopus, Web of Science

CNN and Bidirectional GRU-Based Heartbeat Sound Classification Architecture for Elderly People

Journal

Journal NameMathematics, MDPI [Impact Factor: 2.592]

Title of PaperCNN and Bidirectional GRU-Based Heartbeat Sound Classification Architecture for Elderly People

PublisherMultidisciplinary Digital Publishing Institute

Volume Number11

Page Number1365

Published YearMarch 2023

Indexed INScopus, Web of Science

EmReSys: AI-based Efficient Employee Ranking and Recommender System for Organizations

Conference

Title of PaperEmReSys: AI-based Efficient Employee Ranking and Recommender System for Organizations

Proceeding Name2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

PublisherIEEE

Author NameDhairya Jadav, Dev Patel, Somya Thacker, Anuja Nair, Rajesh Gupta, Nilesh Kumar Jadav, Sudeep Tanwar

Year , VenueFebruary 2023 , Greater Noida, India

Page Number440-445

Indexed INScopus

Software Effort Estimation using Machine Learning Algorithms

Conference

Title of PaperSoftware Effort Estimation using Machine Learning Algorithms

Proceeding Name2022 6th International Conference on Electronics, Communication and Aerospace Technology

PublisherIEEE

Author NameRuju Shah, Vrunda Shah, Anuja R Nair, Tarjni Vyas, Shivani Desai, Sheshang Degadwala

Year , VenueJanuary 2023 , Coimbatore, India

Page Number1-8

Indexed INScopus

Fusion of blockchain and IoT in scientific publishing: Taxonomy, tools, and future directions

Journal

Journal NameFuture Generation Computer Systems, Elsevier [Impact Factor: 7.307]

Title of PaperFusion of blockchain and IoT in scientific publishing: Taxonomy, tools, and future directions

PublisherNorth-Holland

Volume Number142

Page Number248-275

Published YearJanuary 2023

Indexed INScopus, Web of Science

Blockchain-Assisted Onion Routing Protocol for Internet of Underwater Vehicle Communication

Journal

Journal NameIEEE Internet of Things Magazine

Title of PaperBlockchain-Assisted Onion Routing Protocol for Internet of Underwater Vehicle Communication

PublisherIEEE

Volume Number5

Page Number30-35

Published YearDecember 2022

Blockchain and AI-based Secure Onion Routing Framework for Data Dissemination in IoT Environment Underlying 6G Networks

Conference

Title of PaperBlockchain and AI-based Secure Onion Routing Framework for Data Dissemination in IoT Environment Underlying 6G Networks

Proceeding Name2022 Sixth International Conference on Smart Cities, Internet of Things and Applications (SCIoT)

PublisherIEEE

Author NameRajesh Gupta, Nilesh Kumar Jadav, Anuja Nair, Sudeep Tanwar, Hossein Shahinzadeh

Year , VenueNovember 2022 , Mashhad, Iran

Page Number1-6

Indexed INScopus

AI‐driven network softwarization scheme for efficient message exchange in IoT environment beyond 5G

Journal

Journal NameInternational Journal of Communication Systems, Wiley [Impact Factor: 1.882]

Title of PaperAI‐driven network softwarization scheme for efficient message exchange in IoT environment beyond 5G

PublisherJohn Wiley & Sons Ltd

Published YearSeptember 2022

Indexed INScopus, Web of Science

A taxonomy on smart healthcare technologies: security framework, case study, and future directions

Journal

Journal NameJournal of Sensors, Hindawi [Impact Factor: 2.336]

Title of PaperA taxonomy on smart healthcare technologies: security framework, case study, and future directions

PublisherHindawi

Volume Number2022

Published YearJuly 2022

AI-empowered Secure Data Communication in V2X Environment with 6G Network

Conference

Title of PaperAI-empowered Secure Data Communication in V2X Environment with 6G Network

Proceeding NameIEEE INFOCOM 2022-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

PublisherIEEE

Author NameAnuja R Nair, Nilesh Kumar Jadav, Rajesh Gupta, Sudeep Tanwar

Year , VenueJune 2022 , New York, NY, USA

Page Number1-6

Indexed INScopus

FAIR: A blockchain-based vaccine distribution scheme for pandemics

Conference

Title of PaperFAIR: A blockchain-based vaccine distribution scheme for pandemics

Proceeding Name2021 IEEE Globecom Workshops (GC Wkshps)

PublisherIEEE

Author NameAnuja R Nair, Rajesh Gupta, Sudeep Tanwar

Year , VenueJanuary 2022 , Madrid, Spain

Page Number1-6

Indexed INScopus

Insights of Deep Learning Applications

Conference

Title of PaperInsights of Deep Learning Applications

Proceeding Name2021 5th International Conference on Electronics, Communication and Aerospace Technology (ICECA)

PublisherIEEE

Author NameHet Shah, Shivani Desai, Tarjni Vyas, Anuja Nair, Sheshang Degadwala

Year , VenueJanuary 2022 , Coimbatore, India

Page Number1355-1360

Indexed INScopus

Intrusion Detection System-Deep Learning Perspective

Conference

Title of PaperIntrusion Detection System-Deep Learning Perspective

Proceeding Name2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS)

PublisherIEEE

Author NameShivani Desai, Bhavyang Dave, Tarjni Vyas, Anuja R Nair

Year , VenueApril 2021 , Coimbatore, India

Page Number1193-1198

Indexed INScopus

Blockchain‐assisted secure UAV communication in 6G environment: Architecture, opportunities, and challenges

Journal

Journal NameIET communications [Impact Factor: 1.345]

Title of PaperBlockchain‐assisted secure UAV communication in 6G environment: Architecture, opportunities, and challenges

PublisherThe Institution of Engineering and Technology

Volume Number15

Page Number1352-1367

Published YearFebruary 2021

Indexed INScopus, Web of Science

Fog Computing Architectures and Frameworks for Healthcare 4.0

Book Chapter

Book NameFog Computing for Healthcare 4.0 Environments

PublisherSpringer, Cham

Author NameAnuja R Nair, Sudeep Tanwar

Page Number55-78

Chapter TitleFog Computing Architectures and Frameworks for Healthcare 4.0

Published YearAugust 2020

Indexed INScopus

Performance Analysis of Video On-demand and Live Video Streaming using Cloud based Services

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperPerformance Analysis of Video On-demand and Live Video Streaming using Cloud based Services

Volume Number21

Page Number479-496

Published YearAugust 2020

Indexed INScopus

Resource allocation in cloud computing

Book Chapter

Book NameInstant Guide to Cloud Computing

PublisherBPB Publications

Author NameVivek Kumar Prasad, Anuja Nair, Sudeep Tanwar

Page Number343-376

Chapter TitleResource allocation in cloud computing

Published YearSeptember 2019

Implementation of Word Sense Disambiguation on Hadoop Using Map-Reduce

Book Chapter

Book NameInformation and Communication Technology for Intelligent Systems

PublisherSpringer, Singapore

Author NameSuresh Chandra Satapathy, Amit Joshi

Page Number573-580

Chapter TitleImplementation of Word Sense Disambiguation on Hadoop Using Map-Reduce

Published YearDecember 2018

ISSN/ISBN No978-981-13-1741-5

Indexed INScopus

Abstract

In Natural Language Processing, it is essential to find a correct sense of sentences or document is written for these type of problem is called word sense disambiguation problem. Currently, any machine learning application based on natural language processing requires to solve this type of problem. To identify the correct sense, pywsd (Python implementations of word sense disambiguation technologi

MobiCloud: Performance Improvement, Application Models and Security Issues

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer

Author NameSuresh Chandra Satapathy, Amit Joshi

Page Number466-472

Chapter TitleMobiCloud: Performance Improvement, Application Models and Security Issues

Published YearAugust 2017

ISSN/ISBN No2190-3018

Indexed INScopus

Abstract

Recent years have seen an exponential increase in cloud computing for services such as high computational capabilities, vast storage, applications etc. that they provide. Moreover, today’s world is a constant shift from desktop or laptop devices towards handheld smartphones because of the wide range of applications that are supported. This paper discusses the present state of cloud computing for m

Survey on Cluster Based Data Aggregation in Wireless Sensor Network

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperSurvey on Cluster Based Data Aggregation in Wireless Sensor Network

PublisherInternational Journal of Advanced Research in Computer Science

Volume Number8

Page Number311-314

Published YearMay 2017

ISSN/ISBN No0976-5697

Indexed INUGC List

Software Engineering Aided By Multimedia and Hypermedia

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperSoftware Engineering Aided By Multimedia and Hypermedia

Volume Number7

Page Number101-107

Published YearJune 2016

ISSN/ISBN No0973-7391

Indexed INUGC List

AdWords : A Study of Usage and Tools

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperAdWords : A Study of Usage and Tools

Volume Number7

Page Number95-99

Published YearFebruary 2016

ISSN/ISBN No0973-7391

Indexed INUGC List

Multi-agent- based Decentralized Residential Energy Management using Deep Reinforcement Learning

Journal

Journal NameJournal of Building Engineering

Title of PaperMulti-agent- based Decentralized Residential Energy Management using Deep Reinforcement Learning

PublisherElsevier

Page Number1-15

Published YearApril 2024

Indexed INScopus, PubMed, Web of Science

ANN- driven Federated Learning for Heart Stroke Prediction in Healthcare 4.0 Underlying 5G

Journal

Journal NameConcurrency and Computation: Practice and Experience

Title of PaperANN- driven Federated Learning for Heart Stroke Prediction in Healthcare 4.0 Underlying 5G

Page Number1-12

Published YearSeptember 2023

Indexed INScopus, PubMed, Web of Science

Blockchain Adoption to Secure the Food Industry: Opportunities and Challenges

Journal

Journal NameSustainability

Title of PaperBlockchain Adoption to Secure the Food Industry: Opportunities and Challenges

PublisherMDPI

Volume Number14

Page Number 7036-7061

Published YearJune 2022

ISSN/ISBN No20711050

Indexed INScopus, PubMed, Web of Science, ABDC, Indian citation Index, EBSCO

GrAb: A Deep Learning-Based Data-Driven Analytics Scheme for Energy Theft Detection

Journal

Journal NameSensor

Title of PaperGrAb: A Deep Learning-Based Data-Driven Analytics Scheme for Energy Theft Detection

PublisherMDPI

Volume Number22

Page Number 4048-4071

Published YearMay 2022

ISSN/ISBN No1424-8220

Indexed INScopus, PubMed, Web of Science, ABDC, Indian citation Index, EBSCO

AI-Empowered Recommender System for Renewable Energy Harvesting in Smart Grid System

Journal

Journal NameIEEE Access

Title of PaperAI-Empowered Recommender System for Renewable Energy Harvesting in Smart Grid System

PublisherIEEE

Volume Number10

Page Number24316- 24326

Published YearFebruary 2022

ISSN/ISBN No2169-3536

Indexed INScopus, PubMed, Web of Science, ABDC, Indian citation Index, EBSCO, Others

A Reinforcement-Learning-Based Secure Demand Response Scheme for Smart Grid System

Journal

Journal NameInternet of Things Journal

Title of PaperA Reinforcement-Learning-Based Secure Demand Response Scheme for Smart Grid System

PublisherIEEE

Volume Number9

Page Number2180 - 2191

Published YearJune 2021

ISSN/ISBN No2327-4662

Indexed INScopus, PubMed, Web of Science, ABDC, Indian citation Index, EBSCO

A Permissioned Blockchain Approach for Real-Time Embedded Control Systems

Conference

Title of PaperA Permissioned Blockchain Approach for Real-Time Embedded Control Systems

Proceeding Name Lecture Notes in Computer Science ((LNAI,volume 13924))

PublisherSpringerLink

Author NamePronaya Bhattacharya, Sudip Chatterjee, Rajan Datt, Ashwin Verma, Pushan Kumar Dutta

Organization Mining Intelligence and Knowledge Exploration

Year , VenueJune 2023 , Springer Nature Switzerland

Page Numberpp 341–352

Indexed INScopus

Abstract

In real-time embedded control (RTEC) systems, sensors collect data which is processed and sent to different control nodes. RTEC deployments have numerous applications in diverse verticals like industrial control, healthcare, and vehicular networks. In such cases, a trusted and verifiable control is required, particularly when the data is kept in a distributed manner, and is exchanged over open wireless channels. Thus, blockchain (BC) is a viable option to store the sensor data between RTEC systems, which maintains a trusted ledger of associated operations. Existing works have not focused on the integration of BC in RTEC systems. Motivated by the gap, the paper presents a systematic approach to integrating BC in RTEC ecosystems. We present a reference architecture and discuss the device registration, the hyperledger fabric set up, and the task offloading strategy between edge gateways and cloud nodes, and present the performance analysis of the architecture. The discussion of open issues and challenges also highlights the practical implications of the approach, emphasizing its importance for future deployments of real-time embedded control systems.

Blockchain-based Federated Learning in UAVs Beyond 5G Networks: A Solution Taxonomy and Future Directions

Journal

Journal NameIEEE Access

Title of PaperBlockchain-based Federated Learning in UAVs Beyond 5G Networks: A Solution Taxonomy and Future Directions

PublisherIEEE

Volume NumberEarly Access

Page Number1-1

Published YearMarch 2022

ISSN/ISBN No2169-3536

Indexed INScopus, PubMed, Web of Science

Abstract

Recently, unmanned aerial vehicles (UAVs) have gained attention due to increased use-cases in healthcare, monitoring, surveillance, and logistics operations. UAVs mainly communicate with mobile base stations, ground stations (GS), or networked peer UAVs, known as UAV swarms. UAVs communicate with GS, or UAV swarms, over wireless channels to support mission-critical operations. Communication latency, bandwidth, and precision are of prime importance in such operations. With the rise of data-driven applications, fifth-generation (5G) networks would face bottlenecks to communicate at near-real-time, at low latency and improved coverage. Thus, researchers have shifted towards network designs that incorporate beyond 5G (B5G) networks for UAV designs. However, UAVs are resource-constrained, with limited power and battery, and thus centralized cloud-centric models are not suitable. Moreover, as exchanged data is through open channels, privacy and security issues exist. Federated learning (FL) allows data to be trained on local nodes, preserving privacy and improving network communication. However, sharing of local updates is required through a trusted consensus mechanism. Thus, blockchain (BC)-based FL schemes for UAVs allow trusted exchange of FL updates among UAV swarms and GS. To date, limited research has been carried out on the integration of BC and FL in UAV management. The proposed survey addresses the gap and presents a solution taxonomy of BC-based FL in UAVs for B5G networks due to the open problem. This paper presents a reference architecture and compares its potential benefits over traditional BC-based UAV networks. Open issues and challenges are discussed, with possible future directions. Finally, we present a logistics case study of BC-based FL-oriented UAVs in 6G networks. The survey aims to aid researchers in developing potential UAV solutions with the key integrating principles over a diverse set of application verticals.

Statistical analysis on the COVID-19 infection spread in United State of America: a Prophet Forecasting Model

Conference

Title of PaperStatistical analysis on the COVID-19 infection spread in United State of America: a Prophet Forecasting Model

Proceeding Name2021 Sixth International Conference on Image Information Processing (ICIIP)

PublisherIEEE

Author NameS.R. Mishra

OrganizationNirma University

Year , VenueFebruary 2022 , Shimla, India

Page Number1-1

ISSN/ISBN No978-1-6654-3362-4

Abstract

In the current scenario, the pandemic COVID-19 spread globally starting from the end of 2019, in Wuhan, a city of China. As per the current data taken up to 26th of May 2020, globally there are a huge number of people are affected (Approximately 3 billions) by the pandemic. Though the entire data varies depending upon the several parameters like, population size, congestion of area, climate condition, awareness of peoples etc. we have only analyzes on the data of the country USA. The entire data is partitioned into various categories such as: infected rate, mortality rate. A statistical analysis is prepared to analyze or predict the future strategies of the infected rate as well as the removal (Death/cured) rate. The growth of both the infected and the removed can be predicted with the same observed data taken on daily basis from 15th February 2020. We retrieved these data from an authenticate source provided by "Worldometer" (http://www.worldometers.info). However, Prophet Forecasting Model (PMF) is used to simulate and discussed for the prediction of the mortality rate, active rate due to pandemic COVID-19. The proposed method is also tested for accuracy of model via cross validation method.

Blockchain-enabled secure Internet of Vehicles: A solution taxonomy, architecture, and future directions In Book

Book Chapter

Book NameBlockchain for Information Security and Privacy

PublisherCRC Press

Author NameZuhair

Page Number1-1

Chapter TitleBlockchain-enabled secure Internet of Vehicles: A solution taxonomy, architecture, and future directions In Book

Published YearJanuary 2022

ISSN/ISBN No9781000483093

Amalgamation of blockchain and 6G-envisioned responsive edge orchestration in future cellular V2X ecosystems: Opportunities and Challenges

Journal

Journal NameWiley Transactions of Emerging Telecommunication Technologies

Title of PaperAmalgamation of blockchain and 6G-envisioned responsive edge orchestration in future cellular V2X ecosystems: Opportunities and Challenges

PublisherWiley

Volume NumberEarly Access

Page Number1-1

Published YearDecember 2021

Indexed INScopus, PubMed, Web of Science

Abstract

In modern decentralized cellular-vehicle-to-anything (C-V2X) infrastructures, connected autonomous smart vehicles (CASVs) exchange vehicular information with peer CASVs. To leverage responsive communication, sensors deployed in CASVs communicate through responsive edge computing (REC) infrastructures to support device-to-device- (D2D) based communication. To support low-latency, high-bandwidth, dense mobility, and high availability, researchers worldwide have proposed efficient 5G REC infrastructures to end vehicular users (VU). However, with the growing number of sensor units, intelligent automation, dense sensor integration at massive ultra-low latency is required. To address the issue, the focus has shifted toward sixth-generation (6G)-based intelligent C-V2X orchestration. However, the sensor data is exchanged through open channels, and thus trust and privacy among C-V2X nodes is a prime concern. Thus, blockchain (BC) is a potential solution to allow immutable exchange ledgers among CASV sensor units for secure data exchange. With this motivation, the proposed survey integrates BC and 6G-leveraged REC in C-V2X to address the issues of fifth-generation (5G)-REC through immutable, verified, and chronological timestamped data exchanged through 6G-envisioned terahertz (THz) channels, at high mobility, extremely low latency, and high availability. The survey also presents the open issues and research challenges in the 6G-envisioned BC-enabled REC C-V2X ecosystems via a proposed framework. A case study 6Edge is presented for smart 6G intelligent edge integration with BC-based ledgers. Finally, the concluding remarks and future direction of research are proposed. Thus, the proposed survey forms a guideline for automotive stakeholders, academicians, and researchers to explore the various opportunities of the possible integration in more significant detail.

Blockchain based Federated cloud environment-Issues and Challenges

Book Chapter

Book NameBlockchain for Information Security and Privacy

PublisherCRC Press

Author NameAshwin Verma; Pronaya Bhattacharya; Mohammad Zuhair; Umesh Bodkhe, Ram kishan Dewangan

Page Number1-1

Chapter TitleBlockchain based Federated cloud environment-Issues and Challenges

Published YearNovember 2021

NyaYa: Blockchain-based electronic law record management scheme for judicial investigations

Journal

Journal NameJournal of Information Security and Applications

Title of PaperNyaYa: Blockchain-based electronic law record management scheme for judicial investigations

PublisherElsevier

Volume Number63

Page Number1-1

Published YearOctober 2021

ISSN/ISBN No103025

Indexed INScopus, PubMed, Web of Science

Abstract

In digitization, judicial investigations have transitioned towards digital storage of forensic shreds of evidence as electronic law records (ELRs). The shift poses varied challenges of ELR preservation, homogeneity of case formats, chronology in recorded statements by suspects, time-stamping and digital signatures on ELRs, and the chain of transfer of cases to different law enforcement agencies (LEAs) over open channels. Thus, privacy and trust among judicial stakeholders-case appellant (CA), case defendant (CD), the police officer (PO), defence lawyer (DL), prosecutor lawyers (PL), LEAs, and court judge is a prime concern. Motivated from the aforementioned discussions, the paper presents a blockchain (BC)-based ELR management scheme, NyaYa, that operates as a four-phased scheme of judicial stakeholder registration in BC, case registration with meta-hash keys in public BC, that reference an external off-chain interplanetary file storage (IPFS), chronology of investigative updates among LEAs, and case hearing and settlement through smart contracts (SCs). In the simulation, NyaYa is compared to traditional ELR storage schemes for parameters like mining cost, query fetching time, block processing time, obtained IPFS throughput, signing latency, the effect of collusion attacks, ELR processing time, and corrupted indexes in IPFS. We also presented formal verification and proposed functionalities of SCs. In simulation, at 6 USD mining cost, NyaYa can append 22456 transactions, compared to 21497 and 3000 transactions respectively in existing schemes. The achieved query fetching time is 0.852 milli-seconds (ms), at 25 blocks, with cache support of 32 kilobyte (KB). The scheme has an average signing latency of , and achieves a high-trust probability of 0.887 %, compared to 0.765 % in consortium BC, and 0.455 % in private BC, at 500, colluding nodes. An improvement of 6.77 % is achieved in ELR uploading latency, and the scheme has only 21 corrupted IPFS indexes for 350 fetched ELRs. The obtained results indicate the efficacy of the proposed scheme against conventional schemes.

VaCoChain: Blockchain-based 5G-assisted UAV Vaccine distribution scheme for future pandemics

Journal

Journal NameIEEE Journal of Biomedical and Health Informatics

Title of PaperVaCoChain: Blockchain-based 5G-assisted UAV Vaccine distribution scheme for future pandemics

PublisherIEEE

Volume NumberEarly Access

Page Number1-1

Published YearAugust 2021

ISSN/ISBN No2168-2208

Indexed INScopus, PubMed, Web of Science

Abstract

This paper proposes a generic scheme VaCoChain, that fuses blockchain (BC) and unmanned aerial vehicles (UAVs) underlying fifth-generation (5G) communication services for timely vaccine distribution during novel coronavirus (COVID-19) and future pandemics. The scheme offers 5G-tactile internet (5G-TI)-based services for UAV communication networks (UAVCN) monitored through ground controller stations (GCs). 5G-TI enabled UAVCN supports real-time dense connectivity at ultra-low round-trip time (RTT) latency of < 1 and high availability of 99.9999%. Thus, it can support resilient vaccine distributions in a phased manner at government-designated nodal centers (NCs) with reduced round trip delays from vaccine production warehouses (VPW). Further, UAVCNs ensure minimizes human intervention and controls vaccine health conditions due to shorter trip times. Once vaccines are supplied at NCs warehouses, then the BC ensures timestamped documentation of vaccinated persons with chronology, auditability, and transparency of supply-chain checkpoints from VPW to NCs. Through smart contracts (SCs), priority groups can be formed for vaccination based on age, healthcare workers, and general commodities. In the simulation, for UAV efficacy, we have compared the scheme against fourth-generation (4G)-assisted long term evolution-advanced (LTE-A), orthogonal frequency division multiplexing (OFDM) channels, and traditional logistics for round-trip time (RTT) latency, logistics, and communication costs. In the BC setup, we have compared the scheme against the existing 5G-TI delivery scheme (Gupta et al.) for processing latency, packet losses, and transaction time. For example, in communication costs, the proposed scheme achieves an average improvement of 9.13 for block meta-information. For 4000 transactions, the proposed scheme has a communication latency of 16s compared to 36s. The packet loss is significantly reduced to 2.5% using 5G-TI compared to 16% in 4G-LTE-A. The proposed scheme has a computation cost of 1.6 ms and a communication cost of 157 bytes, which indicates the proposed scheme efficacy against conventional approaches.

Blockchain Adoption for Trusted Medical Records in Healthcare 4.0 Applications: A Survey

Book Chapter

Book NameProceedings of Second International Conference on Computing, Communications, and Cyber-Security

PublisherSpringer

Author NameUmesh Bodkhe

Page Number759-774

Chapter TitleBlockchain Adoption for Trusted Medical Records in Healthcare 4.0 Applications: A Survey

Published YearMay 2021

ISSN/ISBN No978-981-16-0733-2

Indexed INScopus

Abstract

Healthcare 4.0 allows monitoring of electronic health record (EHR) at distributed locations, through wireless infrastructures like Bluetooth, ZigBee, near-field communication (NFC), and GPRS. Thus, the private EHR data can be tampered by malicious entities that affect updates through different stakeholders like patients, doctors, laboratory technicians, and insurance agencies. Hence, there must be a notion of trust among aforementioned stakeholders. Moreover, the accessed volume of data is humongous; thus, to ensure security and trust, blockchain (BC)-based solutions can handle timestamped volumetric data as chronological ledger. Motivated from the same, the paper presents a systematic survey of BC applications in Healthcare 4.0 ecosystems. The contribution of the paper is to conduct a systematic survey of BC adoption in Healthcare 4.0. The survey identifies tools and technologies to support BC-based healthcare applications and addresses open challenges for future research of integrating BC to secure EHR in Healthcare 4.0 ecosystem.

BaY cP: A novel Bayesian customer Churn prediction scheme for Telecom sector

Conference

Title of PaperBaY cP: A novel Bayesian customer Churn prediction scheme for Telecom sector

Proceeding NameLecture Notes in Networks and Systems

PublisherIEEE

Author NameAshwin Verma

OrganizationNirma University

Year , VenueMay 2021 , UP, India

ISSN/ISBN No978-981-16-0733-2

Indexed INScopus, Web of Science

AnSMart: A SVM-based anomaly detection scheme via system profiling in Smart Grids.

Conference

Title of PaperAnSMart: A SVM-based anomaly detection scheme via system profiling in Smart Grids.

Proceeding Name2021 2nd International Conference on Intelligent Engineering and Management (ICIEM)

PublisherIEEE

Author NameDeepti Saraswat

OrganizationNirma University

Year , VenueApril 2021 , London, UK

Page Number1-1

ISSN/ISBN No978-1-6654-1450-0

Abstract

Anomaly detection techniques analyze consumer spend patterns and grid load profiles to predict possible deviations from normal behavior. However, as the measured data is time-varying, profiling the measured drifts becomes complex owing to the amount of raw generated data. Motivated from the aforementioned discussions, in this paper, we propose a scheme, AnSMart, to predict deviations in smart grid (SG) data through obtained profiling operations. The scheme operates in two phases. In the first phase, valuable grid features are extracted from internal system call lists made by grid kernels after load profiling operations are completed over a day. Then, in the second phase, based on data logs, vector differences are computed for call vectors and malign scenarios are identified. The data is fed to the support vector machine (SVM) model for training, and compromised grid behavior is classified. SVM predicts metrics deviation from normal grids. The deviation is measured depending on parameters like-call vector signal, call-sizes, call-list deviations, and call-return values collected from the open-source libiec61850 library that consists of resource-rich (RR) and resource-limited (RL) libraries for both compromised and uncompromised grids. Based on different cases, a total of 50 experiments were conducted. The obtained F-score is 0.926 and the accuracy of 92.5% is obtained based on system-call stacks and grid operating system (OS) behavior that outperforms the conventional anomaly-based approaches on SG.

DAMS: Dynamic Association for View Materialization based on rule mining scheme

Conference

Title of PaperDAMS: Dynamic Association for View Materialization based on rule mining scheme

Proceeding NameLecture Notes in Electrical Engineering

PublisherSpringer

Author NameAshwin Verma, Pronaya Bhattacharya, Umesh Bodkhe, Akhilesh Ladha, Sudeep Tanwar

OrganizationNirma University

Year , VenueFebruary 2021 , Jammu, India

ISSN/ISBN No978-981-15-8297-4

Indexed INScopus, Web of Science

Neural Network Based Diagnostic Approach for Cervical Cancer Cell Stratification From Pap Smear Images

Conference

Title of PaperNeural Network Based Diagnostic Approach for Cervical Cancer Cell Stratification From Pap Smear Images

PublisherIEEE

Author NameBarkha Bhavsar, Bela Shrimali

Published YearMarch 2024

Indexed INScopus, Web of Science, Others

Fault Detection in Forest Fire Monitoring using Negative Selection Approach

Conference

Title of PaperFault Detection in Forest Fire Monitoring using Negative Selection Approach

PublisherIEEE

Published YearMarch 2024

Indexed INScopus, Others

Meticulous Review: Cutting-Edge Cervix Cancer Stratification Using Image Processing And Machine Learning.

Journal

Journal NameInternational Journal of Computing and Digital Systems

Title of PaperMeticulous Review: Cutting-Edge Cervix Cancer Stratification Using Image Processing And Machine Learning.

PublisherUniversity of Bahrain

Volume Number15.1

Page Number 1343-1358

Published YearMarch 2024

Indexed INScopus, PubMed, Web of Science, Indian citation Index, EBSCO, Others

An Enhanced Diagnosis of Monkeypox Disease Using Deep Learning and a Novel Attention Model Senet on Diversified Dataset

Journal

Journal NameMultimodal Technologies Interaction

Title of PaperAn Enhanced Diagnosis of Monkeypox Disease Using Deep Learning and a Novel Attention Model Senet on Diversified Dataset

PublisherMDPI

Volume Number7

Page Number75

Published YearJuly 2023

ISSN/ISBN No2414-4088

Indexed INScopus, PubMed, Web of Science

Abstract

With the widespread of Monkeypox and increase in the weekly reported number of cases, it is observed that this outbreak continues to put the human beings in risk. The early detection and reporting of this disease will help monitoring and controlling the spread of it and hence, supporting international coordination for the same. For this purpose, the aim of this paper is to classify three diseases viz. Monkeypox, Chikenpox and Measles based on provided image dataset using trained standalone DL models (InceptionV3, EfficientNet, VGG16) and Squeeze and Excitation Network (SENet) Attention model. The first step to implement this approach is to search, collect and aggregate (if require) verified existing dataset(s). To the best of our knowledge, this is the first paper which has proposed the use of SENet based attention models in the classification task of Monkeypox and also targets to aggregate two different datasets from distinct sources in order to improve the performance parameters. The unexplored SENet attention architecture is incorporated with the trunk branch of InceptionV3 (SENet+InceptionV3), EfficientNet (SENet+EfficientNet) and VGG16 (SENet+VGG16) and these architectures improve the accuracy of the Monkeypox classification task significantly. Comprehensive experiments on three datasets depict that the proposed work achieves considerably high results with regard to accuracy, precision, recall and F1-score and hence, improving the overall performance of classification. Thus, the proposed research work is advantageous in enhanced diagnosis and classification of Monkeypox that can be utilized further by healthcare experts and researchers to confront its outspread.

Deep Learning Model based Face Mask Detection for Automated Mandation

Conference

Title of PaperDeep Learning Model based Face Mask Detection for Automated Mandation

PublisherIEEE

Published YearJune 2023

Indexed INScopus

MediBlock: A Blockchain-based Architecture for Secure Healthcare System

Conference

Title of PaperMediBlock: A Blockchain-based Architecture for Secure Healthcare System

PublisherIEEE

Author Name Bela Shrimali , Shivangi Surati, Himani Trivedi

Published YearJune 2023

Blockchain in Supply Chain Management

Book Chapter

PublisherSpringer

Author Name Bela Shrimali , Shivangi Surati, Himani Trivedi, Payal Chaudhari

Chapter TitleBlockchain in Supply Chain Management

Published YearJune 2023

Indexed INScopus, PubMed, Web of Science

Blockchain State-of-the-Art: Architecture, Use Cases, Consensus, Challenges

Journal

Journal NameJournal of King Saud University - Computer and Information Sciences

Title of PaperBlockchain State-of-the-Art: Architecture, Use Cases, Consensus, Challenges

PublisherElsevier

Volume Number34

Page Number6793-6807

Published YearAugust 2021

Indexed INScopus, EBSCO

The Importance of 5G Healthcare Using Blockchain Technologies

Book Chapter

Book Name Blockchain Applications for Healthcare Informatics: Beyond 5G

Author NameBela Shrimali

Chapter TitleThe Importance of 5G Healthcare Using Blockchain Technologies

Published YearJuly 2021

Indexed INScopus, EBSCO

A Fuzzy-based Approach to Evaluate Multi-Objective Optimization for Resource Allocation in Cloud

Journal

Journal NameInternational Journal of Advanced Technology and Engineering Exploration

Title of PaperA Fuzzy-based Approach to Evaluate Multi-Objective Optimization for Resource Allocation in Cloud

Volume Number43

Published YearJanuary 2018

ISSN/ISBN No2394-5443

Indexed INScopus, Others

Multi-Objective Optimization Oriented Policy for Performance and Energy Efficient Resource Allocation In Cloud Environment

Journal

Journal NameJournal of King Saud University - Computer and Information Sciences

Title of PaperMulti-Objective Optimization Oriented Policy for Performance and Energy Efficient Resource Allocation In Cloud Environment

PublisherElsevier

Published YearJanuary 2017

ISSN/ISBN No1319-1578

Indexed INScopus, EBSCO, Others

Comparative Study for Selection of Open Source Hypervisors and Cloud Architectures under Variant Requirements

Journal

Journal NameJournal of Computer Science and Engineering (IJCSE)

Title of PaperComparative Study for Selection of Open Source Hypervisors and Cloud Architectures under Variant Requirements

Published YearMay 2016

ISSN/ISBN NoComparative Study for Selection of Open Source Hypervisors and Cloud Architectures under Variant Requirements

Indexed INOthers

Performance Based Energy Efficient Techniques for VM Allocationin Cloud Environment

Conference

Title of PaperPerformance Based Energy Efficient Techniques for VM Allocationin Cloud Environment

Proceeding NameACM

PublisherACM

Author NameBela Shrimali

Page Number477-486.

Published YearAugust 2015

ISSN/ISBN No 978-1-4503-3361- 0/15/08

Indexed INOthers

Optimizing the Parameters of Fluidizer Bed Dryer

Conference

Title of PaperOptimizing the Parameters of Fluidizer Bed Dryer

Proceeding NameIEEE 2024 9th International Conference for Convergence in Technology (I2CT)

PublisherIEEE

Author NameBinjal Soni, Jay Padhiyar, AG Ragupathy, Amitava Choudhury, Santish Bharti

OrganizationIEEE Bombay Section and Siddhant Group of Institution Pune

Year , VenueApril 2024 , The Fern - An Ecotel Hotel, Lonavala, India

Page Number5

Abstract

The present study centres on the application of an allencompassing methodology for optimizing the parameters of Fluidized Bed Dryer (FBD). First, a dataset with various FBD attributes are subjected to Principle Component Analysis (PCA). Subsequently, a variety of regression algorithms, including multiple linear regressors, support vector classifiers, decision trees, random forests, and gradient boosting regressors, are employed to analyze the identified key attributes. These attributes comprise the actual values of inlet air flow, inlet air temperature, exhaust air temperature, loss on drying, product temperature, and total drying time. When it comes to predicting the total drying time, the gradient boosting regressor performs better than others. A novel optimization technique called Bayesian optimization is used to find the optimized values of highly correlated features with the total drying time in order further maximize efficiency. This integrated approach uses both sophisticated machine learning algorithms for predictive modelling and optimization techniques to fine-tune specific parameters that are critical for the Fluidized Bed Dryer. The study's findings provide useful information about enhancing FBDs' overall performance and efficacy, which advances drying processes in a variety of industries.

Book Chapter

PublisherSpringer Singapore

Author NameBinjal Soni, Sangita Patil, Shakti Mishra

Page Number25

Published YearDecember 2023

Abstract

Because fake news and clickbait can spread false information and cause havoc, they have grown to be major social issues. Machine learning models have demonstrated great promise in identifying fake news, but adding clickbait detection to these models can improve their precision even more. In this study, we have investigated the use of various machine learning models to identify clickbait and identify fake news. First, we have evaluated how well the well-known machine learning algorithms Naive Bayes, SVM, and Long Short Tern Memory (LSTM) performed at identifying fake news. To train and test these models, we used a dataset of news articles both with and without clickbait. With an accuracy of 88%, our results demonstrated that LSTM performed the best when using clickbait. The best performing model, LSTM, was then combined with clickbait detection to create a hybrid model. We extracted clickbait elements from the headlines using regular expressions and combined them with the content of the articles. Our findings demonstrated that the LSTM model had the highest accuracy out of all the models.

A Hybrid Model for Fake News Detection Using Clickbait An Incremental Approach

Conference

Title of PaperA Hybrid Model for Fake News Detection Using Clickbait An Incremental Approach

Proceeding Name Advanced Network Technologies and Intelligent Computing (ANTIC-2022)

PublisherSpringer, Cham

Author NameSangita Patil, Binjal Soni, Ronak Makwana, Deep Gandhi, Devam Zanzmera, Shakti Mishra

OrganizationDepartment of Computer Science, Banaras Hindu University, Varanasi

Year , VenueDecember 2022 , Varanasi, India

Page Number5

Abstract

In this paper, we have developed a hybrid model to predict fake news that includes clickbait detection as a parameter. The correlation between two different labels has been computed using a chi-square test. After establishing the correlation, the clickbait implementation was done on the heading of the dataset [11], and a fake news detection model has been executed on the content of the dataset [12]. Then, the results of both the models were combined to generate a hybrid model through a regex equation. Our model is successful in enhancing the accuracy of the existing models by 1-2%.

PGASH: Provable group-based authentication scheme for Internet of Healthcare Things

Journal

Journal NamePeer-to-Peer Networking and Applications

Title of PaperPGASH: Provable group-based authentication scheme for Internet of Healthcare Things

PublisherSpringer

Page Number1-20

Published YearJanuary 2024

ISSN/ISBN No1936-6450

Indexed INScopus, Web of Science, Others

Abstract

Electronic healthcare based on medical sensors is now developing to incorporate a significant amount of the Internet of Things (IoT) to communicate between sensors and intended recipients. The key requirements in this domain are to exchange messages safely and to provide confidentiality during communication. Designing and implementing an authentication strategy is essential for resolving security concerns, but it is also challenging to work with constrained computing and processing resources during group communication. Standard one-to-one authentication models do not consider the scalability of resource-limited nodes, which is a vital factor to deal with. However, group authentication presents a unique concept for IoT nodes that verify group members concurrently. The conventional group authentication methods based on the IoT are vulnerable to security risks and cannot defend against attacks like replay attacks, forgery attacks, or unauthorized key distribution by the group manager. In this paper, we propose a dynamic and provable group authentication scheme (GAS) based on a secret sharing scheme that can withstand the dishonest behavior of group managers. We introduced a key updating scenario with a provable group authentication model for dynamic node leaving and joining. Our system complies with the requirements for secrecy and accuracy, and based on security analysis, it is resistant to attacks, as mentioned earlier. Performance analysis and security proof show that our approach performs well in terms of computation cost for group members while maintaining security.

Secrecy aware key management scheme for Internet of Healthcare Things

Journal

Journal NameJournal of Supercomputing

Title of PaperSecrecy aware key management scheme for Internet of Healthcare Things

PublisherSpringer

Volume Number79

Page Number12492–12522

Published YearMarch 2023

Indexed INScopus, Web of Science, Others

A transformative shift toward blockchain-based IoT environments: Consensus, smart contracts, and future directions

Journal

Journal NameSecurity and Privacy

Title of PaperA transformative shift toward blockchain-based IoT environments: Consensus, smart contracts, and future directions

PublisherWiley

Volume Numbere308

Published YearFebruary 2023

Indexed INWeb of Science, Others

Blockchain for Industry 5.0: Vision, Opportunities, Key Enablers, and Future Directions

Journal

Journal NameIEEE Accesss

Title of PaperBlockchain for Industry 5.0: Vision, Opportunities, Key Enablers, and Future Directions

PublisherIEEE

Volume Number10

Page Number69160 - 69199

Published YearJune 2022

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Industry 4.0 have witnessed a paradigm shift from cyber-physical systems (CPS) that aims at massive automation, to a more customer-driven approach. The shift has been attributed to the design of hyper-cognitive systems, integration of virtual and extended reality, digital machinery prototyping and twin designs, trusted machine boundaries, collaborative robots, and artificial intelligence (AI)-based supply chains. This new wave, termed Industry 5.0, is expected to leverage massive production with user-centric customization outside the scope of Industry 4.0 ecosystems. Industry 5.0 is expected to assist diverse industrial verticals like healthcare, smart farming, drones, smart grids, and supply chain production ecosystems. However, data is shared among multiple heterogeneous networks, spanning different authoritative domains. Thus, trusted and secured data transfer is crucial to synergize and secure the industrial perimeters. Blockchain (BC) is a preferred choice as a security enabler to Industry 5.0 ecosystems owing to its inherent property of immutability, chronology, and auditability in industrial systems. Limited works are proposed that present the vision and holistic view of BC-assisted Industry 5.0 applications. The article presents a first-of-its-kind survey on BC as a security enabler in Industry 5.0. Based on a descriptive survey methodology and research questions, we presented the key drivers, and potential applications, and propose an architectural vision of BC-based Industry 5.0 in diverse applicative verticals. The survey intends to present solutions that would assist industry practitioners, academicians, and researchers to drive novel BC-assisted solutions in Industry 5.0 verticals.

Blockchain for Information Security and Privacy

Book

PublisherTaylor and Fransis, CRC Press

Published YearDecember 2021

ISSN/ISBN No9781003129486

Indexed INScopus, Others

Blockchain-Based Security and Privacy for Smart Contracts

Book Chapter

Book NameBlockchain for Information Security and Privacy

PublisherTaylor and Fransis, CRC Press

Author NameChandan Trivedi

Chapter TitleBlockchain-Based Security and Privacy for Smart Contracts

Published YearDecember 2021

ISSN/ISBN No9781003129486

Indexed INScopus

LEAPS: Load And Emission Performance Characteristics For Sensor-Driven Green Transport Systems

Conference

Title of PaperLEAPS: Load And Emission Performance Characteristics For Sensor-Driven Green Transport Systems

PublisherSpringer

Author NameChandan Trivedi

Year , VenueDecember 2021 , Nirma University, Ahmedabad

Indexed INScopus

Decentralized blockchain based framework for securing review system

Conference

Title of PaperDecentralized blockchain based framework for securing review system

Proceeding NameLecture Notes in Electrical Engineering (LNEE)

PublisherSpringer

Author NameChandan Trivedi

Year , VenueDecember 2021 , SVNIT, Surat

Indexed INScopus

Wireless Implantable Medical Devices Security and Privacy: A Survey

Conference

Title of PaperWireless Implantable Medical Devices Security and Privacy: A Survey

Proceeding NameLecture Notes in Electrical Engineering (LNEE)

PublisherSpringer

Author NameChandan Trivedi

Year , VenueSeptember 2021 , NIT, Jamshedpur

Indexed INScopus

Irregularity Detection in Clinical Data of Patients Encountering Heart Surgery

Journal

Journal NameInternational Journal of Innovations & Advancement in Computer Science IJIACS

Title of PaperIrregularity Detection in Clinical Data of Patients Encountering Heart Surgery

PublisherAcademic Science

Volume NumberVolume 7, Issue 5

Page Number331-339

Published YearMay 2018

ISSN/ISBN No2347 – 8616

Indexed INUGC List, Others

Abstract

We depict two approaches to manage distinguishing abnormalities in time course of action of multi-parameter clinical data: (1) metric and model-based markers and (2) information astound. (1) Metric and model-based markers are ordinarily used as early advised signs to perceive progresses between substitute states in light of individual time course of action. Here we explore the real nature of existing pointers to perceive fundamental (peculiarities) from non-essential conditions in patients encountering heart surgery, in perspective of a little anonymized clinical trial dataset. We find that a mix of time-fluctuating autoregressive show, kurtosis, and skewness markers successfully perceived fundamental from non-essential patients in 5 out of 36 blood parameters at a window size of 0.3 (ordinary of 37 hours) or higher. (2) Information bewilder measures how the development of one patient's condition fluctuates from that of rest of the people in perspective of the cross-territory of time course of action. With the most outrageous awe and slope features we recognize each and every essential patient at the 0.05 significance level. Moreover we show that a sincere special case acknowledgment does not work, displaying the necessity for the more intricate philosophies examined here. Our preliminary results suggest that future enhancements in early advised systems for persevering condition watching may foresee the start of fundamental advance and allow remedial mediation balancing calm passing. Advance methodology change is relied upon to decline overfitting and deceiving results, and keep an eye on considerable clinical datasets.

Iterative Deconvolution Approach for High Resolution Satellite Imagery

Journal

Journal NameJournal of Geomatics

Title of PaperIterative Deconvolution Approach for High Resolution Satellite Imagery

PublisherIndian Society of Geomatics

Volume Number10

Page Number114-120

Published YearOctober 2016

ISSN/ISBN No2

Indexed INOthers

DriverSense: A Multi-Modal Framework for Advanced Driver Assistance System

Conference

Title of PaperDriverSense: A Multi-Modal Framework for Advanced Driver Assistance System

Proceeding NameIEEE Explore

PublisherIEEE

Author NameDaiwat Amit Vyas, Manish Chaturvedi

OrganizationIEEE

Year , VenueJanuary 2024 , Bengaluru

Page Number6

ISSN/ISBN No2155-2509

Indexed INScopus

Abstract

Driver distraction, lack of concentration, and increased stress levels are the primary reasons for road accidents. The Advanced Driver Assistance System (ADAS) is used in high-end cars to improve the safety of drivers. These systems use an in-vehicle camera to track the eye movement of a driver and analyze the facial expressions to classify the driver's attention level, mood and/or drowsiness. However, these computer vision-based solutions do not classify the stress and distraction level of a driver which are the major causes of fatality. Further, no ADAS is available to the best of our knowledge for two-wheeler (2W) and three-wheeler (3W) vehicle drivers who represent 80% of the driver population in India. These drivers are exposed to more distractions, stress, and risk due to an open environment. Accordingly, this paper proposes DriverSense, a wearable device based vehicle independent framework for ADAS that uses mobility sensors (e.g., gyroscope, accelerometer, GPS, etc.) and physiological sensors (e.g., EEG, PPG, ECG, SPO2, etc.) to detect aggressiveness and stress level of drivers in real time. The framework employs edge computing to reduce communication delays, and machine learning models for computing inferences related to driver behavior. The results of preliminary experiments conducted using the existing datasets and the data of mobility sensors collected in Ahmedabad city of India are encouraging. The aggressiveness of the drivers could be classified with 86.05% accuracy, whereas the stress level was identified with 88.24% accuracy using existing machine learning algorithms.

Security Analysis of Multi-factor Authentication with Legitimate Key Exchange for Vehicle to Vehicle Communication

Book Chapter

Book NameInternational Conference on ICT for Sustainable Development

PublisherIEEE

Author NameVipul Chudasama, Daiwat Amit Vyas, Devendra Vashi

Page Number10

Chapter TitleSecurity Analysis of Multi-factor Authentication with Legitimate Key Exchange for Vehicle to Vehicle Communication

Published YearNovember 2023

ISSN/ISBN No978-981-99-5651-7

Indexed INScopus, Others

Abstract

Internet of Vehicles (IOV) in which the vehicles share information like traffic, road safety, location sharing, toll payment, road accident, etc. with each other wirelessly. Vehicle Ad-hoc Network (VANET) includes reliable data transmission on a network, frequently changing topology, mobility of vehicles, and security of each component where vehicles can communicate securely and effectively. However, the existing framework has some security issues for which the security properties like nonce and multi-factor authentication needs to consider. At last, we suggest that our framework is more secure and efficient for V2V communication.

Swine Flu Predication Using Machine Learning

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer

Author NameDvijesh Bhatt, Malaram Kumhar, Daiwat Vyas, Ajay Patel

Page Number611-617

Chapter TitleSwine Flu Predication Using Machine Learning

Published YearJanuary 2019

Indexed INScopus

Abstract

Disease identification is one of the critical and time-consuming tasks in medical diagnosis system. Machine learning is a foremost technique used to predict and identify the diseases at different levels. It is very spontaneous and on-time process to analyze disease based on clinical and laboratory symptoms with the help of appropriate and initial data, and it also helps us to produce a more efficient diagnosis plan in some diseases. In the past, machine learning helped in predicating many diseases like brain tumor, breast cancer, diabetes diagnosis. Swine flu is one of the diseases which take long procedural time before coming to the conclusion. Here, we try to apply some machine learning algorithms to reduce that time by some margin so that diagnosis of patient is start on time. We have analyzed the current scenario of a medical diagnosis system with different data mining and machine learning techniques and proposed feed-forward neural network to predict the “Swine Flu” disease with some data at initial level.

Augmented Reality (AR) Applications: A survey on Current Trends, Challenges, & Future Scope

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperAugmented Reality (AR) Applications: A survey on Current Trends, Challenges, & Future Scope

PublisherAdvance Academic Publisher

Volume Number8

Page Number2724-2730

Published YearMay 2017

ISSN/ISBN No0976-5697

Indexed INEBSCO

Abstract

In the last decade with the advances in computer hardware technologies, display devices, controller devices, software enhancements has tremendously aided the Augmented Reality (AR) Technology to grow from leaps to bounds. Augmented Reality (AR) is a technique that enables users to interact with their physical environment through the overlay of digital information. AR is a field of computer science which deals with combination of reality with computer generated data i.e it aids enhancement over a real world environment in real time. Virtual Reality (VR) and Augmented Reality (AR) are technologies that have a wide spread reach in various technological fronts and has a very promising prospect for various diversified research avenues. An in-depth understanding of trends, challenges, future scope for AR systems is discussed in this survey paper. Authors have made a conscious effort to investigate the state of the art in AR Technologies and its diversified engineering application areas. Various aspects of the design of an AR system are taken into consideration, like the interface devices for interacting with virtual world, software's, the hardware etc. Also, described are a few specific applications that have been developed using the AR technology and possible avenues for future research in the field of AR. Latest trends & evolution of this technology have been touched upon for better understanding. Various applications have been explored and possible approach for enhancing the use of this technology have been discussed. We have discussed some of the limitations in developing such systems. Tools available for development of AR applications that satisfy the current requirements are included. Future directions and suggestions for effectively and efficiently improving the application areas have been focused upon. This paper will provide a better insight for anyone who wishes to do research in the field of AR.

Medical Diagnosis System Using Machine Learning

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperMedical Diagnosis System Using Machine Learning

PublisherCS Journals

Volume Number7

Page Number177-182

Published YearSeptember 2015

ISSN/ISBN No09737391

Indexed INOthers

IoT: trends, challenges and future scope

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperIoT: trends, challenges and future scope

PublisherCS Journal

Volume Number7

Page Number186-197

Published YearSeptember 2015

ISSN/ISBN No09737391

Indexed INOthers

Abstract

IoT (Internet of Things) one of the most exiting trends and innovation in the recent history of technological advancement. Also the advances in computer hardware, embedded system devices, networking devices, display devices, control devices, software enhancements etc. has tremendously supported IoT to grow slowly and steadily from leaps to bounds. With computation, connectivity, and data storage becoming more advanced and universal there has been an explosion of IoT based application solutions in diversified domains from health care to public safety, from assembly line scheduling to manufacturing and various other technological domains. IoT can be defined as a network of physical objects, devices that contain embedded technology (like intelligent sensors, controllers etc.) whichcan communicate, sense, or interact with internal or external systems. In other words, when objects can sense and communicate, it changes how and where decisions are made, and who makes them and accordingly operations can be carried out.In this survey a conscious effort has been put forward to investigate the state of the art involved in IoT and its various diversified engineering applications.Latest trends & evolution,challenges, and future scope of this technology have been touched upon for better understanding.Various IoT based applications have been explored and possible approach for enhancing the use of this technology have been discussed in this paper.Future directions and suggestions for effectively and efficiently improving the IoT based application areas have been touched upon. This paper will provide a better insight for anyone who wishes to carry out research in the field of IoT.In this paper we have tried to provide a holistic perspective on IoT and IoT based applications, application areas, research challenges in IoT, trends and future possibilities in IoT

Focused Web Crawler

Conference

Title of PaperFocused Web Crawler

Proceeding NameAdvances in Soft-computing, E-Learning, Information & Communication Technology

PublisherKrishi Sanskriti Publications

Author NameDvijesh Bhatt, Daiwat Amit Vyas, Sharnil Pandya

OrganizationAdvances in Soft-computing, E-Learning, Information & Communication Technology

Year , VenueMarch 2015 , Delhi

Page Number18

ISSN/ISBN No2393-9907

Indexed INOthers

Recognition of Fruits Using Hybrid Features and Machine Learning

Conference

Title of PaperRecognition of Fruits Using Hybrid Features and Machine Learning

Proceeding NameIEEE International Conference on Computing, Analytics and Security Trends

PublisherIEEE

Year , VenueDecember 2016 , College of Engineering , Pune

Page Number572-577

ISSN/ISBN No978-1-5090-1338-8

Empirical Performance Comparison of OODBMS over RDBMS

Journal

Journal NameIJCSC

Title of PaperEmpirical Performance Comparison of OODBMS over RDBMS

Volume Number7

Page Number83-88

Published YearMarch 2016

ISSN/ISBN No0973-7391

Indexed INOthers

Review on Generic Object Recognition Techniques : Challenges and Opportunities

Journal

Journal NameIJARET

Title of PaperReview on Generic Object Recognition Techniques : Challenges and Opportunities

Volume Number6

Page Number104-133

Published YearDecember 2015

ISSN/ISBN No0976-6480

Indexed INUGC List

Analyzing the Comprehensibility of Aspect-Oriented Modelling and Design of Software System

Journal

Journal NameInternational Journal of Computer Application

Title of PaperAnalyzing the Comprehensibility of Aspect-Oriented Modelling and Design of Software System

Volume Number95

Page Number7-11

Published YearJune 2014

ISSN/ISBN No0975 - 8887

Indexed INEBSCO

SanJeeVni: Secure UAV-envisioned Massive Vaccine Distribution for COVID-19 Underlying 6G Network

Journal

Journal NameIEEE Sensors Journal

Title of PaperSanJeeVni: Secure UAV-envisioned Massive Vaccine Distribution for COVID-19 Underlying 6G Network

PublisherIEEE Sensors Journal

Volume NumberEarly Access

Page Number 1 - 1

Published YearJuly 2022

ISSN/ISBN No1530-437X

Indexed INScopus, Others

Abstract

Recently, unmanned aerial vehicles (UAVs) are deployed in Novel Coronavirus Disease-2019 (COVID-19) vaccine distribution process. To address issues of fake vaccine distribution, real-time massive UAV monitoring and control at nodal centers (NCs), the authors propose SanJeeVni, a blockchain (BC)-assisted UAV vaccine distribution at the backdrop of sixth-generation (6G) enhanced ultra-reliable low latency communication (6G-eRLLC) communication. The scheme considers user registration, vaccine request, and distribution through a public Solana BC setup, which assures a scalable transaction rate. Based on vaccine requests at production setups, UAV swarms are triggered with vaccine delivery to NCs. An intelligent edge offloading scheme is proposed to support UAV coordinates and routing path setups. The scheme is compared against fifth-generation (5G) uRLLC communication. In the simulation, we achieve and 86% improvement in service latency, 12.2% energy reduction of UAV with 76.25% more UAV coverage in 6G-eRLLC, and a significant improvement of ≈ 199.76% in storage cost against the Ethereum network, which indicates the scheme efficacy in practical setups.

Explainable AI for Healthcare 5.0: Opportunities and Challenges

Journal

Journal NameIEEE Access

Title of PaperExplainable AI for Healthcare 5.0: Opportunities and Challenges

PublisherIEEE Access

Volume NumberEarly Access

Page Number84486 - 84517

Published YearJuly 2022

ISSN/ISBN No1530-437X

Indexed INScopus

Abstract

n the healthcare domain, a transformative shift is envisioned towards Healthcare 5.0. It expands the operational boundaries of Healthcare 4.0 and leverages patient-centric digital wellness. Healthcare 5.0 focuses on real-time patient monitoring, ambient control and wellness, and privacy compliance through assisted technologies like artificial intelligence (AI), Internet-of-Things (IoT), big data, and assisted networking channels. However, healthcare operational procedures, verifiability of prediction models, resilience, and lack of ethical and regulatory frameworks are potential hindrances to the realization of Healthcare 5.0. Recently, explainable AI (EXAI) has been a disruptive trend in AI that focuses on the explainability of traditional AI models by leveraging the decision-making of the models and prediction outputs. The explainability factor opens new opportunities to the black-box models and brings confidence in healthcare stakeholders to interpret the machine learning (ML) and deep learning (DL) models. EXAI is focused on improving clinical health practices and brings transparency to the predictive analysis, which is crucial in the healthcare domain. Recent surveys on EXAI in healthcare have not significantly focused on the data analysis and interpretation of models, which lowers its practical deployment opportunities. Owing to the gap, the proposed survey explicitly details the requirements of EXAI in Healthcare 5.0, the operational and data collection process. Based on the review method and presented research questions, systematically, the article unfolds a proposed architecture that presents an EXAI ensemble on the computerized tomography (CT) image classification and segmentation process. A solution taxonomy of EXAI in Healthcare 5.0 is proposed, and operational challenges are presented. A supported case study on electrocardiogram (ECG) monitoring is presented that preserves the privacy of local models via federated learning (FL) and EXAI for metric validation. The case-study is supported through experimental validation. The analysis proves the efficacy of EXAI in health setups that envisions real-life model deployments in a wide range of clinical applications.

Blockchain-Based Federated Learning in UAVs Beyond 5G Networks: A Solution Taxonomy and Future Directions

Journal

Journal NameIEEE Access

Title of PaperBlockchain-Based Federated Learning in UAVs Beyond 5G Networks: A Solution Taxonomy and Future Directions

PublisherIEEE Access

Volume Number10

Page Number33154 - 33182

Published YearMarch 2022

ISSN/ISBN No2169-3536

Indexed INScopus, Others

Abstract

Recently, unmanned aerial vehicles (UAVs) have gained attention due to increased use-cases in healthcare, monitoring, surveillance, and logistics operations. UAVs mainly communicate with mobile base stations, ground stations (GS), or networked peer UAVs, known as UAV swarms. UAVs communicate with GS, or UAV swarms, over wireless channels to support mission-critical operations. Communication latency, bandwidth, and precision are of prime importance in such operations. With the rise of data-driven applications, fifth-generation (5G) networks would face bottlenecks to communicate at near-real-time, at low latency and improved coverage. Thus, researchers have shifted towards network designs that incorporate beyond 5G (B5G) networks for UAV designs. However, UAVs are resource-constrained, with limited power and battery, and thus centralized cloud-centric models are not suitable. Moreover, as exchanged data is through open channels, privacy and security issues exist. Federated learning (FL) allows data to be trained on local nodes, preserving privacy and improving network communication. However, sharing of local updates is required through a trusted consensus mechanism. Thus, blockchain (BC)-based FL schemes for UAVs allow trusted exchange of FL updates among UAV swarms and GS. To date, limited research has been carried out on the integration of BC and FL in UAV management. The proposed survey addresses the gap and presents a solution taxonomy of BC-based FL in UAVs for B5G networks due to the open problem. This paper presents a reference architecture and compares its potential benefits over traditional BC-based UAV networks. Open issues and challenges are discussed, with possible future directions. Finally, a logistics case study of BC-based FL-oriented UAVs in 6G networks is presented. The survey aims to aid researchers in developing potential UAV solutions with the key integrating principles over a diverse set of application verticals.

Secure 5G-Assisted UAV Access Scheme in IoBT for Region Demarcation and Surveillance Operations

Journal

Journal NameIEEE Communications Standards Magazine

Title of PaperSecure 5G-Assisted UAV Access Scheme in IoBT for Region Demarcation and Surveillance Operations

PublisherIEEE Access

Volume Number6

Page Number58-66

Published YearMarch 2022

ISSN/ISBN No-

Indexed INScopus

Abstract

This article proposes a generic scheme that integrates blockchain (BC) and unmanned aerial vehicles (UAVs) through a fifth-generation (5G) Tactile Internet (TI) service to leverage responsive and secure communications in the Internet-of-Battlefield-Things (IoBT)-based ecosystems. UAVs are deployed with camera sensors to monitor and transfer ultra-high resolution (UHR) images and real-time live video feeds of region demarcation and surveillance to ground control stations (GCS). Currently, UAVs operate through Long-Term Evolution-Advanced (LTE-A) services and face bottlenecks in terms of bandwidth and end latency for live feeds. As the feed is sent through open channels, it is vulnerable to security attacks by an adversary. The proposed scheme addresses the dual issues of responsive network orchestration, and induces trust, immutability, and transparency in shared data among UAVs and GCSs via BC as a key solution. Through a case study, the scheme is compared to baseline LTE services. In the simulation, transactions through BC achieve 31.85 percent improvement over cloud-based GCS, an average frame loss of 18.42 percent in 5G-TI compared to 94.07 percent in 4G-LTE-A channel, and processing latency of 0.1061 s in 5G-TI, compared to 2.2133 s in 4G-LTE, which indicates the viability of the proposed scheme.

Coalition of 6G and Blockchain in AR/VR Space: Challenges and Future Directions

Journal

Journal NameIEEE Access

Title of PaperCoalition of 6G and Blockchain in AR/VR Space: Challenges and Future Directions

PublisherIEEE Access

Volume Number9

Page Number168455 - 168484

Published YearDecember 2021

ISSN/ISBN No2169-3536

Indexed INScopus, Others

Abstract

The digital content wave has proliferated the financial and industrial sectors. Moreover, with the rise of massive internet-of-things, and automation, technologies like augmented reality (AR) and virtual reality (VR) have emerged as prominent players to drive a range of applications. Currently, sixth-generation (6G) networks support enhanced holographic projection through terahertz (THz) bandwidths, ultra-low latency, and massive device connectivity. However, the data is exchanged between autonomous networks over untrusted channels. Thus, to ensure data security, privacy, and trust among stakeholders, blockchain (BC) opens new dimensions towards intelligent resource management, user access control, audibility, and chronology in stored transactions. Thus, the BC and 6G coalition in future AR/VR applications is an emerging investigative topic. To date, authors have proposed surveys that study the integration of BC and 6G in AR/VR in isolation, and hence a coherent survey is required. Thus, to address the gap, the survey is the first-of-its-kind to investigate and study the coalition of BC and 6G in AR/VR space. Based on the proposed research questions in the survey, a solution taxonomy is presented, and different verticals are studied in detail. Furthermore, an integrative architecture is proposed, and open issues and challenges are presented. Finally, a case study, BvTours , is presented that presents a unique survey on BC-based 6G-assisted AR/VR virtual home tour service. The survey intends to propose future resilient frameworks and architectures for different industry 4.0 verticals and would serve as starting directions for academia, industry stakeholders, and research organizations to study the coalition of BC and 6G in AR/VR in industrial applications, gaming, digital content manufacturing, and digital assets protection in greater detail.

NYAYA: BLOCKCHAIN-BASED ELECTRONIC LAW RECORD MANAGEMENT SCHEME FOR JUDICIAL INVESTIGATIONS

Journal

Journal NameJOURNAL OF INFORMATION SECURITY AND APPLICATION

Title of PaperNYAYA: BLOCKCHAIN-BASED ELECTRONIC LAW RECORD MANAGEMENT SCHEME FOR JUDICIAL INVESTIGATIONS

PublisherElseiver

Volume Number63

Page Number1-13

Published YearOctober 2021

ISSN/ISBN No22142126

Indexed INScopus, Others

Abstract

In digitization, judicial investigations have transitioned towards digital storage of forensic shreds of evidence as electronic law records (ELRs). The shift poses varied challenges of ELR preservation, homogeneity of case formats, chronology in recorded statements by suspects, time-stamping and digital signatures on ELRs, and the chain of transfer of cases to different law enforcement agencies (LEAs) over open channels. Thus, privacy and trust among judicial stakeholders-case appellant (CA), case defendant (CD), the police officer (PO), defence lawyer (DL), prosecutor lawyers (PL), LEAs, and court judge is a prime concern. Motivated from the aforementioned discussions, the paper presents a blockchain (BC)-based ELR management scheme, NyaYa, that operates as a four-phased scheme of judicial stakeholder registration in BC, case registration with meta-hash keys in public BC, that reference an external off-chain interplanetary file storage (IPFS), chronology of investigative updates among LEAs, and case hearing and settlement through smart contracts (SCs). In the simulation, NyaYa is compared to traditional ELR storage schemes for parameters like mining cost, query fetching time, block processing time, obtained IPFS throughput, signing latency, the effect of collusion attacks, ELR processing time, and corrupted indexes in IPFS. We also presented formal verification and proposed functionalities of SCs. In simulation, at 6 USD mining cost, NyaYa can append 22456 transactions, compared to 21497 and 3000 transactions respectively in existing schemes. The achieved query fetching time is 0.852 milli-seconds (ms), at 25 blocks, with cache support of 32 kilobyte (KB). The scheme has an average signing latency of , and achieves a high-trust probability of 0.887 %, compared to 0.765 % in consortium BC, and 0.455 % in private BC, at 500, colluding nodes. An improvement of 6.77 % is achieved in ELR uploading latency, and the scheme has only 21 corrupted IPFS indexes for 350 fetched ELRs. The obtained results indicate the efficacy of the proposed scheme against conventional schemes.

An Efficient Approach for Job Scheduling in Cloud Computing

Journal

Journal NameInternational Journal of Computer Science Engineering and Information Technology Research (IJCSEITR)

Title of PaperAn Efficient Approach for Job Scheduling in Cloud Computing

PublisherTRANSSTELLAR

Volume Number4-4

Page Number9-14

Published YearAugust 2014

ISSN/ISBN No2249-7943

Indexed INOthers

Analyzing Large-Scaled Applications in Cloud Computing Environment

Journal

Journal NameInternational Journal of Computer Science Engineering and Information Technology Research (IJCSEITR)

Title of PaperAnalyzing Large-Scaled Applications in Cloud Computing Environment

PublisherTRANSSTELLAR

Volume Number4-4

Page Number1-8

Published YearAugust 2014

ISSN/ISBN No2249-7943

Indexed INOthers

An Efficient Hybrid Approach of Attribute Based Encryption for Privacy Preserving Through Horizontally Partitioned Data

Journal

Journal NameProcedia Computer Science

Title of PaperAn Efficient Hybrid Approach of Attribute Based Encryption for Privacy Preserving Through Horizontally Partitioned Data

PublisherElsevier

Volume Number167

Page Number2437–2444

Published YearMarch 2020

ISSN/ISBN No18770509

Indexed INScopus

Performance of Symmetric and Asymmetric Encryption Techniques for Attribute Based Encryption

Journal

Journal NameInternational Journal of Recent Technology and Engineering

Title of PaperPerformance of Symmetric and Asymmetric Encryption Techniques for Attribute Based Encryption

PublisherBlue Eyes Intelligence Engineering & Sciences Publication

Volume Number8

Page Number176-182

Published YearNovember 2019

ISSN/ISBN No2277-3878

Indexed INOthers

Implementation of Attribute based Symmetric Encryption through Vertically Partitioned Data in PPDM

Journal

Journal NameInternational Journal of Engineering and Advanced Technology

Title of PaperImplementation of Attribute based Symmetric Encryption through Vertically Partitioned Data in PPDM

PublisherBlue Eyes Intelligence Engineering & Sciences Publication

Volume Number8

Page Number5384-5390

Published YearAugust 2019

ISSN/ISBN No2249 – 8958

Indexed INScopus

Critical study and analysis for deciding sensitive and non-sensitive attributes of medical healthcare dataset through survey and using association rule mining

Journal

Journal NameInternational Journal of Recent Scientific Research

Title of PaperCritical study and analysis for deciding sensitive and non-sensitive attributes of medical healthcare dataset through survey and using association rule mining

Volume Number8

Page Number17218-17222

Published YearMay 2017

ISSN/ISBN No0976-3031

Indexed INUGC List

Challenges & Opportunities in Privacy Preserving Data Mining for Healthcare Dataset

Conference

Title of PaperChallenges & Opportunities in Privacy Preserving Data Mining for Healthcare Dataset

Proceeding NameICRISET-2017

Author NameDevendra Vashi

OrganizationBirla Vishvakarma Mahavidyalaya Engineering College, VV Nagar

Year , VenueFebruary 2017 , BVM, VV Nagar

Page Number133

ISSN/ISBN No978-93-84339-38-8

Indexed INOthers

Abstract

Now a day’s medical organization, health care Centres, insurance companies are very much interested to do analysis for various diseases. Their objective is to make aware the societies about diseases causes and patterns. Also, insurance companies may introduce medical health care policies as per the analysis of medical data. One of the problems faced during such data mining is that personal or sensitive data is exposed to the public which most of the people may not like. Hence one of the requirements of data extraction during data mining is to preserve the privacy of sensitive/personal data. This is possible using various Privacy Preserving Data Mining (PPDM) techniques. This paper reviews and compares the different PPDM techniques with data mining methods and privacy analysis. Paper also discusses the challenges faced and its solutions during PPDM.

OPTIMAL LECTURE PLANNING FOR TEACHING THE SUBJECT USING AGILE METHODOLOGY

Journal

Journal NameInternational Journal of Advanced Research in Engineering and Technology

Title of PaperOPTIMAL LECTURE PLANNING FOR TEACHING THE SUBJECT USING AGILE METHODOLOGY

Publisher IAEME

Volume Number7

Page Number64–68

Published YearMarch 2016

ISSN/ISBN No0976-6499

Comparative stud of some cryptographic algorithms

Conference

Title of PaperComparative stud of some cryptographic algorithms

Author NameDevendra Vashi

OrganizationSN Patel Institute Of Technology & Research Centre

Year , VenueApril 2015 , SN Patel Institute Of Technology & Research Centre, Bardoli

ISSN/ISBN No978-81-929339-1-7

Indexed INOthers

Abstract

in privacy-preserving data mining technique, the cryptographic process is good to implement properly for making data private while sending data to the third party. This paper is just a study of some of the encryption and decryption technique like DES, RSA and hash function which can be implemented for cryptography. This paper is also emphasized on a comparative study on different encryption technique and how is useful in the cryptographic technique

Detection of traffic rule violation in University campus using deep learning model

Journal

Journal NameInternational Journal of System Assurance Engineering and Management

Title of PaperDetection of traffic rule violation in University campus using deep learning model

PublisherSpringer India

Volume Number14 (6)

Page Number2527-2545

Published YearDecember 2023

ISSN/ISBN No0975-6809

Indexed INScopus, Web of Science

Regenerating vital facial keypoints for impostor identification from disguised images using CNN

Journal

Journal NameExpert Systems with Applications

Title of PaperRegenerating vital facial keypoints for impostor identification from disguised images using CNN

PublisherElsevier B.V.

Volume Number219

Page Number119669

Published YearFebruary 2023

ISSN/ISBN No0957-4174

Indexed INScopus, Web of Science

The Evolution of Ad Hoc Networks for Tactical Military Communications: Trends, Technologies, and Case Studies

Book Chapter

Book NameLecture Notes in Networks and Systems

PublisherSpringer

Author NameZalak Patel, Pimal Khanpara, Sharada Valiveti, Gaurang Raval

Page Number331-346

Chapter TitleThe Evolution of Ad Hoc Networks for Tactical Military Communications: Trends, Technologies, and Case Studies

Published YearFebruary 2023

ISSN/ISBN No2367-3370

Indexed INScopus

A Review of Non Invasive Blood Pressure Monitoring using Artificial Intelligence based Approaches

Conference

Title of PaperA Review of Non Invasive Blood Pressure Monitoring using Artificial Intelligence based Approaches

Proceeding NameInternational Conference on Applied Artificial Intelligence and Computing (ICAAIC)

PublisherIEEE

Author NameVimal Sheoran, Gaurang Raval, Sharada Valiveti, Saurin Parikh

OrganizationNarasu's Sarathy Institute of Technology

Year , VenueMay 2022 , Salem, India

Page Number1-6

ISSN/ISBN No78-1-6654-9710-7

Indexed INScopus

On Performance Enhancement of Molecular Dynamics Simulation Using HPC Systems

Conference

Title of PaperOn Performance Enhancement of Molecular Dynamics Simulation Using HPC Systems

Proceeding NameProceedings of Second International Conference on Computing, Communications, and Cyber-Security

Publisher Lecture Notes in Networks and Systems book series. Springer

Author NameTejal Rathod, Monika Shah, Niraj Shah, Gaurang Raval, Madhuri Bhavsar, R Ganesh

OrganizationKrishna Engg College, Gazhiabad

Year , VenueMay 2021 , Krishna Engg College, Gazhiabad

Page Number1031-1044

ISSN/ISBN No23673389

Indexed INScopus

Quality Evaluation Model for Multimedia Internet of Things (MIoT) Applications: Challenges and Research Directions

Conference

Title of PaperQuality Evaluation Model for Multimedia Internet of Things (MIoT) Applications: Challenges and Research Directions

Proceeding NameInternational Conference on Internet of Things and Connected Technologies

PublisherAdvances in Intelligent Systems and Computing, Springer

Author NameMalram Kumhar, Gaurang Raval, Vishal Parikh

OrganizationMalaviya National Institute of Technology (MNIT), Jaipur, India

Year , VenueFebruary 2020 , Malaviya National Institute of Technology (MNIT), Jaipur, India

Page Number330-336

ISSN/ISBN No21945365

Indexed INScopus

Survey on Security Provisions in Named Data Networking

Journal

Journal NameInternational Journal of Applied Research on Information Technology and Computing

Title of PaperSurvey on Security Provisions in Named Data Networking

PublisherIndianJournals

Volume Number10

Page Number20-26

Published YearMay 2019

ISSN/ISBN No 22493212

Indexed INIndian citation Index

Multi-Objective Optimization Based Clustering in Wireless Sensor Networks Using Harmony Search Algorithm

Journal

Journal NameJournal of Communication Engineering and Systems

Title of PaperMulti-Objective Optimization Based Clustering in Wireless Sensor Networks Using Harmony Search Algorithm

Publisheri-Managers Journal Publications

Volume Number7

Page Number1-12

Published YearAugust 2018

Indexed INIndian citation Index

Natural Language Interface for Multilingual Database

Conference

Title of PaperNatural Language Interface for Multilingual Database

PublisherInternational Conference on Information and Communication Technology for Intelligent Systems (ICTIS)

OrganizationSpringer

Page Number113-120

Published YearAugust 2017

ISSN/ISBN No978-3-319-63644-3

Open Issues in Named Data Networking – A Survey

Book Chapter

Book Name Smart Innovation, Systems and Technologies (SIST, volume 83)

PublisherSpringer, Cham

Page Number 285-292

Chapter TitleOpen Issues in Named Data Networking – A Survey

Published YearAugust 2017

ISSN/ISBN No978-3-319-63673-3

Abstract

Internet is now being used as content distribution network also. Internet users are interested in specific contents rather than host machines where the content is located. Named Data Networking (NDN) is a step towards future Internet architecture that would be based on named data rather than numerically identified hosts. Many projects are in progress to architect the structure of the Internet.

Open Issues in Named Data Networking-A Survey

Conference

Title of PaperOpen Issues in Named Data Networking-A Survey

PublisherSpringer

Year , VenueJanuary 2017 , Ahmedabad , India

Page Number285-292

ISSN/ISBN No978-3-319-63672-6

Securing Application Layer Protocol for IOT

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of Paper Securing Application Layer Protocol for IOT

PublisherIJCSC

Volume Number7

Page Number42-48

Published YearSeptember 2016

Enhancing data delivery with density controlled clustering in wireless sensor networks

Journal

Journal NameMicrosystem Technologies

Title of PaperEnhancing data delivery with density controlled clustering in wireless sensor networks

PublisherSpringer

Volume Number23 (3)

Page Number613-631

Published YearMay 2016

ISSN/ISBN No1432-1858

Optimization of clustering process in WSN with meta-heuristic techniques - a survey

Conference

Title of PaperOptimization of clustering process in WSN with meta-heuristic techniques - a survey

PublisherIEEE

Year , VenueMarch 2016 , 2016 3rd International Conference on Recent Advances in Information Technology (RAIT)

ISSN/ISBN No978-1-4799-8579-1

Analyzing the Performance of Centralized Clustering Techniques for Realistic Wireless Sensor Network Topologies

Conference

Title of PaperAnalyzing the Performance of Centralized Clustering Techniques for Realistic Wireless Sensor Network Topologies

Proceeding NameProcedia Computer Science

PublisherElsevier

Author NameGaurang Raval, Madhuri Bhavsar, Nitin Patel

OrganizationAmity University, Noida

Year , VenueDecember 2015 , Amity University, Noida

Page Number1026-1035

ISSN/ISBN No18770509

Indexed INScopus

Improving Energy Estimation based Clustering with Energy Threshold for Wireless Sensor Networks

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperImproving Energy Estimation based Clustering with Energy Threshold for Wireless Sensor Networks

PublisherIJCA

Volume Number113 (19)

Page Number41-47

Published YearMarch 2015

Improving Data Delivery with Density Control based Clustering in Wireless Sensor Networks

Conference

Title of PaperImproving Data Delivery with Density Control based Clustering in Wireless Sensor Networks

Year , VenueDecember 2014 , At Puri, Odisha, India

ISSN/ISBN No81-85824-46-0

Performance Comparison of Various Clustering Techniques in Wireless Sensor Networks

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of Paper Performance Comparison of Various Clustering Techniques in Wireless Sensor Networks

PublisherIJCSC

Volume Number5

Page Number116-223

Published YearJuly 2014

3-D Localization in Wireless Sensor Networks

Journal

Journal NameInternational Journal of Computer Engineering and Technology (IJCET)

Title of Paper3-D Localization in Wireless Sensor Networks

PublisherIJCET

Volume NumberVolume 5, Issue 3, March 2014, pp. 09-22

Published YearMarch 2014

ISSN/ISBN NoISSN 0976 – 6367(Print) ISSN 0976 – 6375(Online)

Optimization of Clustering Techniques Using Energy Thresholds in Wireless Sensor Networks

Journal

Journal NameInternational Journal of Advanced Research in Engineering and Technology (IJARET)

Title of PaperOptimization of Clustering Techniques Using Energy Thresholds in Wireless Sensor Networks

PublisherIJARET

Volume Number4, Issue 7

Published YearJanuary 2014

ISSN/ISBN NoISSN 0976 - 6480 (Print) ISSN 0976 - 6499 (Online)

Optimization of Collection Tree Protocol

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperOptimization of Collection Tree Protocol

Volume Number4,Issue 8

Published YearJanuary 2013

Optimization of Hierarchical Routing Protocol for Wireless Sensor Networks with Identical Clustering

Conference

Title of PaperOptimization of Hierarchical Routing Protocol for Wireless Sensor Networks with Identical Clustering

PublisherProceedings of International Conference on Advances in Communication, Network, and Computing, 2010

Year , VenueOctober 2010 , Calicut

Page Number119-123

ISSN/ISBN No978-0-7695-4209-6

Problem Area Identification with Secure Data Aggregation in Wireless Sensor Networks

Conference

Title of PaperProblem Area Identification with Secure Data Aggregation in Wireless Sensor Networks

PublisherProceedings of International Conference on Sensor Networks, 2010

Year , VenueSeptember 2010 , Kochi, Kerala, India

Page Number258-266

ISSN/ISBN No978-3-642-15766-0_37

Performance Analysis of Hierarchical Routing Protocol (LEACH) for Wireless Sensor Networks

Conference

Title of PaperPerformance Analysis of Hierarchical Routing Protocol (LEACH) for Wireless Sensor Networks

Proceeding NameNational Conference on Advances in Wireless Communications-2010

Page Number40-43

Published YearJune 2010

Multi Resolution Feature Based Active Handwritten Character Recognition

Conference

Title of PaperMulti Resolution Feature Based Active Handwritten Character Recognition

Proceeding NameInternational Conference on Trends & Advances in Computation & Engineering (TRACE),

PublisherProceedings of International Conference on Trends and Advances in Computation and Engineering, 2010

Page Number963-971

Published YearFebruary 2010

Performance Evaluation of Routing Protocols for Wireless Sensor Networks

Conference

Title of PaperPerformance Evaluation of Routing Protocols for Wireless Sensor Networks

PublisherExcel India Publishers

Published YearJanuary 2010

ISSN/ISBN No978-93-80043-70-8

Problem Area Identification with Secure Data Aggregation in Wireless Sensor Networks

Book Chapter

Book Name Communications in Computer and Information Science

PublisherSpringer Berlin Heidelberg

Page Number258-266

Chapter TitleProblem Area Identification with Secure Data Aggregation in Wireless Sensor Networks

Published YearJanuary 2010

ISSN/ISBN No978-3-642-15766-0

Abstract

The primary use of wireless sensor networks (WSNs) is to collect and process data. Most of the energy consumption is due to data transmission. Because of the unique properties of WSNs all raw data samples are not directly sent to the sink node instead data aggregation is preferred. Since sensor nodes are deployed in an open environment such as a battlefield or similar applications

Survey on Energy Efficient Hierarchical Routing Algorithms in Wireless Sensor Networks – A Survey

Conference

Title of PaperSurvey on Energy Efficient Hierarchical Routing Algorithms in Wireless Sensor Networks – A Survey

Proceeding NameProceedings of National Conference, NUCONE

PublisherNUCONE

Published YearJanuary 2009

Analyzing the Performance of Centralized Clustering Techniques for Realistic Wireless Sensor Network Topologies

Conference

Title of PaperAnalyzing the Performance of Centralized Clustering Techniques for Realistic Wireless Sensor Network Topologies

PublisherElsevier

Year , VenueAugust 201 , 3rd International Conference on Recent Trends in Computing 2015 (ICRTC-2015)

ISSN/ISBN No1026 – 1035

Analysis of Quantum Computing with Food Processing Use Case

Book Chapter

Book NameCyber Security Using Modern Technologies: Artificial Intelligence, Blockchain and Quantum Cryptography

PublisherCRC Press

Author NameDhaval S Jha, Het Shah, Jai Prakash Verma

Page Number47

Chapter TitleAnalysis of Quantum Computing with Food Processing Use Case

Published YearAugust 2023

ISSN/ISBN No9781000908022

Indexed INScopus

Abstract

Quantum computing has undoubtedly pushed the frontiers of a maximum achievable computational speed. By harnessing the laws of “quantum mechanics,” a quantum computer can easily outperform a conventional computer or a supercomputer [1]. Many problems that are perceived to be unsolvable can be efficiently handled by a quantum computer. A quantum computer can provide solutions to many intractable problems, within reasonable time bounds [2]. Although quantum computing technology is quite fascinating, there are many issues and challenges that need to be addressed. There are many problems that cannot be solved by conventional computers or even by modern-day supercomputers. The computational speed required for solving such problems is quite high, and so all present-day computing machines are overwhelmed by the complexity of such problems. Quantum computing provides the solution for solving such types of problems. Quantum computing is based on the concepts of Quantum Superposition and Quantum Entanglement. A quantum computer is capable of solving highly computationally intensive problems very quickly [3]. Conventional computers process the information stored in the form of bits, whereas a quantum computer uses the concept of quantum bits (qubits). Qubits allow the states to be not only 0 or 1, but also any combination of 0 and 1. This allows a quantum computer to process more information at any given instance of time. Problems, which traditionally take exponential time to solve on a conventional computer or a supercomputer, can be solved by a quantum computer in polynomial.

Graph-Based Extractive Text Summarization Sentence Scoring Scheme for Big Data Applications

Journal

Journal NameInformation

Title of PaperGraph-Based Extractive Text Summarization Sentence Scoring Scheme for Big Data Applications

PublisherMDPI

Volume Number14

Page Number472

Published YearAugust 2023

ISSN/ISBN No2227-9709

Indexed INScopus

Abstract

The recent advancements in big data and natural language processing (NLP) have necessitated proficient text mining (TM) schemes that can interpret and analyze voluminous textual data. Text summarization (TS) acts as an essential pillar within recommendation engines. Despite the prevalent use of abstractive techniques in TS, an anticipated shift towards a graph-based extractive TS (ETS) scheme is becoming apparent. The models, although simpler and less resource-intensive, are key in assessing reviews and feedback on products or services. Nonetheless, current methodologies have not fully resolved concerns surrounding complexity, adaptability, and computational demands. Thus, we propose our scheme, GETS, utilizing a graph-based model to forge connections among words and sentences through statistical procedures. The structure encompasses a post-processing stage that includes graph-based sentence clustering. Employing the Apache Spark framework, the scheme is designed for parallel execution, making it adaptable to real-world applications. For evaluation, we selected 500 documents from the WikiHow and Opinosis datasets, categorized them into five classes, and applied the recall-oriented understudying gisting evaluation (ROUGE) parameters for comparison with measures ROUGE-1, 2, and L. The results include recall scores of 0.3942, 0.0952, and 0.3436 for ROUGE-1, 2, and L, respectively (when using the clustered approach). Through a juxtaposition with existing models such as BERTEXT (with 3-gram, 4-gram) and MATCHSUM, our scheme has demonstrated notable improvements, substantiating its applicability and effectiveness in real-world scenarios.

Impact of Boosting Techniques in AI-Based Credit Card Fraud Detection Classifier

Conference

Title of PaperImpact of Boosting Techniques in AI-Based Credit Card Fraud Detection Classifier

Proceeding NameProceedings of Fourth International Conference on Computing, Communications, and Cyber-Security

PublisherSpringer Nature

Author NameMisri Parikh, Niket Kothari, Karan Patel, Jai Prakash Verma, Pronaya Bhattacharya

OrganizationInternational Conference on Computing, Communications, and Cyber-Security

Year , VenueJuly 2023 , Singapore

Page Number461-475

ISSN/ISBN No978-981-99-1479-1

Indexed INScopus

Abstract

In this modern era, with online shopping on the rise, many e-commerce websites and a myriad of different online websites have increased online payment methods and modes, unfortunately increasing the risk of credit card fraud. Hundreds of thousands of people fall victim, each year. This will be susceptible to increase. To avoid massive losses, financial institutions must strengthen their detection and privacy measures. This paper aims to provide a novel approach to recognizing credit card fraud transactions by using machine learning techniques like kNN, decision tree classifier, Random Forest regressor, and further training datasets with AdaBoost and Bagging classifier which increases the accuracy for identifying the fraudulent transaction. Experimental analysis of the proposed approach and findings are based on a legitimate dataset, containing information on European cardholders.

Stock Price Prediction for Market Forecasting Using Machine Learning Analysis

Conference

Title of PaperStock Price Prediction for Market Forecasting Using Machine Learning Analysis

Proceeding Name Proceedings of Fourth International Conference on Computing, Communications, and Cyber-Security

PublisherSpringer, Singapore

Author NameVivek Kumar Prasad, Darshan Savaliya, Sakshi Sanghavi, Vatsal Sakariya, Pronaya Bhattacharya, Jai Prakash Verma, Rushabh Shah, Sudeep Tanwar

OrganizationIC4S-2022

Year , VenueJuly 2023 , Singapore

Page Number477-492

ISSN/ISBN No978-981-99-1479-1

Indexed INScopus

Abstract

A common opinion of stock market in society is that the stock market is either insecure to invest in or troublesome to trade, so many people are disinterested. The stock market is a marketplace that facilitates the acquisition and sale of business stock. The stock index has its unique value on each stock exchange. The index is the average value calculated by aggregating the prices of several stocks. The forecast of the entire stock market is time-varying and depends on the stock price movement. The seasonal variance and steady flow of any index helps both professional as well as amateur investors understand and decide whether to invest in shares and the stock market. Individuals and businesses alike can be affected significantly by the stock market. As a consequence, accurately anticipating stock movements can lower the risk of losing money while increasing profits. To address these issues, time series analysis will be the most effective tool for predicting the trend or even the future. This article represents the comparison of LSTM, ARIMA and SARIMAX models for stock price prediction. It is observed that error for ARIMA model is less as compared to SARIMAX model.

AI Based Prediction for Heart Disease: A Comparative Analysis and an Improved Machine Learning Approach

Conference

Title of PaperAI Based Prediction for Heart Disease: A Comparative Analysis and an Improved Machine Learning Approach

Proceeding Name2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT)

PublisherIEEE

Author NameJay Raval, Jai Prakash Verma, Sardar NM Islam, Rachna Jain, Narina Thakur

Organization2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT)

Year , VenueJune 2023 , Changzhou, China

Page Number1-9

ISSN/ISBN No978-1-6654-5311-0

Indexed INScopus

Abstract

Heart disease problems are growing day by day in the world. Many factors are responsible for increasing the chance of heart attack and any other disease. Many countries have a low level of cardiovascular competence in predicting heart disease-related issues. Finding the best accurate machine learning classifiers for various diagnostic uses by data mining and machine learning techniques aids in predicting whether or not the heart disease-related issue will occur. To predict heart disease, a number of supervised machine-learning algorithms are used and their effectiveness are evaluated. With the exceptionof MLP and KNN, all applied algorithms had their estimated feature significance scores for each feature. This helps to find the main factors affecting heart disease and the accuracy of the model, which helps to get the best prediction. At the end of the research the support vector machine gives us 87.91 % highest testing accuracy compare with all applied machine learning algorithm.

WePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining

Conference

Title of PaperWePaMaDM-Outlier Detection: Weighted Outlier Detection using Pattern Approaches for Mass Data Mining

Proceeding Name2023 International Conference on Advancement in Computation & Computer Technologies (InCACCT)

PublisherIEEE

Author NameRavindrakumar Purohit, Jai Prakash Verma, Rachna Jain, Madhuri Bhavsar

Organization2023 International Conference on Advancement in Computation & Computer Technologies (InCACCT)

Year , VenueJune 2023 , Gharuan, India, 2023

Page Number1-6

ISSN/ISBN No979-8-3503-9648-5

Indexed INScopus

Abstract

Weighted Outlier Detection is a method for identifying unusual or anomalous data points in a dataset, which can be caused by various factors like human error, fraud, or equipment malfunctions. Detecting outliers can reveal vital information about system faults, fraudulent activities, and patterns in the data, assisting experts in addressing the root causes of these anomalies. However, creating a model of normal data patterns to identify outliers can be challenging due to the nature of input data, labeled data availability, and specific requirements of the problem. This article proposed the WePaMaDM-Outlier Detection with distinct mass data mining domain, demonstrating that such techniques are domain-dependent and usually developed for specific problem formulations. Nevertheless, similar domains can adapt solutions with modifications. This work also investigates the significance of data modeling in outlier detection techniques in surveillance, fault detection, and trend analysis, also referred to as novelty detection, a semi-supervised task where the algorithm learns to recognize abnormality while being taught the normal class.

AI based Classification for Autism Spectrum Disorder Detection using Video Analysis

Conference

Title of PaperAI based Classification for Autism Spectrum Disorder Detection using Video Analysis

Proceeding Name2022 IEEE Bombay Section Signature Conference (IBSSC)

PublisherIEEE

Page Number1-6

Published YearFebruary 2023

Indexed INScopus, Web of Science

Classifying Malignant and Benign Tumors of Breast Cancer: A Comparative Investigation Using Machine Learning Techniques

Journal

Journal NameInternational Journal of Reliable and Quality E-Healthcare (IJRQEH)

Title of PaperClassifying Malignant and Benign Tumors of Breast Cancer: A Comparative Investigation Using Machine Learning Techniques

PublisherIGI GLOBAL

Volume Number12

Page Number1-19

Published YearFebruary 2023

Indexed INScopus

Machine Learning-Based Investigation of Employee Attrition Prediction and Analysis

Book Chapter

Book NameEmerging Technology Trends in Electronics, Communication and Networking

PublisherSpringer, Singapore

Author NameJai Prakash Verma

Page Number221-238

Chapter TitleMachine Learning-Based Investigation of Employee Attrition Prediction and Analysis

Published YearDecember 2022

Indexed INScopus

Abstract Data Models and System Design for Big Data Geospatial Analytics

Book Chapter

Book NameEmerging Technology Trends in Electronics, Communication and Networking

PublisherSpringer, Singapore

Author NameJai Prakash Verma

Page Number177-193

Chapter TitleAbstract Data Models and System Design for Big Data Geospatial Analytics

Published YearDecember 2022

Indexed INScopus

Mobility prediction for uneven distribution of bikes in bike sharing systems

Journal

Journal NameConcurrency and Computation: Practice and Experience

Title of PaperMobility prediction for uneven distribution of bikes in bike sharing systems

PublisherWiley Online Library

Published YearNovember 2022

ISSN/ISBN No1532-0626

Indexed INScopus, Web of Science

A New Approach for Processing Raster Geospatial Big Data in Distributed Environment

Book Chapter

Book NameAdvances in Distributed Computing and Machine Learning

PublisherSpringer, Singapore

Author NameJai Prakash Verma

Page Number83-93

Chapter TitleA New Approach for Processing Raster Geospatial Big Data in Distributed Environment

Published YearJuly 2022

Indexed INScopus

Parameter optimization for surface mounter using a self-alignment prediction model

Journal

Journal NameSoldering & Surface Mount Technology

Title of PaperParameter optimization for surface mounter using a self-alignment prediction model

PublisherEmerald Publishing Limited

Volume Number1

Page Number1

Published YearJuly 2022

ISSN/ISBN No0954-0911

Indexed INScopus, Web of Science

Abstract

Abstract Purpose The purpose of this paper is to develop a machine learning model that predicts the component self-alignment offsets along the length and width of the component and in the angular direction. To find the best performing model, various algorithms like random forest regressor (RFR), support vector regressor (SVR), neural networks (NN), gradient boost (GB) and K-nearest neighbors (KNN) were performed and analyzed. The models were implemented using input features, which can be categorized as solder paste volume, paste-pad offset, component-pad offset, angular offset and orientation. Design/methodology/approach Surface-mount technology (SMT) is the technology behind the production of printed circuit boards, which is used in several types of commercial equipment such as communication devices, home appliances, medical imaging systems and sensors. In SMT, components undergo movement known as self-alignment during the reflow process. Although self-alignment is used to decrease the misalignment, it may not work for smaller size chipsets. If the solder paste depositions are not well-aligned, the self-alignment might deteriorate the final alignment of the component. Findings It were trained on their targets. Results obtained by each method for each target variable were compared to find the algorithm that gives the best performance. It was found that RFR gives the best performance in case of predicting offsets along the length and width of the component, whereas SVR does so in case of predicting offsets in the angular direction. The scope of this study can be extended to developing this model further to predict defects that can occur during the reflow process. It could also be developed to be used for optimizing the placement process in SMT. Originality/value This paper proposes a predictive model that predicts the component self-alignment offsets along the length and width of component and in the angular direction. To find the best performing model, various algorithms like RFR, SVR, NN, GB and KNN were performed and analyzed for predicting the component self-alignment offsets. This helps to achieve the following research objectives: best machine learning model for prediction of component self-alignment offsets. This model can be used to optimize the mounting process in SMT, which reduces occurrences of defects and making the process more efficient.

Collaborative Filtering-Based Music Recommendation in View of Negative Feedback System

Book Chapter

Book NameProceedings of Third International Conference on Computing, Communications, and Cyber-Security pp 447–460 (Lecture Notes in Networks and Systems book series (LNNS,volume 421))

PublisherSpringer, Singapore

Author NameJai Prakash Verma, Pronaya Bhattacharya, Aarav Singh Rathor, Jaymin Shah, Sudeep Tanwar

Page Number447–460

Chapter TitleCollaborative Filtering-Based Music Recommendation in View of Negative Feedback System

Published YearJuly 2022

ISSN/ISBN No978-981-19-1142-2

Indexed INScopus

Abstract

Recommender systems (RS) are information filtering algorithms that suggest users items that they might be interested in. In this paper, the authors have proposed a content-based approach that maintains fresh recommendations in a music recommendation ecosystem that improves by suggesting new recommendations. A collaborative filtering system has been proposed alongside a negative feedback system (NFS). This results in a much newer array of song recommendations based only on the songs which the user likes, and due to NFS, it can be easily recognized by the user with the precision of 16.78%. Analysis of the results reveals that the song recommendations made by the newly proposed system have a significantly lower intersection with songs that users play from general playlists and available music datasets. Thus, the proposed system allows users to discover new recommendations every time they use the NFS recommendation algorithm and thus performs better compared to the old content-based algorithms, such as popularity-based filtering mechanisms.

Improvise approach for respiratory pathologies classification with multilayer convolutional neural networks

Journal

Journal NameMultimedia Tools and Applications

Title of PaperImprovise approach for respiratory pathologies classification with multilayer convolutional neural networks

PublisherSpringer US

Page Number1-21

Published YearApril 2022

ISSN/ISBN No1573-7721

Indexed INScopus, Web of Science

Abstract

Every respiratory-related checkup includes audio samples collected from the individual, collected through different tools (sonograph, stethoscope). This audio is analyzed to identify pathology, which requires time and effort. The research work proposed in this paper aims at easing the task with deep learning by the diagnosis of lung-related pathologies using Convolutional Neural Network (CNN) with the help of transformed features from the audio samples. International Conference on Biomedical and Health Informatics (ICBHI) corpus dataset was used for lung sound. Here a novel approach is proposed to pre-process the data and pass it through a newly proposed CNN architecture. The combination of pre-processing steps MFCC, Melspectrogram, and Chroma CENS with CNN improvise the performance of the proposed system, which helps to make an accurate diagnosis of lung sounds. The comparative analysis shows how the proposed approach performs better with previous state-of-the-art research approaches. It also shows that there is no need for a wheeze or a crackle to be present in the lung sound to carry out the classification of respiratory pathologies.

Psychometric profiling of individuals using Twitter profiles: A psychological Natural Language Processing based approach

Journal

Journal NameConcurrency and Computation: Practice and Experience

Title of PaperPsychometric profiling of individuals using Twitter profiles: A psychological Natural Language Processing based approach

PublisherWiley Online Library

Page Number7029

Published YearApril 2022

ISSN/ISBN Nohttps://doi.org/10.1002/cpe.7029

Indexed INScopus, Web of Science

Abstract

The recent pandemic saw the operations of many businesses shifting to virtual mode. Tasks like psychometric analysis of individuals, for various applications, are conducted online. In this article, we introduce a novel system to analyze the semantics of an individual's tweets from their Twitter profile using LIWC and SALLEE scores. These scores can be used to evaluate less fortunate, thin-filed candidates using their Twitter profiles. With increased access to phones and the internet, many organizations are focusing on making credit systems available to the masses by introducing psychometric analysis. This article proposes a dynamic model for evaluating the personality of a Twitter user using the textual content shared on their page. The model will allow stakeholders to ascertain the personality of user according to any personality model. To analyze if this is viable and flexible approach to model any kind of personality model, we take MBTI personality dataset and train classifier to predict personality types. Then these results are correlated with a linguistic score to find correlation between the two. We found that proposed approach, outperformed the other relevant works also some aspects of these linguistic scores show a heavy correlation with certain personality types.

GraDex—Graph-Based Data Analytics for Extractive Text Summarization

Book Chapter

Book NameEmerging Technologies for Computing, Communication and Smart Cities pp 303–316 (Lecture Notes in Electrical Engineering book series (LNEE,volume 875))

PublisherSpringer, Singapore

Author NameMaher Thakkar, Siddhant Patel, Jai Prakash Verma

Page Number303–316

Chapter TitleGraDex—Graph-Based Data Analytics for Extractive Text Summarization

Published YearApril 2022

ISSN/ISBN No978-981-19-0284-0

Indexed INScopus

Abstract

This paper aims to brief the reader about different Automatic Text Summarization methods and their efficiency when it comes to providing meaningful summaries. In this paper, we have conducted comparative research between the BERT model for text embeddings along with K-Means clustering to identify sentences closest to the centroid for summary selection, and a Word Frequency algorithm that computes the frequency of appearing word, assigns appropriate weights and selects sentences based on a threshold score. The purpose of this is to compare the two different approaches, for Reviews and Feedback Analysis of different texts and their summaries. Through our research, we were able to find that BERT outperforms the Word Frequency model according to all the evaluation metrics and this is clearly demonstrated in the following sections of the paper.

Context-Enriched Machine Learning-Based Approach for Sentiment Analysis

Conference

Title of PaperContext-Enriched Machine Learning-Based Approach for Sentiment Analysis

Proceeding NameRecent Innovations in Computing (Lecture Notes in Electrical Engineering book series (LNEE,volume 855))

PublisherSpringer, Singapore

Author NameKheruwala Hamza Abubakar, Mohammed S Ahmad, Jai Prakash Verma, Sudeep Tanwar, Pradeep Kumar Singh

OrganizationICRIC 2021

Year , VenueApril 2022 , Central University, Jammu

Page Number67-84

ISSN/ISBN No978-981-16-8892-8

Indexed INScopus

Abstract

The advent of technology has given rise to a tremendous rise in people sharing information and voicing their opinions over different platforms. Several research studies have been focused on the analysis and prediction of political events through the “sentiment” perspective. Here, we present a comparative analysis of different approaches used by various researchers in this area. Also, an experiment-based analysis is presented with sentiment analysis for the situation of reservations in India with the consideration of public opinion on tweets, news reviews, and word of influential leaders with a huge number of public following to ensure that their opinions had a considerable impact with a bigger audience. We use a novel analysis model by employing SVM with grid search for sentiment analysis. The detailed discussion showcased is an intensive study of different methodologies adopted, which is of use to researchers looking to pursue this domain.

Automatic Speech Emotion Recognition Using Cochleagram Features

Conference

Title of PaperAutomatic Speech Emotion Recognition Using Cochleagram Features

Proceeding NameRecent Innovations in Computing (Lecture Notes in Electrical Engineering book series (LNEE,volume 855))

PublisherSpringer, Singapore

Author NameSaumya Borwankar, Dhruv Shah, Jai Prakash Verma, Sudeep Tanwar

OrganizationICRIC 2021

Year , VenueApril 2022 , Central University, Jammu

Page Number453–466

ISSN/ISBN No978-981-16-8892-8

Indexed INScopus

Abstract

Speech Emotion Recognition (SER) has become a popular field in recent years. The efficiency of the SER system is determined by how much useful information is present in the extracted features. Ongoing research has come close to achieve state-of-the-art results using neural networks like Convolutional Neural Networks (CNN) with the extracted features. Speech emotion detection deals with the recognition of the speaker’s emotion from their speech sample. This detection helps us in recognizing the psychological and physical state. In this work, we have worked with two publicly available corpora—Surrey Audio-Visual Expressed Emotion (SAVEE) and Toronto Emotional Speech Set (TESS). In this paper, we approach this problem with the help of cochleagrams, we first extract cochleagram features from all the audio files and then classify different classes with the help of convolutional neural network architecture …

Graph-based data analysis in Big Data Computing Environment: An investigation of Flight Network Datasets

Conference

Title of PaperGraph-based data analysis in Big Data Computing Environment: An investigation of Flight Network Datasets

Proceeding NameProceedings of 2nd International Conference on Artificial Intelligence: Advances and Applications

PublisherSpringer, Singapore

Author NameNaishadh Mehta, Anand Ruparelia, Jai Prakash Verma, Manoj Kumar Khinchi

OrganizationPoornima College of Engineering, Jaipur and Rajasthan Technical University Kota

Year , VenueJanuary 2022 , Poornima College of Engineering, Jaipur

Page Number699-710

ISSN/ISBN No978-981-16-6332-1

Indexed INScopus

Abstract

The airline industry has always been a cornerstone in the growing economies of the world and also stands to be the most efficient mode of transport for many decades. Being such a prime industry, it requires vital operational analytics for productive decision-making, which is directly related to revenue generation, and being a data-driven industry, Big Data analytics and especially graph-based analytics turn out to be the appropriate match for generating actionable insights from airline network data. The research work here applies algorithms such as the PageRank algorithm and Label Propagation algorithm to the flight network data. The results generated are helpful in achieving business objectives such as discovering the most influential airports and finding airport communities among the airline network that ultimately leads to effective flight route planning.

Investigation of IoMT-Based Cancer Detection and Prediction

Book Chapter

Book NameCancer Prediction for Industrial IoT 4.0: A Machine Learning Perspective

PublisherChapman and Hall/CRC

Author NameMeet Shah, Harsh Patel, Jai Prakash Verma, Rachna Jain

Page Number1-15

Chapter TitleInvestigation of IoMT-Based Cancer Detection and Prediction

Published YearDecember 2021

ISSN/ISBN NoMeet Shah, Harsh Patel, Jai Prakash Verma, Rachna Jain

Indexed INScopus

Abstract

Cancer is a genetic disease caused by the unregulated growth of normal cells into tumor cells that happens in a multistage process. According to the World Health Organization, almost 19.3 million cancer cases were reported in 2020, and an estimated 28.4 million cases are projected to occur in 2040. The disease is more likely to be treated if diagnosed at an early stage. For example, 9 out of 10 women diagnosed with ovarian cancer at its earliest stage survive for at least 5 years, which is reduced to just 1 out of 10 women when ovarian cancer is diagnosed at the most advanced stage. Despite the growth of Internet of Medical Things (IoMT) technology, there remains a lack of appropriate data needed to train machine learning/deep learning models for the use cases defined. The data accumulated are unstructured at times, which leads to an unnecessary increase of computational load. The objective of the research …

Fractal-Based Speech Emotion Detection Using CNN

Book Chapter

Book NameSoft Computing for Problem Solving

PublisherSpringer, Singapore

Author NameSaumya Borwankar, Manmohan Dogra, Jai Prakash Verma

Page Number741-755

Chapter TitleFractal-Based Speech Emotion Detection Using CNN

Published YearOctober 2021

ISSN/ISBN No978-981-16-2709-5

Indexed INScopus

Abstract

In our day-to-day life, speech is the primary medium of communication between humans. All the interpersonal communication that takes place is emotional. There is often a need to predict the emotion of the intended speech to understand the emotional and psychological response for the state of the person. Now machines can automate this task with the help of machine learning, so the task of speech emotion detection has seen many developments. In this paper, we have looked at a different feature for the classification of speech emotion and we have analyzed the results on three publicly available datasets, namely, Surrey Audio-Visual Expressed Emotion (SAVEE), Toronto emotional speech set (TESS), and Berlin Database of Emotional Speech (Emo-DB) with the help of convolutional neural networks. The accuracy of the proposed model reaches around 97% which is better than previous approaches. This robust Speech Emotion Recognition (SER) system can help people in many sectors like healthcare, accident prevention to name a few.

Fog Computing Based Architecture for Smart City Projects and Applications

Book Chapter

Book NameEnergy Conservation Solutions for Fog-Edge Computing Paradigms

PublisherSpringer, Singapore

Author NameJai Prakash Verma

Page Number191-213

Chapter TitleFog Computing Based Architecture for Smart City Projects and Applications

Published YearSeptember 2021

ISSN/ISBN No978-981-16-3448-2

Indexed INScopus

Abstract

Fog computing is an extension to cloud computing, offering benefits such as minimal latency, wide geographical distribution, and location awareness by providing flexible services at the edge of the network. The onset of fog computing has catered solutions to many applications, Smart City projects being one of them. Fog computing has the potential to deliver an impact in smart city projects, as the former application involves economic and social aspects along with the technical aspect. The increase in city urbanization demands smart solutions that tackle critical problems such as healthcare, mobility, infrastructure, parking space availability, waste management, and energy consumption. Industry 4.0 conceptualizes that, Internet of Things (IoT) along with fog computing would be used for the development of a network of devices. These devices function independently in real-time and provide the required infrastructure for a smart city. This research study presents a comprehensive literature survey on the deployment architectures of fog computing in smart city applications such as Smart Waste Management and Smart Parking. An emphasis is laid more on the integration of Industry 4.0’s core concepts and fog computing while also taking into consideration the deployment aspects. With the proposed architectures and mentioned approaches, improvements would be seen in terms of resource utilization, processing overhead, and latency. In the latter part of the research survey, the potential merits of the proposed approaches and future work directions are discussed.

A Knowledge Investigation Framework for Crowdsourcing Analysis for e-Commerce Networks

Book Chapter

Book NameMachine Learning and Deep Learning Techniques in Wireless and Mobile Networking Systems

PublisherCRC Press

Author NameHarsh Jigneshkumar Patel, Dipanshi Digga, Jai Prakash Verma

Page Number225-247

Chapter TitleA Knowledge Investigation Framework for Crowdsourcing Analysis for e-Commerce Networks

Published YearSeptember 2021

ISSN/ISBN No9781003107477

Indexed INScopus

Abstract

This chapter presented a novel approach to solve the problem of redundancy and wastage of computational resources with the help of review nodes representation system. The review text data were mined for the various aspects and features present in the text corpus. This was done using the LSTM network, which produced a higher accuracy compared to the CNN and the RNN. Then the review text data were clus- tered on the basis of the aspects that the nodes consist of with the help of PageRank algorithm, which calculates a relativity index that helps the clustering process of the nodes and the selection of the representative node for each aspect mined from the text corpus. The accuracy of the aspect mining along with the review node representation was 91.0823%.

Improvised VGG16 CNN Architecture for Predicting Tuberculosis Using the Frontal Chest X-Ray Images

Book Chapter

Book NameSmart Systems: Innovations in Computing

PublisherSpringer, Singapore

Author NameSmit B Patel, Parth H Patel, Viral D Jain, Jai Prakash Verma

Page Number69-80

Chapter TitleImprovised VGG16 CNN Architecture for Predicting Tuberculosis Using the Frontal Chest X-Ray Images

Published YearSeptember 2021

ISSN/ISBN No978-981-16-2877-1

Indexed INScopus

Abstract

Tuberculosis is an infectious bacterial disease that mainly impacts the lungs. But these bacteria could attack any part of the body such as the kidney, brain, and spine. Therefore, if tuberculosis is not detected early, it could damage the body parts may also lead to death. In contrast to other infectious diseases, the diagnosis of tuberculosis is highly doughty. Numerous checks are usually needed where chest X-rays are mostly used for TB screening. This paper proposes a deep learning-based method to detect tuberculosis from a chest X-ray. For this, we have proposed a VGG16-based model for tuberculosis detection. For training, the model used two publically available datasets Shenzhen and Montgomery datasets. We have achieved 91% and 89% accuracy, respectively, on the Shenzhen and Montgomery datasets. The results we have obtained show promising results in tuberculosis detection.

Fog Computing Based Architecture for Smart City Projects and Applications

Book Chapter

Book NameEnergy Conservation Solutions for Fog-Edge Computing Paradigms

PublisherSpringer, Singapore

Author NameNaishadh Mehta, Anand Ruparelia, Jai Prakash Verma

Page Number191-213

Chapter TitleFog Computing Based Architecture for Smart City Projects and Applications

Published YearSeptember 2021

ISSN/ISBN No978-981-16-3448-2

Indexed INScopus

Abstract

Fog computing is an extension to cloud computing, offering benefits such as minimal latency, wide geographical distribution, and location awareness by providing flexible services at the edge of the network. The onset of fog computing has catered solutions to many applications, Smart City projects being one of them. Fog computing has the potential to deliver an impact in smart city projects, as the former application involves economic and social aspects along with the technical aspect. The increase in city urbanization demands smart solutions that tackle critical problems such as healthcare, mobility, infrastructure, parking space availability, waste management, and energy consumption. Industry 4.0 conceptualizes that, Internet of Things (IoT) along with fog computing would be used for the development of a network of devices. These devices function independently in real-time and provide the required infrastructure for a smart city. This research study presents a comprehensive literature survey on the deployment architectures of fog computing in smart city applications such as Smart Waste Management and Smart Parking. An emphasis is laid more on the integration of Industry 4.0’s core concepts and fog computing while also taking into consideration the deployment aspects. With the proposed architectures and mentioned approaches, improvements would be seen in terms of resource utilization, processing overhead, and latency. In the latter part of the research survey, the potential merits of the proposed approaches and future work directions are discussed.

Shortest Pathfinder for Air Traffic Network: A Graph-Based Analysis

Conference

Title of PaperShortest Pathfinder for Air Traffic Network: A Graph-Based Analysis

Proceeding NameProceedings of the International e-Conference on Intelligent Systems and Signal Processing

PublisherSpringer, Singapore

Author NamePiyushi Jain, Drashti Patel, Jai Prakash Verma

OrganizationGCET, Anand, Gujarat

Year , VenueAugust 2021 , GCET, Anand, Gujarat

Page Number699-712

ISSN/ISBN No978-981-16-2123-9

Indexed INScopus

Abstract

Air Traffic Management is the dynamic, integrated management of air traffic. There has been a dramatic increase in people who are preferring airways over the traditional transportation system as it saves time. The growth will generate countless new routes and require hundreds of new airports and thousands of new planes and pilots. Most of the traffic management is done throughout the flight to help the pilot with ongoing traffic above there. Due to this rapid growth of passengers and the increasing environmental concerns, there is a need to find the shortest and efficient path for any flight considering distance and time. Using graph theory’s Dijkstra algorithm, the shortest point between a source and a distance could be calculated. The shortest path based on parameters including distance and time has been implemented with Neo4j and Apache Spark and hence a comparative study between the two software has also been done. The model was trained using a dataset of air routes of Oceania and was able to predict the best route in terms of distance and time separately. Neo4j provides visual results in the form of a graph while spark provides the shortest distance and route followed in the path. An optimal path that is derived using the shortest distance on the cost of time or vice versa is not only the findings of the system. An equation could be derived that would balance both distance and time. That equation can also be extended to take care of parameters like traffic, weather conditions, and country borders or restricted areas.

Leveraging Deep Learning Techniques on Remotely Sensing Agriculture Data

Book Chapter

Book NameCommunication and Intelligent Systems

PublisherSpringer

Author NameAjaysinh Vikramsinh Kathiya, Jai Prakash Verma, Sanjay Garg

Page Number955-965

Chapter TitleLeveraging Deep Learning Techniques on Remotely Sensing Agriculture Data

Published YearJune 2021

ISSN/ISBN No978-981-15-3325-9

Indexed INScopus

Abstract

Crop yield prediction is very beneficial for the farmers to predict their profit. It can be used by private firms to make business decisions and governments to plan food security as well as planning imports and exports. Several published state-of-the-art techniques rely on handcrafted data. Our model deals with remotely sensed data to predict crop yield using deep learning algorithms such as CNN and LSTM. This model has proved better than existing techniques on evaluation based on its RMSE value. We have leveraged the capabilities of both algorithms to increase the accuracy of crop yield prediction and have successfully closed upon a model that surpassed the accuracy of previously used approaches.

A deep learning based approach for trajectory estimation using geographically clustered data

Journal

Journal NameSN Applied Sciences

Title of PaperA deep learning based approach for trajectory estimation using geographically clustered data

PublisherSpringer Nature

Volume Number3

Page Number1-17

Published YearJune 2021

ISSN/ISBN No2523-3971

Indexed INScopus, Web of Science

Abstract

This study presents a novel approach to predict a complete source to destination trajectory of a vehicle using a partial trajectory query. The proposed architecture is scalable to extremely large-scale data with respect to the dense road network. A deep learning model Long Short Term Memory (LSTM) has been used for analyzing the temporal data and predicting the complete trajectory. To handle a large amount of data, clustering of similar trajectory data is used that helps in reducing the search space. The clusters based on geographical locations and temporal values are used for training different LSTM models. The proposed approach is compared with the other published work on the parameters as Average distance error and one step prediction accuracy The one-step prediction accuracy is as good as 81% and Distance error are. 33 Km.

Computer-Aided-Diagnosis System for Symptom Detection of Breast and Cervical Cancer

Book Chapter

Book Name Lecture Notes in Networks and Systems

PublisherSpringer

Author NamePiyushi Jain, Drashti Patel, Jai Prakash Verma, Sudeep Tanwar

Page Number743-758

Chapter TitleComputer-Aided-Diagnosis System for Symptom Detection of Breast and Cervical Cancer

Published YearMay 2021

ISSN/ISBN No23673370, 23673389

Indexed INScopus

Abstract

As witnessed,’ Cancer metastasis is the leading cause of death worldwide, lots of efforts done for understanding the pathology of cancer for prognosis and diagnosis. Cancer treatment at an early stage can increase the chances of survival of the sufferer considerably. This research aims to contribute to the detection of breast and cervical cancer in the early stages. A comparative study of classification techniques includes Support Vector Classifier (SVC), Multi-layer Perceptron (MLP), and Random Forest (RF) has done to identify the best model for cancer prediction. These models are differentiated for different symptoms collected from electronic health care data. A correlation matrix with a heat map is used for symptoms/feature selection from the results of biopsy examinations applied on a dataset collected from the UCI repository. The predictive model based on Random forest techniques achieves the highest …

Improvised VGG16 CNN Architecture for Predicting Tuberculosis Using the Frontal Chest X-Ray Images

Conference

Title of PaperImprovised VGG16 CNN Architecture for Predicting Tuberculosis Using the Frontal Chest X-Ray Images

Proceeding NameSmart Systems: Innovations in Computing

PublisherSpringer, Singapore

Author NameJai Prakash Verma

OrganizationSSIC 2021, Manipal University, Jaipur, India

Year , VenueJanuary 2021 , SSIC 2021, held in Manipal University, Jaipur, India

Page Number69-80

ISSN/ISBN No978-981-16-2877-1

Indexed INScopus

Predictive Analysis for User Mobility Using Geospatial Data

Book Chapter

Book NameRecent Innovations in Computing

PublisherSpringer Singapore

Author NameJai Prakash Verma, Sudeep Tanwar, Archies Desai, Poojan Khatri, Zdzislaw Polkowski

Page Number845-857

Chapter TitlePredictive Analysis for User Mobility Using Geospatial Data

Published YearJanuary 2021

ISSN/ISBN No1876-1100

Indexed INScopus

Abstract

Extremely usage of smart wearable devices such as smartphones and smartwatches which contain various sensors for location detection such as Wi-Fi, LTE, GPS and motion detection such as accelerometer, it has become easier to obtain user mobility data. Today communication systems are becoming more popular due to the developments in communication technologies. There are various services provided which also help to access the data such as video, audio, images from which we can be used to grab the information or pattern of user mobility. The user mobility where user’s movements and locations can be predicted using various methods and algorithms. It can be predicted through data mining, machine learning, and deep learning algorithms where user’s data are fetched from the communication system. A comparative data mining model base on DBSCAN and RNN-LSTM was proposed for …

Predictive Analysis for User Mobility Using Geospatial Data

Book Chapter

Book NameRecent Innovations in Computing

PublisherSpringer, Singapore

Author NameJai Prakash Verma, Sudeep Tanwar, Archies Desai, Poojan Khatri, Zdzislaw Polkowski

Page Number845-857

Chapter TitlePredictive Analysis for User Mobility Using Geospatial Data

Published YearJanuary 2021

ISSN/ISBN No18761119, 18761100

Indexed INScopus, Web of Science

Abstract

Extremely usage of smart wearable devices such as smartphones and smartwatches which contain various sensors for location detection such as Wi-Fi, LTE, GPS and motion detection such as accelerometer, it has become easier to obtain user mobility data. Today communication systems are becoming more popular due to the developments in communication technologies. There are various services provided which also help to access the data such as video, audio, images from which we can be used to grab the information or pattern of user mobility. The user mobility where user’s movements and locations can be predicted using various methods and algorithms. It can be predicted through data mining, machine learning, and deep learning algorithms where user’s data are fetched from the communication system. A comparative data mining model base on DBSCAN and RNN-LSTM was proposed for predicting the user’s future location-based information predicted from the last locations reported. Mobility prediction based on the transition matrix prediction is done from cell to cell and calculated with the help of the previous inter-cell movement.

Blockchain Based Framework for Document Authentication and Management of Daily Business Records

Book Chapter

Book NameBlockchain for 5G-Enabled IoT

PublisherSpringer

Author NamePrakrut Chauhan, Jai Prakash Verma, Swati Jain, Rohit Rai

Page Number497-517

Chapter TitleBlockchain Based Framework for Document Authentication and Management of Daily Business Records

Published YearDecember 2020

ISSN/ISBN No978-3-030-67490-8

Indexed INScopus

Event-Triggered Share Price Prediction

Book Chapter

Book NameEvolving Technologies for Computing, Communication and Smart World

PublisherLecture Notes in Electrical Engineering

Author NameJay Pareshkumar Patel, Nikunj Dilipkumar Gondha, Jai Prakash Verma, Zdzislaw Polkowski

Page Number83-96

Chapter TitleEvent-Triggered Share Price Prediction

Published YearNovember 2020

ISSN/ISBN No18761119, 18761100

Indexed INScopus, Web of Science

Abstract

The stock market price analysis or the prediction of the stock prices has always been a classical problem because of the fluctuating prices of the stocks for a particular company based on the economy. This stock market price analysis/prediction problem has attracted researchers from various fields like statistics, machine learning (ML), deep learning (DL), etc. The analysis or prediction of the stock prices will help the individuals/customers to buy/sell shares of a particular company in order to incur profit. The aim of the proposed paper is to accurately predict the future prices of shares of a company. The prediction on prices can be done through various techniques or methods of machine learning and deep learning. In this paper, we are proposing a hybrid approach of deep learning neural network long short-term memory (LSTM) with sentiment analysis to predict the variations in share prices. First, we apply sentiment analysis on the various company news, market sentiments and get the values. Then, the sentiment results are combined with the LSTM features and observed the results. We predicted the variations in the prices of the stocks for one day and for 30 days long-time period. The observation that we got is very helpful to get the idea of a particular company’s future variations in share prices.

Lecture Notes in Electrical Engineering

Book Chapter

Book NameEvolving Technologies for Computing, Communication and Smart World

PublisherSpringer, Singapore

Author NameHarsh Jigneshkumar Patel, Jai Prakash Verma, Atul Patel

Chapter TitleLecture Notes in Electrical Engineering

Published YearNovember 2020

ISSN/ISBN No18761119, 18761100

Indexed INScopus, Web of Science

Abstract

The sentiment analysis performed using the general methodologies, i.e., lexicon and neural networks based mainly on the content written by the user. They all are mainly content-centric methodologies. The aspect of the user’s mindset and sentiment for writing the reviews is never considered and the emotions of the writer. In this paper, we are proposing the consideration of these aspects and their impact. They are accommodated on the basis of the sentiment score of the review written by the user. The intensity of the words used to describe the product or an issue matters significantly in the classification of the product features. Unsupervised learning methods were used to calculate more precise sentence-level sentiments with the help of contextual dependencies. They are more suitable for the aspect-based sentiment analysis as they are found to be more adaptable to different contexts and domains with the change in information rather than changing the entire model structure. The clustering algorithms are used for segregating the different types of groups related to viral sharing of ads. Various factors can be analysed to decide whether the ad is shared by a user or not.

Crowdsourced Social Media Reaction Analysis for Recommendation

Journal

Journal NameInternational Journal of Knowledge and Systems Science (IJKSS)

Title of PaperCrowdsourced Social Media Reaction Analysis for Recommendation

PublisherIGI Global

Volume Number12

Page Number1-19

Published YearNovember 2020

ISSN/ISBN No1947-8208

Indexed INScopus, Web of Science

Abstract

A pre-analysis is always important for crucial decision making in many events where reviews, feedback, and comments posted by different stakeholders play an important role. Summaries generated by humans are mostly based on abstractive summarization. It sometimes changes the meaning of the text. This paper proposes a customized extractive summarization approach to generate a summary of large text extracted from social media viz. Twitter, YouTube review, feedback, comments, etc. for a movie. The proposed approach where PageRank with k-means clustering was used to select representative sentences from a large number of reviews and feedback. Cluster heads were selected based on the customization of PageRank. The proposed approach shows improved results over the graph-based TextRank approach with and without synonyms. It can be applied to predict trends for items other than movies through the social media platform.

Comparative Study of Sentiment Analysis and Text Summarization for Commercial Social Networks

Book Chapter

Book NameCommunications in Computer and Information Science

Publisher© Springer Nature Singapore Pte Ltd. 2020

Author NameHamza Abubakar Kheruwala, Jimeet Viren Shah, Jai Prakash Verma

Page Number213-224

Chapter TitleComparative Study of Sentiment Analysis and Text Summarization for Commercial Social Networks

Published YearJuly 2020

ISSN/ISBN No18650929

Indexed INScopus

Abstract

The rapid shift towards digitalization today has actually transferred the market to an entirely digitalized platform. The participation of such a large number of users has given rise to a huge amount of data over the internet, proving the need for proper structuring and removal of unwanted and redundant data. The presence of a system that gives them the complete overview of a product is a dire need for the public today. Diving deep, we nd technologies that help us in the analysis and modification of data found over the internet. Sentiment analysis helps us nd the opinions people have towards a variety of entities, through a series of processes. Along with this, we have text summarisation which aids in the attainment of meaningful information from the wide range of irrelevant and redundant data found online. Clubbing these two, we can obtain concise reviews in addition to the overall sentiment towards selected entities. Here, we propose a model where we convolve into a system that provides the user with the overall recommendation found on popular e-commerce websites (Amazon, Flipkart and TripAdvisor). Starting with the collection of data from given sources, we pre-process the data, we combine machine learning with a lexicon-based approach, obtain the summaries and sentiments and eventually provide the user with the popular opinion behind the product.

GeoHash tag based mobility detection and prediction for traffic management

Journal

Journal NameSN Applied Sciences

Title of PaperGeoHash tag based mobility detection and prediction for traffic management

PublisherSpringer International Publishing

Volume Number2

Page Number1-13

Published YearJuly 2020

ISSN/ISBN No2523-3963 / 2523-3971

Indexed INWeb of Science

Abstract

User mobility detection and prediction can help in many ways for planning and monitoring a population distribution and displacement in a specific area or location. It also helps in planning for resource distribution and allocation. In this paper, we present a study on the mobility of the population which can be monitored by sensors, GPS devices through location detection. All the public transports like buses, taxis, etc. have GPS devices posted that can provide movement of a vehicle in city traffic. For experimental analysis, the T-Drive Taxi Trajectories dataset was selected, in which taxi location data are collected with the information of taxi ID, timestamp, latitude, and longitude. GeoHash tags were generated for the location of a taxi based on latitude and longitude. A graph was built based on vertices as GeoHash tag and edges as a direct link between the GeoHash tags. Graph-Based data analysis was applied to identify the importance of GeoHash tag based on the in-degree and PageRank of the vertices. The mobility path and movement of traffic can be predicted that can be used for disaster management and urban development for city planning.

A Graph Based Analysis of User Mobility for a Smart City Project

Book Chapter

Book NameCommunications in Computer and Information Science

PublisherSpringer

Author NameJai Prakash Verma, Sapan H Mankad, Sanjay Garg

Page Number140-151

Chapter TitleA Graph Based Analysis of User Mobility for a Smart City Project

Published YearNovember 2019

ISSN/ISBN No18650929

Indexed INScopus

Abstract

Information and Communication Technologies (ICT) and Internet of Things (IOT) devices generate large amount of data for any Smart City projects. Data structure for storing multidisciplinary large scale data extracted from these types of data loggers become a challenging task. Research work presented in this paper emphasizes on robust data extraction (data streaming), data preprocessing, and integration. A graph based data analysis on different mobile movement is generated by different mobile tracer (data loggers) placed in diverse locations. Using data ingestion tools like Kafka/Flume/MQTT and Spark-Streaming data can be stored in a distributed storage, HDFS is used for storing such huge size of data. As we know due to the data volume and data generation speed, this problem is considered under Big Data Analysis (BDA) problem. Heat map has been used to depict the movement of customer carrying mobile phone in different locations of store. A ping signal collected whenever a person is moving from the range of sensor device. PageRank algorithm is used to assign a numerical rank to each vertex as per the in-degree links to that vertex. It considers a random walk from any selected vertex with the traversed connected vertexes. The rank of vertices that are representing mobile tracer sensors shows the movement of customers during a specific time period. It can be used for making decision about the reorganization of a store layout.

Big Data Analytics: Performance Evaluation for High Availability and Fault Tolerance using MapReduce Framework with HDFS

Conference

Title of PaperBig Data Analytics: Performance Evaluation for High Availability and Fault Tolerance using MapReduce Framework with HDFS

Proceeding Name2018 IEEE - Fifth International Conference on Parallel, Distributed and Grid Computing (PDGC - 2018)

PublisherIEEE

Author NameJai Prakash Verma, Sapan H Mankad, Sanjay Garg

OrganizationJAYPEE UNIVERSITY OF INFORMATION TECHNOLOGY, Himachal Pradesh, India

Year , VenueJune 2019 , JAYPEE UNIVERSITY OF INFORMATION TECHNOLOGY, Himachal Pradesh, India

Page Number770-775

Indexed INScopus

Abstract

Big data analytics helps in analyzing structured data transaction and analytics programs that contain semi-structured and unstructured data. Internet clickstream data, mobile-phone call details, server logs are examples of big data. Relational database-oriented dataset doesn't fit in traditional data warehouse since big data set is updated frequently and large amount of data are generated in real time. Many open source solutions are available for handling this large scale data. The Hadoop Distributed File System (HDFS) is one of the solutions which helps in storing, managing, and analyzing big data. Hadoop has become a standard for distributed storage and computing in Big Data Analytic applications. It has the capability to manage distributed nodes for data storage and processing in distributed manner. Hadoop architecture is also known as Store everything now and decide how to process later. Challenges and issues of multi-node Hadoop cluster setup and configuration are discussed in this paper. The troubleshooting for high availability of nodes in different scenarios for Hadoop cluster failure are experimented with different sizes of datasets. Experimental analysis carried out in this paper helps to improve uses of Hadoop cluster effectively for research and analysis. It also provides suggestions for selecting size of Hadoop cluster as per data size and generation speed.

Evaluation of Pattern Based Customized Approach for Stock Market Trend Prediction With Big Data and Machine Learning Techniques

Journal

Journal NameInternational Journal of Business Analytics

Title of PaperEvaluation of Pattern Based Customized Approach for Stock Market Trend Prediction With Big Data and Machine Learning Techniques

PublisherIGI Global

Volume Number6

Page Number1-15

Published YearFebruary 2019

ISSN/ISBN No2334-4547

Indexed INScopus, Web of Science

Abstract

The stock market is very volatile and non-stationary and generates huge volumes of data in every second. In this article, the existing machine learning algorithms are analyzed for stock market forecasting and also a new pattern-finding algorithm for forecasting stock trend is developed. Three approaches can be used to solve the problem: fundamental analysis, technical analysis, and the machine learning. Experimental analysis done in this article shows that the machine learning could be useful for investors to make profitable decisions. In order to conduct these processes, a real-time dataset has been obtained from the Indian stock market. This article learns the model from Indian National Stock Exchange (NSE) data obtained from Yahoo API to forecast stock prices and targets to make a profit over time. In this article, two separate algorithms and methodologies are analyzed to forecast stock market trends and iteratively improve the model to achieve higher accuracy. Results are showing that the proposed pattern-based customized algorithm is more accurate (10 to 15%) as compared to other two machine learning techniques, which are also increased as the time window increases.

Data Consumption-Aware Load Forecasting Scheme for Smart Grid Systems

Conference

Title of PaperData Consumption-Aware Load Forecasting Scheme for Smart Grid Systems

Proceeding Name2018 IEEE Globecom Workshops (GC Wkshps),

PublisherIEEE Globecom

Author NameJai Prakash Verma

Organization2018 IEEE Globecom Workshops (GC Wkshps), Abu Dhabi, United Arab Emirates, United Arab Emirates

Year , VenueDecember 2018 , Abu Dhabi, United Arab Emirates, United Arab Emirates

Page Number1-6

ISSN/ISBN NoISBN: 978-1-5386-4920-6 , ISBN: 978-1-5386-6977-8

Indexed INScopus

Abstract

With the realisation of the Smart Grids (SG) infrastructure at a large scale, demand predictions can be mapped more accurately. Systems base forecasts on user consumption patterns have mined from old feedback systems to modern extensive sensor based network technologies. Therefore, to derive the usage functions, it is essential to perceive such conditions. These directly impact the power needs and the lifestyle of the consumers, and hence, aid in understanding the user behavior and correspondingly manage power generation. This study propounds mean weather conditions as pivotal to determining power usage. Employing a time based data driven approach, this research functions to predict load expectation in various utilization sectors. Repositioning the adoption of climatic conditions from absolute to relative, the investigation establishes the dependence of collective load prediction on the general weather. The simulation results prove that the time dependent load forecasting model accurately predicts the energy demand of residential and commercial sector.

A Range-Based Approach for Long-Term Forecast of Weather Using Probabilistic Markov Model

Conference

Title of PaperA Range-Based Approach for Long-Term Forecast of Weather Using Probabilistic Markov Model

Proceeding Name 2018 IEEE International Conference on Communications Workshops (ICC Workshops)

Publisher 2018 IEEE International Conference on Communications Workshops (ICC Workshops)

Author NameJai Prakash Verma

Organization 2018 IEEE International Conference on Communications Workshops (ICC Workshops)

Year , VenueMay 2018 , Kansas City, MO, USA

Page Number1-6

ISSN/ISBN No2474-9133

Indexed INScopus

Abstract

Weather forecasts serve to incline individual behaviors and interactions, commercial intentions and organizational efforts. A normal user is usually indifferent to weather statistics and corresponding value predictions but obtains an approximate idea from the average weather conditions. Forecasts justifying overall conditions for a duration which is usually rely on previous observations. Correspondingly, they extend the probability of inducing incorrect predictions as relatively insignificant variations consequently compound to substantial errors. As such, long term predictions are usually limited and unreliable. This paper aims to bridge this gap, by adopting a range specific approach to a probabilistic markov model (PMM). To develop a certainty in availability, we employ a cloud server to house for the analytics. We have achieved a considerable rise in accuracy in the results, along with a simplistic convenience for the user as compared to other available state-of- the-art methods.

Evaluation of Unsupervised Learning based Extractive Text Summarization Technique for Large Scale Review and Feedback Data

Journal

Journal NameIndian Journal of Science and Technology

Title of PaperEvaluation of Unsupervised Learning based Extractive Text Summarization Technique for Large Scale Review and Feedback Data

PublisherIndian Journal of Science and Technology

Volume Number10

Page Number17-22

Published YearMay 2017

ISSN/ISBN NoISSN (Print) : 0974-6846, ISSN (Online) : 0974-5645

Indexed INWeb of Science

Abstract

Background/Objectives: Supervised techniques uses human generated summary to select features and parameter for summarization. The main problem in this approach is reliability of summary based on human generated parameters and features. Many researches have shown the conflicts in summary generated. Due to diversity of large scale datasets, supervised techniques based summarization also fails to meet the requirements. Big data analytics for text dataset also recommends unsupervised techniques than supervised techniques. Unsupervised techniques based summarization systems finds representative sentences from large amount of text dataset. Methods/Statistical Analysis: Co-selection based evaluation measure is applied for evaluating the proposed research work. The value of recall, precision, f-measure and similarity measure are determined for concluding the research outcome for the respective objective. Findings: The algorithms like KMeans, MiniBatchKMeans, and Graph based summarization techniques are discussed with all technical details. The results achieved by applying Graph Based Text Summarization techniques with large scale review and feedback data found improvement over previously published results based on sentence scoring using TF and TF-IDF. Graph based sentence scoring method is much efficient than other unsupervised learning techniques applied for extractive text summarization. Application/Improvements: The execution of graph based algorithm with Spark’s Graph X programming environment will secure execution time for this types of large scale review and feedback dataset which is considered under Big Data Problem.

Web Warehouse: Issues and Challenges for Web Data Mining

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperWeb Warehouse: Issues and Challenges for Web Data Mining

Publisher International Journal of Advanced Research in Computer Science

Volume Number8

Page Number645-649

Published YearMay 2017

Indexed INEBSCO

Abstract

Web Mining defines as extracting knowledge from web. Its types are web uses mining, web content mining, and web structured mining. Each category requires handling the issues of heterogeneous behaviour of web data. This paper will focus on the issues of web data, web mining and its applications. The detailed architecture of web warehouse is also proposed. Each component of architecture requires more exploration and research. As well as paper describe Knowledge as a Service (KAAS) and Web Warehousing as a Service (WWAAS) as web mining applications with cloud computing. The implementation of web warehouse as KAAS and WWAAS with cloud computing is proposed as future extension of this work.

Text Data Analysis: Computer Aided Automated Assessment System

Conference

Title of PaperText Data Analysis: Computer Aided Automated Assessment System

Proceeding Name3rd IEEE International Conference on "Computational Intelligence and Communication Technology" (IEEE-CICT 2017)

Publisher 2017 3rd International Conference on Computational Intelligence & Communication Technology (CICT)

Author NameJai Prakash Verma

Organization 2017 3rd International Conference on Computational Intelligence & Communication Technology (CICT)

Year , VenueFebruary 2017 , Ghaziabad, India

Page Number1-5

ISSN/ISBN No ISBN: 978-1-5090-6218-8, ISBN: 978-1-5090-6219-5

Indexed INScopus

Abstract

Computer aided evaluation systems are generally considered objective types of questionnaires. Evaluation based on subjective answer is consider a problem under text analytics, where text answer will be compare with available correct text answer. This paper is emphasizing the issues of computer aided automated assessment and proposing a model for handling these issues. Using such mechanism a faculty can avoid the evaluation process manually. Students can be automatically graded using the application and given a summary report.

Comparison of MapReduce and Spark Programming Frameworks for Big Data Analytics on HDFS

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperComparison of MapReduce and Spark Programming Frameworks for Big Data Analytics on HDFS

PublisherInternational Journal of Computer Science & Communication

Volume Number7

Page Number80-84

Published YearJune 2016

Abstract

Use of internet and all the types of computer automated systems generates large amount of data in different forms. Due to large volume, different types of varieties, and high velocity of this type of data emerges the Big Data Problem. Spark and MapReduce programming frameworks provide an effective open source solution for managing and analyzing the Big Data. Today researcher are comparing both the frameworks and making many interpretations which also generates many misconceptions about the performances and efficiency. In this paper we are discussing the working model of both the programming frameworks and by experimental analysis, we are also finding that Spark is three to four times faster than MapReduce paradigm on single node implementation of Hadoop Distributed File System.

An Extractive Text Summarization approach for Analyzing Educational Institution’s Review and Feedback Data

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperAn Extractive Text Summarization approach for Analyzing Educational Institution’s Review and Feedback Data

PublisherInternational Journal of Computer Applications

Volume Number143

Page Number51-55

Published YearJune 2016

ISSN/ISBN No0975 – 8887

Indexed INEBSCO

Abstract

Big Data analytics helps the enterprises and institutions to understand and identify the usability of large amount of data generated by their routine operations. All most third forth part of these types of data is semi-structured text data. Many types of actionable insights can be found from these type of semistructured text data that can help strategic management for making right decision. In this paper we are proposing a recommendation system model for understanding and finding actionable insight from the large amount of text data generated for an educational institution. Here we are discussing different type of data generation sources of this types of data as well as data cleaning processes required. The wordcloud for an educational institution is published that help strategic management for understanding the sentiment of different stack holders mainly students. Herewith we are identifying different types of findings from these sets of words that helps for betterment in the functionaries of an Educational Institution.

Big data analysis: recommendation system with Hadoop framework

Conference

Title of PaperBig data analysis: recommendation system with Hadoop framework

Proceeding Name2015 IEEE International Conference on Computational Intelligence & Communication Technology

Publisher2015 IEEE International Conference on Computational Intelligence & Communication Technology

Author NameJai Prakash Verma

Organization2015 IEEE International Conference on Computational Intelligence & Communication Technology

Year , VenueFebruary 2015 , Ghaziabad, India

Page Number92-97

ISSN/ISBN NoISBN: 978-1-4799-6023-1,

Indexed INScopus

Abstract

Recommendation system provides the facility to understand a person's taste and find new, desirable content for them automatically based on the pattern between their likes and rating of different items. In this paper, we have proposed a recommendation system for the large amount of data available on the web in the form of ratings, reviews, opinions, complaints, remarks, feedback, and comments about any item (product, event, individual and services) using Hadoop Framework. We have implemented Mahout Interfaces for analyzing the data provided by review and rating site for movies.

Web Mining: Opinion and Feedback Analysis for Educational Institutions

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperWeb Mining: Opinion and Feedback Analysis for Educational Institutions

PublisherInternational Journal of Computer Applications

Volume Number84

Page Number17-22

Published YearDecember 2013

ISSN/ISBN No0975 – 8887

Indexed INEBSCO

Abstract

Big amount of data available in the forms of reviews, opinions, feedbacks, remarks, comments, observations, clarifications, and explanations that require a robust mechanism to store, retrieve, analyze, and management. In this paper, we are proposing system that provides review or summary of above mention text data available on web for an educational institute. Due to big data size above system can be extended as real time recommendation system for Big Data analysis as future enhancement.

Image to Sound Conversion

Journal

Journal NameInternational Journal of Advance Research in Computer Science and Management Studies

Title of PaperImage to Sound Conversion

PublisherInternational Journal of Advance Research in Computer Science and Management Studies

Volume Number1

Page Number34 - 39

Published YearNovember 2013

ISSN/ISBN NoISSN: 2321-7782 (Online)

Indexed INOthers

Abstract

In this paper we are proposing a system to convert pictures into sound. This proposed system will identify the object from its picture and person will be able to listen to the name of the objects, in the picture. Here we will first get the image from a digital camera then by removing noise by Grey scale and after this Thresholding will be applied. In image processing, thresholding is used to split an image into smaller segments, or junks, using at least one color or grayscale value to define their boundary. After that Object recognizing can be done with Memory-Based Object Recognition Algorithm and object will be identified as Textual name and this name will be stored in the database. Then Optical Character Recognition will be applied to convert text into machine Text. This Text will be converted finally to sound.

Deep Learning-Based Model for Detection of Brinjal Weed in the Era of Precision Agriculture

Journal

Journal NameComputers, Materials & Continua

Title of PaperDeep Learning-Based Model for Detection of Brinjal Weed in the Era of Precision Agriculture

PublisherTechScience

Volume Number77

Page Number1281-1301

Published YearNovember 2023

Indexed INScopus, Web of Science

Abstract

The overgrowth of weeds growing along with the primary crop in the fields reduces crop production. Conventional solutions like hand weeding are labor-intensive, costly, and time-consuming; farmers have used herbicides. The application of herbicide is effective but causes environmental and health concerns. Hence, Precision Agriculture (PA) suggests the variable spraying of herbicides so that herbicide chemicals do not affect the primary plants. Motivated by the gap above, we proposed a Deep Learning (DL) based model for detecting Eggplant (Brinjal) weed in this paper. The key objective of this study is to detect plant and non-plant (weed) parts from crop images. With the help of object detection, the precise location of weeds from images can be achieved. The dataset is collected manually from a private farm in Gandhinagar, Gujarat, India. The combined approach of classification and object detection is applied in the proposed model. The Convolutional Neural Network (CNN) model is used to classify weed and non-weed images; further DL models are applied for object detection. We have compared DL models based on accuracy, memory usage, and Intersection over Union (IoU). ResNet-18, YOLOv3, CenterNet, and Faster RCNN are used in the proposed work. CenterNet outperforms all other models in terms of accuracy, ie, 88%. Compared to other models, YOLOv3 is the least memory-intensive, utilizing 4.78 GB to evaluate the data.

ConCollA-A Smart Emotion-based Music Recommendation System for Drivers

Journal

Journal NameScalable Computing- Practice and Expirence

Title of PaperConCollA-A Smart Emotion-based Music Recommendation System for Drivers

PublisherSCPE

Volume Number24-4

Page Number919-939

Published YearNovember 2023

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science

Abstract

Music recommender system is an area of information retrieval system that suggests customized music recommendations to users based on their previous preferences and experiences with music. While existing systems often overlook the emotional state of the driver, we propose a hybrid music recommendation system - ConCollA to provide a personalized experience based on user emotions. By incorporating facial expression recognition, ConCollA accurately identifies the driver’s emotions using convolution neural network(CNN) model and suggests music tailored to their emotional state. ConCollA combines collaborative filtering, a novel content-based recommendation system named Mood Adjusted Average Similarity (MAAS), and apriori algorithm to generate personalized music recommendations. The performance of ConCollA is assessed using various evaluation parameters. The results show that proposed emotion-aware model outperforms a collaborative-based recommender system.

ConCollA-A Smart Emotion-based Music Recommendation System for Drivers

Journal

Journal NameScalable Computing- Practice and Expirence

Title of PaperConCollA-A Smart Emotion-based Music Recommendation System for Drivers

PublisherSCPE

Volume Number24-4

Page Number919-939

Published YearNovember 2023

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science

Abstract

Music recommender system is an area of information retrieval system that suggests customized music recommendations to users based on their previous preferences and experiences with music. While existing systems often overlook the emotional state of the driver, we propose a hybrid music recommendation system-ConCollA to provide a personalized experience based on user emotions. By incorporating facial expression recognition, ConCollA accurately identifies the driver’s emotions using convolution neural network (CNN) model and suggests music tailored to their emotional state. ConCollA combines collaborative filtering, a novel content-based recommendation system named Mood Adjusted Average Similarity (MAAS), and apriori algorithm to generate personalized music recommendations. The performance of ConCollA is assessed using various evaluation parameters. The results show that proposed emotion-aware model outperforms a collaborative-based recommender system.

Deep Learning-Based Model for Detection of Brinjal Weed in the Era of Precision Agriculture

Journal

Journal NameComputers, Materials & Continua

Title of PaperDeep Learning-Based Model for Detection of Brinjal Weed in the Era of Precision Agriculture

PublisherTechScience

Volume Number77

Page Number1281-1301

Published YearNovember 2023

ISSN/ISBN NoISSN:1546-2218(print)

Indexed INScopus, Web of Science

Abstract

The overgrowth of weeds growing along with the primary crop in the fields reduces crop production. Conventional solutions like hand weeding are labor-intensive, costly, and time-consuming; farmers have used herbicides. The application of herbicide is effective but causes environmental and health concerns. Hence, Precision Agriculture (PA) suggests the variable spraying of herbicides so that herbicide chemicals do not affect the primary plants. Motivated by the gap above, we proposed a Deep Learning (DL) based model for detecting Eggplant (Brinjal) weed in this paper. The key objective of this study is to detect plant and non-plant (weed) parts from crop images. With the help of object detection, the precise location of weeds from images can be achieved. The dataset is collected manually from a private farm in Gandhinagar, Gujarat, India. The combined approach of classification and object detection is applied in the proposed model. The Convolutional Neural Network (CNN) model is used to classify weed and non-weed images; further DL models are applied for object detection. We have compared DL models based on accuracy, memory usage, and Intersection over Union (IoU). ResNet-18, YOLOv3, CenterNet, and Faster RCNN are used in the proposed work. CenterNet outperforms all other models in terms of accuracy, i.e., 88%. Compared to other models, YOLOv3 is the least memory-intensive, utilizing 4.78 GB to evaluate the data.

Three Class Classification of Alzheimer’s Disease Using Deep Neural Networks

Journal

Journal NameCurrent Medical Imaging

Title of PaperThree Class Classification of Alzheimer’s Disease Using Deep Neural Networks

PublisherBentham Science

Volume Number19-8

Page Number855-864(10)

Published YearJuly 2023

ISSN/ISBN NoISSN (Print): 1573-4056

Indexed INScopus, Web of Science

Abstract

Abstract Alzheimer's disease (AD) is a prevalent type of dementia that can cause neurological brain disorders, poor decision making, impaired memory, mood swings, unstable emotions, and personality change. Deep neural networks are proficient in classifying Alzheimer's disease based on MRI images. This classification assists human experts in diagnosing AD and predicts its future progression. The paper proposes various Deep Neural Networks (DNN) for early AD detection to save cost and time for doctors, radiologists, and caregivers. A 3330-image-based Kaggle dataset is used to train the DNN, including 52 images of AD, 717 images of Mild Cognitive Impairment (MCI), and the remaining images of Cognitive Normal (CN). Stratified partitioning splits the dataset into 80% and 20% proportions for training and validation datasets. Proposed models include DenseNet169, DenseNet201, and Res- Net152 DNNs with additional three fully-connected layers and softmax and Kullback Leibler Divergence (KLD) loss function. These models are trained considering pre-trained, partially pre-trained, and fully re-trained extended base models. The KLD loss function reduces the error and increases accuracy for all models. The partially pre-trained DenseNet201 model outperformed all the other models. DenseNet201 gives the highest accuracy of 99.98% for training, 99.07% for validation, and 95.66% for test datasets. The DenseNet201 model has the highest accuracy in comparison to other state-of-artmethods. Keywords: Alzheimer’s disease; DNN; DenseNet; MRI; ResNet; classification.

Three Class Classification of Alzheimer’s Disease Using Deep Neural Networks

Journal

Journal NameCurrent Medical Imaging

Title of PaperThree Class Classification of Alzheimer’s Disease Using Deep Neural Networks

PublisherBentham Science

Volume Number19-8

Page Number855-864(10)

Published YearJuly 2023

ISSN/ISBN NoISSN (Print): 1573-4056

Indexed INScopus, Web of Science

Abstract

Alzheimer’s disease (AD) is a prevalent type of dementia that can cause neurological brain disorders, poor decision making, impaired memory, mood swings, unstable emotions, and personality change. Deep neural networks are proficient in classifying Alzheimer's disease based on MRI images. This classification assists human experts in diagnosing AD and predicts its future progression. The paper proposes various Deep Neural Networks (DNN) for early AD detection to save cost and time for doctors, radiologists, and caregivers. A 3330-image-based Kaggle dataset is used to train the DNN, including 52 images of AD, 717 images of Mild Cognitive Impairment (MCI), and the remaining images of Cognitive Normal (CN). Stratified partitioning splits the dataset into 80% and 20% proportions for training and validation datasets. Proposed models include DenseNet169, DenseNet201, and Res- Net152 DNNs with additional three fully-connected layers and softmax and Kullback Leibler Divergence (KLD) loss function. These models are trained considering pre-trained, partially pre-trained, and fully re-trained extended base models. The KLD loss function reduces the error and increases accuracy for all models. The partially pre-trained DenseNet201 model outperformed all the other models. DenseNet201 gives the highest accuracy of 99.98% for training, 99.07% for validation, and 95.66% for test datasets. The DenseNet201 model has the highest accuracy in comparison to other state-of-artmethods.

Early Prediction of Prevalent Diseases Using IoMT

Book Chapter

Book NameFederated Learning for Internet of Medical Things

PublisherCRC Press

Author NameJigna Patel, Jitali Patel, Rupal Kapdi, Shital Patel

Page Number125-144

Chapter TitleEarly Prediction of Prevalent Diseases Using IoMT

Published YearJune 2023

ISSN/ISBN No9781003303374

Indexed INScopus, Web of Science

Abstract

Improvement in healthcare is essential for developing countries like India to achieve in the age of informatics. Non-communicable diseases such as diabetes and thyroid disease have already replaced communicable diseases as major causes of death. Diabetes is a non-communicable disease prominent to long-term complications and severe health problems. Due to lack of physical activity, work culture, and unhealthy diet and lifestyle, these diseases grow exponentially. Thyroid disease is also one of the most common chronic diseases. There are 60 million adults are suffering from non-communicable diseases in India. According to a health survey, still, 30 million adults’ conditions are unknown, untreated, and undiagnosed. A working population may also be affected if a person is diagnosed with the disease at the age of 30; complications will start at early age. Early prediction of diseases will lead to improved treatment and helps to warn patients to change their lifestyles and reduce future complications; it will also decrease the major economic burden on the nation. Prevention measures for each disease with personal recommendations will spread awareness and minimize the chances of becoming a patient. Internet of Medical Things (IoMT) and data analytics will predict early signs of this prevalent disease. In this chapter, cloud computing-based remote patient monitoring (RPM) architecture is proposed, comprising a data collection module, a data preprocessing module, and a data analytics module. Doctors, patients, caregivers, and family members as stakeholders can access the analytics and prediction results computed by the model. Also, the recommendation module of the architecture will help patients with expert advice for the disease diagnosed.

Early Prediction of Prevalent Diseases Using IoMT

Book Chapter

Book NameFederated Learning for Internet of Medical Things

Publishertaylor and Farncis

Author NameJigna Patel, Jitali Patel, Rupal Kapdi, Shital Patel

Page Number855-864(10)

Chapter TitleEarly Prediction of Prevalent Diseases Using IoMT

Published YearMay 2023

ISSN/ISBN No9781003303374

Indexed INScopus, Web of Science

Abstract

Improvement in healthcare is essential for developing countries like India to achieve in the age of informatics. Non-communicable diseases such as diabetes and thyroid disease have already replaced communicable diseases as major causes of death. Diabetes is a non-communicable disease prominent to long-term complications and severe health problems. Due to lack of physical activity, work culture, and unhealthy diet and lifestyle, these diseases grow exponentially. Thyroid disease is also one of the most common chronic diseases. There are 60 million adults are suffering from non-communicable diseases in India. According to a health survey, still, 30 million adults’ conditions are unknown, untreated, and undiagnosed. A working population may also be affected if a person is diagnosed with the disease at the age of 30; complications will start at early age. Early prediction of diseases will lead to improved treatment and helps to warn patients to change their lifestyles and reduce future complications; it will also decrease the major economic burden on the nation. Prevention measures for each disease with personal recommendations will spread awareness and minimize the chances of becoming a patient. Internet of Medical Things (IoMT) and data analytics will predict early signs of this prevalent disease. In this chapter, cloud computing-based remote patient monitoring (RPM) architecture is proposed, comprising a data collection module, a data preprocessing module, and a data analytics module. Doctors, patients, caregivers, and family members as stakeholders can access the analytics and prediction results computed by the model. Also, the recommendation module of the architecture will help patients with expert advice for the disease diagnose

Brain Tumor Segmentation Using Fully Convolution Neural Network

Conference

Title of PaperBrain Tumor Segmentation Using Fully Convolution Neural Network

Proceeding NameInternational Conference on Recent Innovations in Computing: ICRIC 2022, Volume 1

PublisherSpringer Nature Singapore

Author NameRupal A Kapdi, Jigna A Patel, Jitali Patel

Year , VenueMay 2023 , Jammu,India

Page Number3-15

ISSN/ISBN No1876-1119

Indexed INScopus

Abstract

Early stage brain tumor diagnosis can lead to proper treatment planning, which improves patient survival chances. A human expert advises an appropriate medical imaging scan based on the symptoms. Diagnosis done by a human expert is time-consuming, non-reproducible, and highly dependent on the expert’s expertise. The computerized analysis is preferred to help experts in diagnosis. The paper focuses on implementing a fully convolution neural network to segment brain tumor from MRI images. The proposed network achieves comparable dice similarity with reduced network parameters.

COVID Detection from Chest X-Ray Images Using Deep Learning

Conference

Title of PaperCOVID Detection from Chest X-Ray Images Using Deep Learning

Proceeding NameFourth International Conference on Computing, Communications, and Cyber-Security: IC4S 2022

Publisherspringer

Author NameJigna patel,Parth Nimbadkar, Dhruv Patel, Aayush Panchal, Jai Prakash Verma

OrganizationKrishan Engineering College

Year , VenueDecember 2022 , KEC,Ghaziabad

Page Number855-864(10)

ISSN/ISBN No-

Indexed INScopus

Abstract

The current COVID-19 disease outbreak has been quite difficult and challenging for human society. Early diagnosis of the virus in people and quarantining them are now vital due to the virus' quick spread around the globe. Currently, the most widely used method for testing for COVID-19 is RT-PCR. Though it is widely been used, its accuracy is not as desired. From CXR images, we have proposed using neural networks to forecast a patient's COVID-19 infection status. The COVIDX CXR dataset has been used to train our model. To use the model with ease for the general public, we have developed a web application using Flask for the backend and HTML, CSS, and JavaScript. Using this web application, the user can get the COVID report in a few seconds.

Yoga Pose Estimation Using Machine Learning

Conference

Title of PaperYoga Pose Estimation Using Machine Learning

Proceeding NameInternational Conference on Computing, Communications, and Cyber-Security

PublisherSpringer Nature Singapore

Author NameIshika Shah, Greeva Khant, Jitali Patel, Jigna Patel, Rupal Kapdi

Page Number425-441

Published YearOctober 2022

ISSN/ISBN No2367-3389

Indexed INScopus

Abstract

Yoga, in the Western culture, is considered a form of posture-based physical activity which helps relieve stress and relax your muscles while increasing flexibility. On the other hand, traditional yoga is focused on meditation and released from worldly attachments. It was first brought up in Rigveda with references in the Upanishads. Yoga originated in India, more than 5000 years ago. While some poses in yoga are simple to understand and perform, some poses require precision in the angle at which your body stays to avoid injuries. In this paper, we propose a system to detect the yoga pose of an individual and help them with the correct pose, if wrong. There are several key points detection algorithms that can be used such as OpenPose, PoseNet, and PifPaf. The key points extracted from the video captured are passed to the system, to calculate the angles made by several joints. These angles are used to check whether the posture is correct or not.

BIG DATA ANALYTICS FOR ADVANCED VITICULTURE

Journal

Journal NameScalable Computing

Title of PaperBIG DATA ANALYTICS FOR ADVANCED VITICULTURE

Publisheruniversitatea de vest

Volume Number22

Page Number301-312

Published YearNovember 2021

ISSN/ISBN No18951767

Indexed INScopus, Web of Science

Abstract

Big data analytics involve a systematic approach to find hidden patterns to help the organization grow from large volume and variety of data. In recent years big data analytics is widely used in the agricultural domain to improve yield. Viticulture (the cultivation of grapes) is one of the most lucrative farming in India. It is a subdivision of horticulture and is the study of wine growing. The demand for Indian Wine is increasing at about 27% each year since the 21st century and thus more and more ways are being developed to improve the quality and quantity of the wine products. In this paper, we focus on a specific agricultural practice as viticulture. Weather forecasting and disease detection are the two main research areas in precision viticulture. Leaf disease detection as a part of plant pathology is the key research area in this paper. It can be applied on vineyards of India where farmers are bereft of the latest technologies. Proposed system architecture comprises four modules: Data collection, data preprocessing, classification and visualization. Database module involves grape leaf dataset, consists of healthy images combined with disease leaves such as Black measles, Black rot, and Leaf blight. Models have been implemented on Apache Hadoop using map reduce programming framework. It applies feature extraction to extract various features of the live images and classification algorithm with reduced computational complexity. Gray Level Co-occurrence Matrix (GLCM) followed by K-Nearest Neighborhood (KNN) algorithm. The system also recommends the necessary steps and remedies that the viticulturists can take to assure that the grapes can be salvaged at the right time and in the right manner based on classification results. The overall system will help Indian viticulturists to improve the harvesting process. Accuracy of the model is 82%, and it can be increased as a future work by including deep learning with time-series grape leaf images.

Indexing On Healthcare Big Data

Conference

Title of PaperIndexing On Healthcare Big Data

Proceeding NameInternational Conference on Soft Computing for Problem Solving - SocProS 2020

PublisherSpringer

Author NameDr Jigna Patel,Aneri Mehta,Vahishta Vandriwala,Prof Jitali Patel

OrganizationIIT-Indore

Year , VenueDecember 2020 , IIT,Indore

Indexed INScopus

Abstract

Extensive use of tools and technology in the healthcare field, resulting in big data. Indexing helps in faster retrieval of intended data from very big datasets. Indexing of Big Data becomes a major concern when the querying field is present in very few of the input files, but the number of input files is more. In this paper, authors have built an index structure for the datasets having the querying need the full scan of the entire database even though it can be achieved without reading the majority of the input files. Focused literature survey imparts different indexing methodology with a suitable application area. The inverted index is the most suitable indexing for the COVID-19 dataset, including the details of the patients’ of India. The inverted index is created on the column with state names in the dataset. Map-Reduce programming framework is used for implementation with the Apache Hadoop platform. Algorithms for grouping the data, creation of index and querying is exemplified with the explanation. Test cases are designed on COVID-19 dataset with indexing and without indexing. Time taken to create index and to fetch the records are recorded for various volumetric input files. Result and discussion part of this paper indicate the use of index enhanced performance of querying on big data. The performance that is achieved while querying the database after index construction is much better than the normal querying.

Online Analytical Processing for Business Intelligence in Big Data

Journal

Journal NameBig data

Title of PaperOnline Analytical Processing for Business Intelligence in Big Data

PublisherMarry Ann Liebert

Volume Number8

Page Number501-518

Published YearDecember 2020

ISSN/ISBN No2167-6461

Indexed INScopus, PubMed, Web of Science

Abstract

Online analytical processing (OLAP) approach is widely used in business intelligence to cater the multidimensional queries for decades. In this era of cutting-edge technology and the internet, data generation rates have been rising exponentially. Internet of things sensors and social media platforms are some of the major contributors, leading toward the absolute data boom. Storage and speed are the crucial parameters and undoubtedly the burning issues in efficient data handling. The key idea here is to address these two challenges of big data computing in OLAP. In this article, the authors have proposed and implemented OLAP on Hadoop by Indexing (OOHI). OOHI offers a simplified multidimensional model that stores dimensions in the schema server and measures on the Hadoop cluster. Overall setup is divided into various modules, namely: data storage module (DSM), dimension encoding module (DEM), cube segmentation module, segment selection module (SSM), and block selection and process (BSAP) module. Serialization and deserialization concept applied by DSM for storage and retrieval of the data for efficient space utilization. Integer encoding adopted by DEM in dimension hierarchy is selected to escape sparsity problem in multidimensional big data. To reduce search space by chunks of the cube from the queried chunks, SSM plays an important role. Map reduce-based indexing approach and series of seek operations of BSAP module were integrated to achieve parallelism and fault tolerance. Real-time oceanography data and supermarket data sets are applied to demonstrate that OOHI model is data independent. Various test cases are designed to cover the scope of each dimension and volume of data set. Comparative results and performance analytics portray that OOHI outperforms in data storage, dice, slice, and roll-up operations compared with Hadoop based OLAP.

Deep Reinforcement Learning Based Personalized Health Recommendations

Book Chapter

Book NameDeep Learning Techniques for Biomedical and Health Informatics

PublisherSpringer

Author NameJigna Patel

Page Number231-255

Chapter TitleDeep Reinforcement Learning Based Personalized Health Recommendations

Published YearNovember 2019

ISSN/ISBN No978-3-030-33965-4

Indexed INScopus

Abstract

In this age of informatics, it has become paramount to provide personalized recommendations in order to mitigate the effects of information overload. This domain of biomedical and health care informatics is still untapped as far as personalized recommendations are concerned. Most of the existing recommender systems have, to some extent, not been able to address sparsity of data and non-linearity of user-item relationships among other issues. Deep reinforcement learning systems can revolutionize the recommendation architectures because of its ability to use non-linear transformations, representation learning, sequence modelling and flexibility for implementation of these architectures. In this paper, we present a deep reinforcement learning based approach for complete health care recommendations including medicines to take, doctors to consult, nutrition to acquire and activities to perform that consists of exercises and preferable sports. We try to exploit an “Actor-Critic” model for enhancing the ability of the model to continuously update information seeking strategies based on user’s real-time feedback. Health industry usually deals with long-term issues. Traditional recommender systems fail to consider the long-term effects, hence failing to capture dynamic sentiments of people. This approach treats the process of recommendation as a sequential decision process, which addresses the aforementioned issues. It is estimated that over 700 million people will possess wearable devices that will monitor every step they take. Data collected with these smart devices, combined with other sources like, Electronic Health Records, Nutrition Data and data collected from surveys can be processed using Big Data Analysis tools, and fed to recommendation systems to generate desirable recommendations. These data, after encoding (state) into appropriate format, will be fed to the Actor network, which will learn a policy for prioritizing a particular recommendation (action). The action, state pair is fed to the critic network, which generates a reward associated with the action, state pair. This reward is used to update the policy of the Actor network. The critic network learns using a pre-defined Expected Reward. Hence, we find that using tools for Big Data Analytics, and intelligent approaches like Deep Reinforcement Learning can significantly improve recommendation results for health care, aiding in creating seamlessly personalized systems.

Efficient computing of OLAP in Big data warehouse

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperEfficient computing of OLAP in Big data warehouse

PublisherIJARCS

Volume Number9

Page Number201-205

Published YearJanuary 2018

ISSN/ISBN No0976-5697

Indexed INIndian citation Index, UGC List

Big Data Harmonization –Challenges and Applications

Journal

Journal NameInternational Journal on Recent and Innovation Trends in Computing and Communication

Title of PaperBig Data Harmonization –Challenges and Applications

Publisheri

Volume Number5

Page Number206-208

Published YearJune 2017

ISSN/ISBN No2321-8169

Indexed INIndian citation Index, UGC List, Others

Abstract

As data grow, need for big data solution gets increased day by day. Concept of data harmonization exist since two decades. Asdata is to be collected from various heterogeneous sources and techniques of data harmonization allow them to be in a single format at same place it is also called data warehouse. Lot of advancement occurred to analyses historical data by using data warehousing. Innovations uncover the challenges and problems faced by data warehousing every now and then. When the volume and variety of data gets increased exponentially, existing tools might not support the OLAP operations by traditional warehouse approach. In this paper we tried to focus on the research being done in the field of big data warehouse category wise. Research issues and proposed approaches on various kind of dataset is shown. Challenges and advantages of using data warehouse before data mining task are also explained in detail.

Women carrer in IT sector

Conference

Title of PaperWomen carrer in IT sector

Proceeding NameIndian Journal of Technical Education

PublisherGTU

Author NameJigna Patel

OrganizationBVM Engineering College,V.V.Nagar

Year , VenueJanuary 2016 , India

Page Number4

ISSN/ISBN NoISSN:0971-3034

Indexed INOthers

Big data for better health planning

Conference

Title of PaperBig data for better health planning

Proceeding NameIEEE International Conference on Advances in Engineering & Technology Research (ICAETR -2014)

PublisherIEEE Xplore

Author NameJigna Patel

Year , VenueAugust 2014 , Dr. Virendra Swarup Group ofinstitutions, Unnao, India

Page Number4

Indexed INScopus

Abstract

he exponential evolution of data in health care has brought a lot of challenges in tenns of data transfer, storage, computation and analysis. For healthcare usage and applications, ample patient infonnation and historical data, which enclose rich and significant insights that can be exposed using advanced tools and techniques as well as latest machine learning algorithms. Though, the size and rapidity of such great dimensional data requires new big data analytics framework. This paper introduces the thought of data in healthcare and the results of various surveys to show the impact of big data. Few case studies of big data analytics in healthcare is presented. Last section is about the tools and techniques comprising Hadoop, Stonn, Spark and HPCC -big data solution offered to solve big data issues and challenges

Traffic control using fuzzy logic

Journal

Journal NameInternational Journal of Electronics, Communication & InstrumentationEngineering Research and Development

Title of PaperTraffic control using fuzzy logic

PublisherTJPRC

Volume NumberVolume4-4

Page NumberPage no: 27-35

Published YearAugust 2014

ISSN/ISBN No2249-7951

Indexed INOthers

Abstract

Fuzzy Logic is based on distinguish between Binary variable which is present in Classical sets which are restricted. Fuzzy Logic helps us to build linguistic variable which enables us to create minute differences in any application. This paper covers the basics of Fuzzy logic. The entire concept of fuzzy logic is presented in well-defined manner. When to use and how to use fuzzy logic is explained. There are many application in which fuzzy logic is used and I have implemented one of them. I have demonstrated a C++ code with algorithm to detect the traffic flow on roads and I have discussits results. Future scope with the extension of existing code would be helpful

ConCollA - A Smart Emotion-based Music Recommendation System for Drivers

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperConCollA - A Smart Emotion-based Music Recommendation System for Drivers

Publisheruniversitatea de vest

Volume Number24

Page Number919–939

Published YearNovember 2023

ISSN/ISBN No18951767

Indexed INScopus, Web of Science

Abstract

Music recommender system is an area of information retrieval system that suggests customized music recommendations to users based on their previous preferences and experiences with music. While existing systems often overlook the emotional state of the driver, we propose a hybrid music recommendation system - ConCollA to provide a personalized experience based on user emotions. By incorporating facial expression recognition, ConCollA accurately identifies the driver’s emotions using convolution neural network(CNN) model and suggests music tailored to their emotional state. ConCollA combines collaborative filtering, a novel content-based recommendation system named Mood Adjusted Average Similarity (MAAS), and apriori algorithm to generate personalized music recommendations. The performance of ConCollA is assessed using various evaluation parameters. The results show that proposed emotion-aware model outperforms a collaborative-based recommender system.

The role of sentiment analysis in a recommender system: a systematic survey

Journal

Journal NameInternational Journal of Web Engineering and Technology

Title of PaperThe role of sentiment analysis in a recommender system: a systematic survey

PublisherInderscience

Volume Number17

Page Number29-62

Published YearAugust 2022

ISSN/ISBN No1741-9212

Indexed INScopus

Abstract

Currently, fields like e-commerce, education, social media, tourism, and the entertainment industry rely on recommender systems to provide personalised services to their clients. The most common and widely accepted technique - collaborative filtering, creates recommendations by examining the users' past rating patterns. Collaborative filtering assumes that a users' past rating data accurately reflects their actual preferences. However, different study found that the ratings may not accurately reflect user preferences in the real-world circumstances. Therefore, to deal with this problem, sentiment analysis of user-generated text is started to be used. It helps to improve the performance of recommender systems, as it provides more specific and trustworthy user preferences than ratings. A sentiment-aware recommender system captures sentiment from the user-generated content and provides most suited personalised services to the user. We have classified sentiment enhanced recommender systems according to the level of sentiment analysis and presented technical aspects such as datasets, methodologies and results.

Big Data Analytics for Advanced Viticulture

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperBig Data Analytics for Advanced Viticulture

Publisheruniversitatea de vest

Volume Number22

Page Number302–312

Published YearNovember 2021

ISSN/ISBN No18951767

Indexed INScopus, Web of Science

Abstract

Big data analytics involve a systematic approach to find hidden patterns to help the organization grow from large volume and variety of data. In recent years big data analytics is widely used in the agricultural domain to improve yield. Viticulture (the cultivation of grapes) is one of the most lucrative farming in India. It is a subdivision of horticulture and is the study of wine growing. The demand for Indian Wine is increasing at about 27% each year since the 21st century and thus more and more ways are being developed to improve the quality and quantity of the wine products. In this paper, we focus on a specific agricultural practice as viticulture. Weather forecasting and disease detection are the two main research areas in precision viticulture. Leaf disease detection as a part of plant pathology is the key research area in this paper. It can be applied on vineyards of India where farmers are bereft of the latest technologies. Proposed system architecture comprises four modules: Data collection, data preprocessing, classification and visualization. Database module involves grape leaf dataset, consists of healthy images combined with disease leaves such as Black measles, Black rot, and Leaf blight. Models have been implemented on Apache Hadoop using map reduce programming framework. It applies feature extraction to extract various features of the live images and classification algorithm with reduced computational complexity. Gray Level Co-occurrence Matrix (GLCM) followed by K-Nearest Neighborhood (KNN) algorithm. The system also recommends the necessary steps and remedies that the viticulturists can take to assure that the grapes can be salvaged at the right time and in the right manner based on classification results. The overall system will help Indian viticulturists to improve the harvesting process. Accuracy of the model is 82%, and it can be increased as a future work by including deep learning with time-series grape leaf images.

A fusion of aspect and contextual information for rating prediction in recommender system using a latent factor model

Journal

Journal NameInternational Journal of Web Engineering and Technology

Title of PaperA fusion of aspect and contextual information for rating prediction in recommender system using a latent factor model

PublisherInderscience

Volume Number16

Page Number30-52

Published YearJune 2021

ISSN/ISBN No1741-9212

Indexed INScopus

Abstract

Referring to reviews, checking online comments and, visiting different websites before buying any product is a call of the day. Online reviews are an excellent source of information both for users and organisations alike. In this article, a hybrid model, named as aspect and context-based latent factor model (ACMF), is proposed to predict user rating on an item based on star ratings provided by users, feature-opinion information, and context information. ACMF mainly consists of three phases: the first phase extracts spam reviews, the second phase extracts features and opinions from written reviews and calculates the polarity score of opinions. In the last phase, reviews and context information are aggregated to predict the unknown rating of a user for better recommendations. The proposed model is tested on ratings and reviews downloaded from the Amazon website. Experiment results show RMSE of ACMF has been achieved significantly less than other relevant methods.

CNN based Variation and Prediction Analysis of 2m Air Temperature for Different Zones of the Indian Region

Conference

Title of PaperCNN based Variation and Prediction Analysis of 2m Air Temperature for Different Zones of the Indian Region

Proceeding NameInternational Conference on Computing Methodologies and Communication (ICCMC)

PublisherIEEE

Author NameJitali Patel

OrganizationSurya Engineering College, Erode, Tamil Nadu ,India

Year , VenueApril 2021 , Surya Engineering College, Erode, Tamil Nadu ,India

Page Number1798–1804

ISSN/ISBN No978-1-6654-0360-3

Indexed INScopus

Abstract

Time series forecasting is a method that predicts future values by analyzing past values. Temperature alarms are valuable predictions because they are used to safeguard life and property and to increase operational performance. Here 2m air temperature refers to the temperature of air recorded at 2 meters from the ground. Paper consists of time-series prediction of temperature data that has been taken from automatic weather stations(AWS) installed by the Indian Space Research Organisation. Given paper presents the applicability of different machine learning(ML) algorithms like convolutional neural network(CNN), long short term memory(LSTM), and autoregressive integrated moving average(ARIMA) algorithms for the validity of temperature prediction over four different stations which are Ahmedabad, Balasore, Coimbatore, and Udaipur. These stations record the hourly-based temperatures. Based on different datasets, the prediction accuracy of algorithms is compared. The paper discusses the results showing that by applying different algorithms to the different datasets with different characteristics, it is observed that the various algorithms behave distinctly with numerous 1-dimensional datasets based on the variation in recorded values, location, or type of the input data i.e hourly input data or daily input data. This analysis shows that different machine learning algorithms have a different performance ratio while applied to various data sets.

Deep reinforcement learning based personalized health recommendations

Book Chapter

Book NameDeep Learning Techniques for Biomedical and Health Informatics

PublisherSpringer

Author NameJitali Patel

Page Number231-255

Chapter TitleDeep reinforcement learning based personalized health recommendations

Published YearNovember 2019

ISSN/ISBN No2197-6503

Indexed INScopus, Web of Science

Abstract

In this age of informatics, it has become paramount to provide personalized recommendations in order to mitigate the effects of information overload. This domain of biomedical and health care informatics is still untapped as far as personalized recommendations are concerned. Most of the existing recommender systems have, to some extent, not been able to address sparsity of data and non-linearity of user-item relationships among other issues. Deep reinforcement learning systems can revolutionize the recommendation architectures because of its ability to use non-linear transformations, representation learning, sequence modelling and flexibility for implementation of these architectures. In this paper, we present a deep reinforcement learning based approach for complete health care recommendations including medicines to take, doctors to consult, nutrition to acquire and activities to perform that consists of exercises and preferable sports. We try to exploit an “Actor-Critic” model for enhancing the ability of the model to continuously update information seeking strategies based on user’s real-time feedback. Health industry usually deals with long-term issues. Traditional recommender systems fail to consider the long-term effects, hence failing to capture dynamic sentiments of people. This approach treats the process of recommendation as a sequential decision process, which addresses the aforementioned issues. It is estimated that over 700 million people will possess wearable devices that will monitor every step they take. Data collected with these smart devices, combined with other sources like, Electronic Health Records, Nutrition Data and data collected from surveys can be processed using Big Data Analysis tools, and fed to recommendation systems to generate desirable recommendations. These data, after encoding (state) into appropriate format, will be fed to the Actor network, which will learn a policy for prioritizing a particular recommendation (action). The action, state pair is fed to the critic network, which generates a reward associated with the action, state pair. This reward is used to update the policy of the Actor network. The critic network learns using a pre-defined Expected Reward. Hence, we find that using tools for Big Data Analytics, and intelligent approaches like Deep Reinforcement Learning can significantly improve recommendation results for health care, aiding in creating seamlessly personalized systems.

A Survey on Security Issues in MANETs

Conference

Title of PaperA Survey on Security Issues in MANETs

Proceeding NameInternational Conference on Recent Innovations in Applied Science, Engineering and Technologies

OrganizationInstitution of Engineers, India

Year , VenueJune 2018 , IEI, Mumbai

Page Number146-155

ISSN/ISBN No987-93-87793-30-2

Review on Different types of Spam Filtering Techniques

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperReview on Different types of Spam Filtering Techniques

Volume Number8

Page Number2720-2723

Published YearJune 2017

ISSN/ISBN No0976-5697

Indexed INOthers

Computational Analysis of different Vertex Cover alorithms of various graphs

Conference

Title of PaperComputational Analysis of different Vertex Cover alorithms of various graphs

Proceeding NameInternational Conference on Intelligent Computing and Control Systems

PublisherIEEE

OrganizationVaigai College of Engineering

Year , VenueJune 2017 , Madurai India.

Page Number730-734

A Review on Different types of Spam Filtering Techniques

Journal

Journal NameIJARCS

Title of PaperA Review on Different types of Spam Filtering Techniques

Volume Number8

Published YearJanuary 2017

ISSN/ISBN No0976-5697

Indexed INUGC List

Twitter Followee Recommender System

Conference

Title of PaperTwitter Followee Recommender System

PublisherInternational conference on recent trends in engineering science and management

Year , VenueApril 2016 , Vendant college of Engineering and Technology,Bundi,Rajasthan

Page Number524-534

ISSN/ISBN No978-81-932074-4-4

Deep Learning Algorithms

Journal

Journal Name International Journal of Computer Science & Communication

Title of PaperDeep Learning Algorithms

Volume Number7

Page Number258-263

Published YearMarch 2016

ISSN/ISBN No0973-7391

Indexed INOthers

Assembling a Web Crawler

Conference

Title of PaperAssembling a Web Crawler

Proceeding NameInternational Conference on Recent Innovations in Science, Engineering and Management

Year , VenueMay 2015 , New Delhi

Page Number710-794

ISSN/ISBN No978-81-931039-4-4

Unleashing the power of SDN and GNN for network anomaly detection: State‐of‐the‐art, challenges, and future directions

Journal

Journal NameSecurity and Privacy

Title of PaperUnleashing the power of SDN and GNN for network anomaly detection: State‐of‐the‐art, challenges, and future directions

PublisherWiley

Volume Number7

Page Number1-16

Published YearJanuary 2024

ISSN/ISBN No2475-6725

Indexed INWeb of Science

Abstract

Modern computer networks' increasing complexity and scale need serious attention towards network anomaly detection. Software-defined networking (SDN) and graph neural networks (GNN) have emerged as promising approaches for anomaly detection due to their ability to capture dynamic network behavior and learn complex patterns from large-scale network data. The amalgamation of SDN and GNN for network anomaly detection presents promising opportunities for improving the accuracy and efficiency of network anomaly detection. This paper focuses on various trends, issues, and challenges by integrating GNN on the top of SDN for network anomaly detection. The article highlights the advantages of using SDN for providing fine-grained control and programmability in network monitoring. At the same time, GNN can model network behavior as a graph and learn representations from graph-structured data. The authors also discuss the limitations of traditional anomaly detection methods in SDN, such as rule-based approaches, and the potential of GNN to overcome these limitations by leveraging their ability to capture non-linear and dynamic patterns in network data. This paper also presents a case study of DoS attack detection using SDN. The result shows that SDN based approach helps to detect attacks with an accuracy of 97% with future research directions.

A comprehensive review of internet of things and cutting-edge technologies empowering smart farming.

Journal

Journal NameCurrent Science

Title of PaperA comprehensive review of internet of things and cutting-edge technologies empowering smart farming.

PublisherCurrent Science

Volume Number126

Page Number1-15

Published YearJanuary 2024

ISSN/ISBN No0011-3891

Indexed INScopus, Web of Science

Abstract

The agricultural sector plays an important role in contributing significantly to the gross domestic product (GDP) growth in developing countries. On the other hand, agriculture is widely affected by major factors such as environmental changes, natural disasters, pesticide control, and soil and irrigation-related issues, which reduce crop yield. The convergence of Industry 4.0 and agriculture offers an opportunity to move into the next generation of Agriculture 4.0. The internet of things (IoT), remote sensing, machine learning, deep learning, big data, cloud computing, thermal imaging, end-user apps and unmanned aerial vehicles offer a full-stack solution. IoT provides the ubiquitous connectivity of smart devices to the internet to collect, process and analyse a large amount of agriculture field data more quickly and synthesize them to make smart decisions using various machine learning and deep learning algorithms. This study reviews the challenges and major issues in the IoT agriculture domain and explores its emergence with new technologies. It covers the existing literature and illustrates how IoT application based precision agriculture solutions have contributed. A case study on weed detection for smart agriculture using the YOLOv5 model is presented, achieving high accuracy. Finally, various IoT agriculture use cases are discussed, along with current research issues and possible solutions for future IoT-based agriculture advancement.

Modeling topics in DFA-based lemmatized Gujarati text

Journal

Journal NameMDPI Sensors

Title of PaperModeling topics in DFA-based lemmatized Gujarati text

PublisherMDPI

Volume Number23

Page Number1-17

Published YearMarch 2023

ISSN/ISBN No1424-8220

Indexed INScopus, PubMed, Web of Science

Abstract

Topic modeling is a machine learning algorithm based on statistics that follows unsupervised machine learning techniques for mapping a high-dimensional corpus to a low-dimensional topical subspace, but it could be better. A topic model’s topic is expected to be interpretable as a concept, i.e., correspond to human understanding of a topic occurring in texts. While discovering corpus themes, inference constantly uses vocabulary that impacts topic quality due to its size. Inflectional forms are in the corpus. Since words frequently appear in the same sentence and are likely to have a latent topic, practically all topic models rely on co-occurrence signals between various terms in the corpus. The topics get weaker because of the abundance of distinct tokens in languages with extensive inflectional morphology. Lemmatization is often used to preempt this problem. Gujarati is one of the morphologically rich languages, as a word may have several inflectional forms. This paper proposes a deterministic finite automaton (DFA) based lemmatization technique for the Gujarati language to transform lemmas into their root words. The set of topics is then inferred from this lemmatized corpus of Gujarati text. We employ statistical divergence measurements to identify semantically less coherent (overly general) topics. The result shows that the lemmatized Gujarati corpus learns more interpretable and meaningful subjects than unlemmatized text. Finally, results show that lemmatization curtails the size of vocabulary decreases by 16% and the semantic coherence for all three measurements—Log Conditional Probability, Pointwise Mutual Information, and Normalized Pointwise Mutual Information—from −9.39 to −7.49, −6.79 to −5.18, and −0.23 to −0.17, respectively.

An Overview of Fog Data Analytics for IoT Applications”

Journal

Journal NameMDPI Sensors

Title of PaperAn Overview of Fog Data Analytics for IoT Applications”

PublisherMDPI

Volume Number23

Published YearFebruary 2023

ISSN/ISBN No1424-8220

Indexed INScopus, Web of Science

Abstract

With the rapid growth in the data and processing over the cloud, it has become easier to access those data. On the other hand, it poses many technical and security challenges to the users of those provisions. Fog computing makes these technical issues manageable to some extent. Fog computing is one of the promising solutions for handling the big data produced by the IoT, which are often security-critical and time-sensitive. Massive IoT data analytics by a fog computing structure is emerging and requires extensive research for more proficient knowledge and smart decisions. Though an advancement in big data analytics is taking place, it does not consider fog data analytics. However, there are many challenges, including heterogeneity, security, accessibility, resource sharing, network communication overhead, the real-time data processing of complex data, etc. This paper explores various research challenges and their solution using the next-generation fog data analytics and IoT networks. We also performed an experimental analysis based on fog computing and cloud architecture. The result shows that fog computing outperforms the cloud in terms of network utilization and latency. Finally, the paper is concluded with future trends.

Deep Learning Based Single-Image Super-Resolution: A Comprehensive Review

Journal

Journal NameIEEE Acess

Title of PaperDeep Learning Based Single-Image Super-Resolution: A Comprehensive Review

PublisherIEEE

Volume Number11

Page Number21811-21830

Published YearFebruary 2023

ISSN/ISBN No21693536

Indexed INScopus, Web of Science

Abstract

High-fidelity information, such as 4K quality videos and photographs, is increasing as high-speed internet access becomes more widespread and less expensive. Even though camera sensors’ performance is constantly improving, artificially enhanced photos and videos created by intelligent image processing algorithms have significantly improved image fidelity in recent years. Single image super-resolution is a class of algorithms that produces a high-resolution image from a given low-resolution image. Since the advent of deep learning a decade ago, this field has made significant strides. This paper presents a comprehensive review of the deep learning assisted single image super-resolution domain including generative adversarial network (GAN) models that discusses the prominent architectures, models used, and their merits and demerits. The reason behind covering the GAN models is that it is been known to perform better than the conventional deep learning methods given the resources and the time. For real-world applications with noise and other issues that can cause low-fidelity super resolution (SR) images, we examine another solution based on GAN model. This GAN model-based technique popularly known as blind super resolution is more resilient. We examined the various super-resolution techniques by varying image scaling factors (i.e., 2x, 3x, 4x) to measure PSNR and SSIM metrics for the different datasets. PSNR across the different datasets covered in the experimental Section shows an average of 14–17 % decrease in the score as we move up the image resolution scale from 2x to 4x. This is observed across all the datasets and for every model mentioned in the experimental Section of the paper. The results also show that blind super-resolution outperforms the conventional deep learning methods and the more complex GAN models. GAN models are complex and preferred when the upscale factor is high, while residual and dense models are recommended for smaller upscaling factors. This paper also discusses the applications of image super-resolution, and finally, the paper is concluded with challenges and future directions.

Software‐defined networks‐enabled fog computing for IoT‐based healthcare: Security, challenges and opportunities

Journal

Journal NameSecurity and Privacy

Title of PaperSoftware‐defined networks‐enabled fog computing for IoT‐based healthcare: Security, challenges and opportunities

PublisherWiley

Volume Number6

Page Number1-15

Published YearDecember 2022

ISSN/ISBN No2475-6725

Indexed INWeb of Science

Abstract

The Internet of Things (IoT) is a crucial technology in the healthcare industry thanks to recent developments in automated data collection. Current statistics of the healthcare sector show that it is expanding at a remarkable rate. However, the performance of the healthcare system is impacted by many challenges, such as security, privacy, latency, scalability, and heterogeneity that come with advancement. Fog computing and software-defined networks (SDN) are critical enabling technologies that help to improve IoT-based healthcare systems by ensuring timely and reliable data provisioning for use in healthcare applications. SDN solves interoperability, device management, and network management issues and automates patient health monitoring without human interaction. SDN and fog computing in IoT-based healthcare can optimize device communication and computing power at a low cost. SDN-enabled fog computing has lower latency and better security than cloud-based IoT healthcare architecture. The researchers have not entirely discovered SDN-enabled fog computing to the best of our knowledge. This paper covers healthcare IoT technicalities and related technologies. We examined ways to merge SDN, fog computing, and IoT to improve healthcare solutions. Finally, we concluded the paper with research issues and future healthcare system improvements.

Advancements in automated testing tools for Android set-top boxes: a comprehensive evaluation and integration approach

Journal

Journal NameInternational Journal of System Assurance Engineering and Management

Title of PaperAdvancements in automated testing tools for Android set-top boxes: a comprehensive evaluation and integration approach

PublisherSpringer India

Page Number1-10

Published YearApril 2024

ISSN/ISBN No0975-6809

Indexed INScopus, Web of Science

Software Effort Estimation using Machine Learning Algorithms

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperSoftware Effort Estimation using Machine Learning Algorithms

Volume Number25(2)

Page Number1276-1285

Published YearFebruary 2024

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science

Abstract

Effort estimation is a crucial aspect of software development, as it helps project managers plan, control, and schedule the development of software systems. This research study compares various machine learning techniques for estimating effort in software development, focusing on the most widely used and recent methods. The paper begins by highlighting the significance of effort estimation and its associated difficulties. It then presents a comprehensive overview of the different categories of effort estimation techniques, including algorithmic, model-based, and expert-based methods. The study concludes by comparing methods for a given software development project. Random Forest Regression algorithm performs well on the given dataset tested along with various Regression algorithms, including Support Vector, Linear, and Decision Tree Regression. Additionally, the research identifies areas for future investigation in software effort estimation, including the requirement for more accurate and reliable methods and the need to address the inherent complexity and uncertainty in software development projects. This paper provides a comprehensive examination of the current state-of-the-art in software effort estimation, serving as a resource for researchers in the field of software engineering.

Detection of traffic rule violation in University campus using deep learning model

Journal

Journal NameInternational Journal of System Assurance Engineering and Management

Title of PaperDetection of traffic rule violation in University campus using deep learning model

PublisherSpringer

Volume Number14(6)

Page Number2527-2545

Published YearDecember 2023

ISSN/ISBN No0976-4348

Indexed INScopus, Web of Science

Software Requirement Classification Using Machine Learning Algorithms

Conference

Title of PaperSoftware Requirement Classification Using Machine Learning Algorithms

Proceeding Name2023 International Conference on Artificial Intelligence and Applications (ICAIA) Alliance Technology Conference (ATCON-1)

PublisherIEEE

Author NameVrutik Patel, Priya Mehta, Kruti Laving

OrganizationAlliance Technology Conference (ATCON-1)

Year , VenueApril 2023 , Bangalore, India

ISSN/ISBN No978-1-6654-5627-2

Indexed INScopus

Stock Trend Prediction: A Comparative Study using Different Approaches

Conference

Title of PaperStock Trend Prediction: A Comparative Study using Different Approaches

Proceeding NameProceedings of the 5th International Conference on Smart Systems and Inventive Technology (ICSSIT 2023)

PublisherIEEE

Author NamePimal Khanpara, Rohan Kadam, Kruti Lavingia, Sanjay Patel

Page Number1697-1701

Published YearMarch 2023

ISSN/ISBN No978-1-6654-7467-2

Indexed INScopus

Abstract

With proper knowledge of any company’s stock and insight, one can gain large profits sitting at home. The stock market of a company is a time-series data and stock price prediction is one of the fields where many researchers have gathered interest to predict the stock prices or trends of the future using historical data and technical indicators with high accuracy. A Simple Moving Average is very useful in predicting the future price direction and gives a good assumption about the future price. A good prediction model of a stock’s future price will increase the trader’s profits. This research proposed a novel model by utilizing the deep learning model, LS TM (Long Short-Term Memory) to predict the stock trend with two different approaches-with and without using a sliding window. The results are then compared and analyzed.

A context-aware internet of things-driven security scheme for smart homes

Journal

Journal NameSecurity and Privacy

Title of PaperA context-aware internet of things-driven security scheme for smart homes

PublisherWiley

Volume Number6(1)

Page Number1-23

Published YearJanuary 2023

ISSN/ISBN No2475-6725

Indexed INWeb of Science

Abstract

In recent years, the Internet of Things (IoT) has become very popular as it has numerous applications in the industrial and research domain. Moreover, the features of IoT systems play a crucial role in the development of smart cities. It enables smart cities and their subsystems tomonitor, control, and manage heterogeneous devices remotely by extracting and communicating real-time data. However, automated IoT systems are vulnerable to many security threats like tempered protocols, device hijacking, and unauthorized access. Motivated by the aforementioned discussion, this paper addresses the security requirements of an essential subsystem of smart city architecture, that is, IoT-based smart homes. Based on the features and functionalities of smart homes, the risk of security violations in the system behavior needs to be analyzed This paper explores various security threats in a smart home environment and proposes a context-aware security-based scheme to prevent and detect possible threats. Results show that the proposed scheme is superior compared to the traditional schemes considering parameters such as the performance, cost, and maintenance requirements.

Machine Learning Based Approach for Traffic Rule Violation Detection

Conference

Title of PaperMachine Learning Based Approach for Traffic Rule Violation Detection

Proceeding Name2022 IEEE 7th International Conference on Recent Advances and Innovations in Engineering (ICRAIE)

PublisherIEEE

Author NameKruti Lavingia, Mihirsinh Vaja, Pooja Chaturvedi, Ami Lavingia

Page Number244-249

Published YearDecember 2022

ISSN/ISBN No978-1-6654-8910-2

Indexed INScopus

Abstract

The goal of this paper is to design an automated system model to monitor the violation of traffic rules, specifically the number of people sitting on a two-wheeler. Typically, in areas near the security offices, people tend to follow the rules, but in areas where no one is watching, people violate the rules. In our case of an organizational campus, if there are three people traveling on a two-wheeler but when they encounter a security guard, one of the persons gets down and walks ahead of the guarded area and then again sits back on the vehicle. In such cases, efficient methods are required to monitor the violation of specified traffic rules without human intervention. For the above-mentioned challenge, a deep learning-based solution is provided where the process starts with object recognition using YOLOv3 (You Only Look Once) model, using which a person sitting on any particular vehicle is identified based on a minimum threshold distance. Also, for the distance calculation, a depth estimation algorithm which helps us in finding the 3-D distance between objects from a 2-D image is implemented. Moreover, the number plate of the vehicle violating the above-mentioned rule is identified for easy identification of the person violating the rule. The proposed approach is implemented on a real time video streaming dataset. The simulation results show the efficiency of the proposed approach in terms of accuracy, precision and recall as 91%, 86% and 94% respectively.

Blockchain for Secure Message Transmission in VANETs

Conference

Title of PaperBlockchain for Secure Message Transmission in VANETs

Proceeding NameInternational Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS)

PublisherIEEE

Author NameKruti Lavingia, Pimal Khanpara, Kishan Vaghela, Darshil Chauh

Page Number1-6

Published YearJune 2022

ISSN/ISBN No978-1-6654-6883-1

Indexed INScopus

Abstract

Number of vehicles on the road is increasing day by day and as a result, the problems caused by these vehicles are also increasing. Hence, to overcome these problems related to road safety, Vehicular Ad-hoc Network (VANET) is being used which plays a major role in solving these safety issues. VANET is a network created to transmit the data using road-side entities and vehicles. To make data transmission secure and storing data such that every user can have access to it in a secured way, the use of Blockchain is preferred. Blockchain is a distributed ledger technology that can fulfill this requirement. There are many cryptographic techniques available that can be used for carrying out data transmission in VANET. This paper discusses and analyses various VANET system ideas for which researchers have carried out implementation. Still, there are many research challenges for carrying out secure transmission in VANET. This paper also proposes an approach to store the vehicular data securely by using Blockchain technology.

Predicting Stock Market Trends using Random Forest: A Comparative Analysis

Conference

Title of PaperPredicting Stock Market Trends using Random Forest: A Comparative Analysis

Proceeding NameProceedings of the Seventh International Conference on Communication and Electronics Systems (ICCES 2022)

PublisherIEEE

Author NameKruti Lavingia, Pimal Khanpara, Rachana Mehta, Niket Kothari, Karan Parekh

Page Number1544-1550

Published YearJune 2022

ISSN/ISBN No978-1-6654-9634-6

Indexed INScopus

Graph Neural Network based Recommender System

Conference

Title of PaperGraph Neural Network based Recommender System

Proceeding NameProceedings of the Seventh International Conference on Communication and Electronics Systems (ICCES 2022)

PublisherIEEE

Author NameRachana Mehta, Kruti Lavingia, Pimal Khanpara, Vijay Dhulera

Page Number1377-1381

Published YearJune 2022

ISSN/ISBN No978-1-6654-9634-6

Indexed INScopus

Information Retrieval and Data Analytics in Internet of Things: Current Perspective, Applications and Challenges

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperInformation Retrieval and Data Analytics in Internet of Things: Current Perspective, Applications and Challenges

Volume Number23(1)

Page Number23-34

Published YearApril 2022

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science

Augmented Reality and Industry 4.0

Book Chapter

Book NameA Roadmap to Industry 4.0: Smart Production, Smart Business and Sustainable Development

PublisherSpringer, Cham

Author NameKruti Lavingia

Page Numberpp 143-155

Chapter TitleAugmented Reality and Industry 4.0

Published YearNovember 2019

ISSN/ISBN No978-3-030-14544-6

Indexed INScopus

Energy conservation in Multimedia big data computing and the Internet of Things—A challenge

Book Chapter

Book NameMultimedia Big Data Computing for IoT Applications

PublisherSpringer, Singapore

Author NameKruti Lavingia

Page Numberpp 37-57

Chapter TitleEnergy conservation in Multimedia big data computing and the Internet of Things—A challenge

Published YearJuly 2019

ISSN/ISBN No978-981-13-8759-3

Indexed INScopus

GDLC: A Software Engineering Approach in Game Development

Journal

Journal NameInternational Journal of Advance Research in Science and Engineering

Title of PaperGDLC: A Software Engineering Approach in Game Development

Volume Number6(6)

Page Number579-584

Published YearJune 2017

ISSN/ISBN No2319-8354

Indexed INUGC List

Software Engineering in freelancing

Journal

Journal NameInternational Journal of Research and Scientific Innovation

Title of PaperSoftware Engineering in freelancing

Volume Number4(5)

Page Number103-105

Published YearMay 2017

ISSN/ISBN No2321-2705

Indexed INUGC List

Survey Paper on Impact of Cloud Computing on Conventional Software Engineering

Journal

Journal NameInternationa Journal of Computer Science and Engineering

Title of PaperSurvey Paper on Impact of Cloud Computing on Conventional Software Engineering

Volume Number9(5)

Page Number149-152

Published YearMay 2017

ISSN/ISBN No0975-3397

Indexed INUGC List

Security Engineering

Conference

Title of PaperSecurity Engineering

Proceeding NameInternational Conference on Academic Research in Engineering and Management

OrganizationInstitution of Electronics and Telecommunication Engineers, Delhi

Year , VenueApril 2017 , Institution of Electronics and Telecomunication Engineers, Lodhi Road, Delhi

Page Number269 - 274

ISSN/ISBN NoISBN - 978-93-86171-43-6

Indexed INUGC List

Performance Evaluation of Transmission distance and Bit Rates in Inter-Satellite optical wireless communication system

Conference

Title of PaperPerformance Evaluation of Transmission distance and Bit Rates in Inter-Satellite optical wireless communication system

Proceeding Name3rd International Conference on Recent Innovations in Science Engineering and Management

OrganizationSri Venkateswara College of Engineering and Technology, Srikakulam,Andhra Pradesh

Year , VenueFebruary 2017 , Sri Venkateswara College of Engineering and Technology,Srikakulam, Andhrapradesh

Page Number36-40

ISSN/ISBN No978-81-932074-1-3

Indexed INUGC List

Performance evolution of optical link using dispersion compensation fiber and FBG

Conference

Title of PaperPerformance evolution of optical link using dispersion compensation fiber and FBG

Proceeding NameInternational Conference on Recent Trends in Engineering Science, Humanities and Management

OrganizationSri S Ramasamy Naidu Memorial College, Sattur, Tamilnadu

Year , VenueFebruary 2017 , Sri S Ramasamy Naidu Memorial College, Sattur, Tamilnadu

Page Number809-812

ISSN/ISBN NoISBN : 978-93-86171-18-4

Indexed INUGC List

A machine learning approach to improve the efficiency of fake website detection techniques

Journal

Journal NameInternational Journal of Computer Science and Communication

Title of PaperA machine learning approach to improve the efficiency of fake website detection techniques

Volume Number7

Page Number236-243

Published YearMarch 2016

ISSN/ISBN No0973-7391

Indexed INUGC List

A novel approach to improve the efficiency of fake website detection techniques: Survey

Conference

Title of PaperA novel approach to improve the efficiency of fake website detection techniques: Survey

Proceeding Name2nd International Conference on Recent Trends in Engineering Science and Management

OrganizationYMCA, New Delhi

Year , VenueFebruary 2016 , YMCA, New Delhi

Page Number71-78

ISSN/ISBN No978-81-932074-3-7

Indexed INUGC List

Blockchain and ML-Based Framework for Diabetes Assessment of Patients in Telesurgery System

Conference

Title of PaperBlockchain and ML-Based Framework for Diabetes Assessment of Patients in Telesurgery System

Proceeding Name2023 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON)

PublisherIEEE Xplore

Author NameYogi Patel, Denisha Tank, Rajesh Gupt, Riya Kakkar, Nilesh Kumar Jadav, Lata Gohil, Sudeep Tanwar

OrganizationGhousia College of Engineering

Year , VenueDecember 2023 , Ghousia College of Engineering, Ramanagaram Bengaluru

Page Number1-6

ISSN/ISBN No979-8-3503-1912-5

Indexed INScopus

EEG-based biometric authentication system using convolutional neural network for military applications

Journal

Journal NameSecurity and Privacy

Title of PaperEEG-based biometric authentication system using convolutional neural network for military applications

PublisherWiley Periodicals, Inc. Boston, USA

Volume Number7

Page Numbere345

Published YearOctober 2023

ISSN/ISBN No2475-6725

Indexed INWeb of Science

Abstract

In this technological era, as the need for security arises, the use of biometrics is increasing in authentication systems as a secure and convenient method of human identification and verification. Electroencephalogram (EEG) signals have gained significant attention among the various biometric modalities available because of their unique and unforgeable characteristics. In this study, we have proposed an EEG-based multi-subject and multi-task biometric authentication system for the military applications that address the challenges associated with multi-task variation in EEG signals. The proposed work considers the use of respective EEG signals for the access of artillery, entrance to highly confidential places for the military and so forth by authenticated personnel only. We have used a multi-subject, multi-session, and multi-task ( ) dataset. The dataset was partially preprocessed with basic signal processing techniques such as bad channel repairing, independent component analysis for artifact removal, downsampling to 250 Hz, and an audio filter of 0.01–200 Hz for signal improvisation. This partially preprocessed dataset was further processed and was used in our deep learning model (DL) architectures. For EEG-based biometric authentication, convolutional neural network (CNN) outperforms many of the state-of-the-art DL architectures with a validation accuracy of approximately 99.86%, training accuracy of 98.49% and precision, recall and F1-score with values of 99.91% that makes this EEG-based approach for authentication more reliable. The DL models were also compared based on training and inference time, where CNN used the most training time but took the least time to predict the output. We compared the performance of the CNN model for three preprocessing techniques by feeding mel spectrograms, chromagrams and mel frequency cepstral coefficients, out of which mel spectrograms provided better results. This proposed architecture proves to be robust and efficient for military applications.

MetaHate: AI-based hate speech detection for secured online gaming in metaverse using blockchain

Journal

Journal NameSecurity and Privacy

Title of PaperMetaHate: AI-based hate speech detection for secured online gaming in metaverse using blockchain

PublisherWiley Periodicals, Inc. Boston, USA

Volume Number7

Page Numbere343

Published YearSeptember 2023

ISSN/ISBN No2475-6725

Indexed INWeb of Science

Abstract

The emergence of Web 3.0, blockchain technology (BC), and artificial intelligence (AI) are transforming multiplayer online gaming in the metaverse. This development has its concerns about safety and inclusivity. Hate speech, in particular, poses a significant threat to the harmony of these online communities. Traditional moderation methods struggle to cope with the immense volume of user-generated content, necessitating innovative solutions. This article proposes a novel framework, MetaHate, that employs AI and BC to detect and combat hate speech in online gaming environments within the metaverse. Various machine learning (ML) models are applied to analyze Hindi–English code mixed datasets, with gradient boosting proving the most effective, achieving 86.01% accuracy. AI algorithms are instrumental in identifying harmful language patterns, while BC technology ensures transparency and user accountability. Moreover, a BC-based smart contract is proposed to support the moderation of hate speech in the game chat. Integrating AI and BC can significantly enhance the safety and inclusivity of the metaverse, underscoring the importance of these technologies in the ongoing battle against hate speech and in bolstering user engagement. This research emphasizes the potential of AI and BC synergy in creating a safer metaverse, highlighting the need for continuous refinement and deployment of these technologies.

CNN and Bidirectional GRU-Based Heartbeat Sound Classification Architecture for Elderly People

Journal

Journal NameMathematics

Title of PaperCNN and Bidirectional GRU-Based Heartbeat Sound Classification Architecture for Elderly People

Volume Number11

Published YearMarch 2023

ISSN/ISBN No2227-7390

Indexed INScopus, Web of Science

Abstract

ardiovascular diseases (CVDs) are a significant cause of death worldwide. CVDs can be prevented by diagnosing heartbeat sounds and other conventional techniques early to reduce the harmful effects caused by CVDs. However, it is still challenging to segment, extract features, and predict heartbeat sounds in elderly people. The inception of deep learning (DL) algorithms has helped detect various types of heartbeat sounds at an early stage. Motivated by this, we proposed an intelligent architecture categorizing heartbeat into normal and murmurs for elderly people. We have used a standard heartbeat dataset with heartbeat class labels, i.e., normal and murmur. Furthermore, it is augmented and preprocessed by normalization and standardization to significantly reduce computational power and time. The proposed convolutional neural network and bi-directional gated recurrent unit (CNN + BiGRU) attention-based architecture for the classification of heartbeat sound achieves an accuracy of 90% compared to the baseline approaches. Hence, the proposed novel CNN + BiGRU attention-based architecture is superior to other DL models for heartbeat sound classification.

Automatic Question Tagging using Machine Learning and Deep learning Algorithms

Conference

Title of PaperAutomatic Question Tagging using Machine Learning and Deep learning Algorithms

Proceeding Name2022 6th International Conference on Electronics, Communication and Aerospace Technology

PublisherIEEE Explore

Author NameM. Prajapati, M. Nakrani, T. Vyas, L. Gohil, S. Desai and S. Degadwala

OrganizationRVS Technical Campus, Coimbatore, Tamil Nadu, India

Year , VenueDecember 2022 , Coimbatore, India

Page Number932-938

ISSN/ISBN No978-1-6654-8272-1

Indexed INScopus

Abstract

Stack Overflow is a well-known website which is utilized by nearly everyone who learns to code, share their knowledge and publicly participate in this question-answering forum. The questions posted on the Stack Overflow forum by a user requires a minimum of 1 tag to be manually entered in by them. Tagging most commonly means to associate some single word information about the context of given text or question. Tagging a question is useful in identifying the category that a question or text belongs. It is also beneficial in providing ease of access to a person having a requirement of specific categories of questions. On analysis of tags associated with the questions on the website, it was found that a large number of the questions are labelled by more than one tags, with many of them not being tagged accurately. Due to this situation, it becomes challenging for the users to search for relevant tags. So, the main aim of this research task is to explore methods and compare different techniques in order to create an auto tagging system with the aid of Machine learning and deep learning facilities, accompanied by data preprocessing steps. The dataset for this purpose was taken from Kaggle, known as StackSample dataset, which is a dataset containing 10 percent of the questions present on the website. The output of the research performed for this purpose provided satisfactory results with scope of improvement.

Music Genre Classification using Deep Learning

Conference

Title of PaperMusic Genre Classification using Deep Learning

Proceeding Name2022 6th International Conference on Computing Methodologies and Communication (ICCMC)

PublisherIEEE Explore

Author NameMitt Shah, Nandit Pujara, Kaushil Mangaroliya, Lata Gohil, Tarjni Vyas, Sheshang Degadwala

OrganizationSurya Engineering College(SEC), Erode

Year , VenueMarch 2022 , Erode, India

Page Number974-978

ISSN/ISBN No978-1-6654-1029-8

Indexed INScopus

Affect Analysis of Multilingual Tweets for Predicting Voting Behavior

Journal

Journal NameInternational Journal of Innovative Technology and Exploring Engineering (IJITEE)

Title of PaperAffect Analysis of Multilingual Tweets for Predicting Voting Behavior

PublisherBlue Eyes Intelligence Engineering and Sciences Publication (BEIESP)

Volume Number9

Page Number1768-1771

Published YearDecember 2019

ISSN/ISBN No2278-3075

Indexed INOthers

Abstract

Social media has been proved as wild card for its role in election campaign across the globe. It has been used for general election of India in year 2014 and year 2019 by political parties for election campaign. Thus social media provides opportunity for electoral prediction. Users from India use regional languages in addition to English language on social media. Multilingual data likely to give better prediction compared to single language data. Affect analysis gives deeper insight compared to sentiment analysis. This research study aims to predict voting behavior for 2019 general election of India using affect analysis of multilingual tweets. Three languages namely English, Hindi and Gujarati are used for this study. Volume-based method and machine learning algorithm based method are two approaches widely used in literature for electoral prediction. In this research study hybrid approach is used along with consideration of ratio of positive count and negative count of tweets. Experiment result shows efficacy of the proposed approach.

Multilabel Classification for Emotion Analysis of Multilingual Tweets

Journal

Journal NameInternational Journal of Innovative Technology and Exploring Engineering

Title of PaperMultilabel Classification for Emotion Analysis of Multilingual Tweets

PublisherBlue Eyes Intelligence Engineering and Sciences Publication (BEIESP)

Volume Number9

Page Number4453-4457

Published YearNovember 2019

ISSN/ISBN No 2278-3075

Indexed INScopus

Abstract

Emotion Analysis of text targets to detect and recognize types of feelings expressed in text. Emotion analysis is successor of Sentiment analysis. The latter does coarse-level analysis and classify the text into positive and negative categories while former does fine-grain analysis and classify text in specific emotion categories like happy, surprise, angry. Analysis of text at fine-level provides deeper insight compared to coarse-level analysis. In this paper, tweets are classified in discrete eight basic emotions namely joy, trust, fear, surprise, sadness, anticipation, anger, disgust specified in Plutchik’s wheel of emotions [1]. Tweets for three languages collected out of which one is English language and rest two are Indian languages namely Gujarati and Hindi. The collected tweets are related to Indian politics and are annotated manually. Supervised Learning and Hybrid approach are used for classification of tweets. Supervised learning uses tf-idf as features while hybrid approach uses primary and secondary features. Primary features are generated using tf-idf weighting and two different algorithms of feature generation are proposed which generate secondary features using SenticNet resource. Multilabel classification is performed to classify tweets in emotion categories. Results of experiments show effectiveness of hybrid approach.

A sentiment analysis of Gujarati text using Gujarati senti word net

Journal

Journal NameInternational Journal of Innovative Technology and Exploring Engineering

Title of PaperA sentiment analysis of Gujarati text using Gujarati senti word net

PublisherBlue Eyes Intelligence Engineering and Sciences Publication (BEIESP)

Volume Number8

Page Number2290-2293

Published YearJuly 2019

ISSN/ISBN No2278-3075

Indexed INScopus

Abstract

Sentiment Analysis plays vital role in decision making. For English language intensive research work is done in this area. Very less work is reported in this domain for Indian languages compared to English language. Gujarati language is almost unexplored for this task. More data in form of movie reviews, product reviews, social media posts etc are available in regional languages as people like to use their native language on Internet which leads to need of mining these data in order to understand their opinion. Various tools and resources are developed for English language and few for Indian languages. Gujarati is resource poor language for this task. Motive of this paper is to develop sentiment lexical resource for Gujarati language which can be used for sentiment analysis of Gujarati text. Hindi SentiWordNet (H-SWN) [1] and synonym relations of words from IndoWordnet (IWN) [2] [3] are used for developing Gujarati SentiWordNet. Our contribution is twofold. (1) Gujarati SentiWordNet (G-SWN) is developed. (2) Gujarati corpus is prepared in order to evaluate lexical resource created. Evaluation result shows the usefulness of generated resource.

Affect Computation Models from Textual Aspect: A Brief Survey

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperAffect Computation Models from Textual Aspect: A Brief Survey

PublisherFoundation of Computer Science (FCS), NY, USA

Volume Number146

Page Number25-29

Published YearJuly 2016

ISSN/ISBN No0975-8887

Indexed INEBSCO

Abstract

Human emotions are outcome of the subjective evaluation of events that occur in the environment. There are various affect theories in psychology to understand human emotion. To make Human-Computer-Interaction (HCI) intelligent, affect theory are to be incorporated. In this paper, discussion of various affect theories and affect computation models have been presented.

Mobile App Monetization: Issues and Challenges

Journal

Journal NameInternational Journal of Engineering Technology, Management and Applied Sciences

Title of PaperMobile App Monetization: Issues and Challenges

PublisherAcademic Science

Volume Number3

Page Number13-15

Published YearMay 2015

ISSN/ISBN No2349-4476

Indexed INOthers

Abstract

In recent years, there has been tremendous advancement in the capabilities of mobile devices which in turn led increase in the development and use of mobile applications. Mobile device users are attracted towards feature-rich applications. The app developers are encouraged to develop applications to meet users need. The app developers can distribute and sell their applications in mobile application market. The rise of mobile application market opened up immense opportunities for mobile app developers to generate revenue by selling mobile applications to large number of consumers as well as to capture new customers. There exist various monetization models which developers opt for creation of economic value. Issues and challenges in this context are discussed in this paper.

Text Mining: Process and Techniques

Journal

Journal NameInternational Journal of Innovative Research in Computer Science & Technology (IJIRCST)

Title of PaperText Mining: Process and Techniques

PublisherInnovative Research Publication

Volume Number3

Page Number70-72

Published YearMay 2015

ISSN/ISBN No2347-5552

Indexed INIndian citation Index

Abstract

Massive amount of digital data is available in form of unstructured text. It is highly required to extract useful information from this textual data. The process to discover non-trivial information and knowledge which are previously unknown is knows as Text Mining. This paper discusses process and techniques with respect to Text Mining.

SLAMMP Framework for Cloud Resource Management and Its Impact on Healthcare Computational Techniques

Journal

Journal NameInternational Journal of E-Health and Medical Communications (IJEHMC)

Title of PaperSLAMMP Framework for Cloud Resource Management and Its Impact on Healthcare Computational Techniques

PublisherIGI Global

Published YearJuly 2021

Indexed INScopus, Web of Science, Others

SDN-Enabled Adaptive Broadcast Timer for Data Dissemination in Vehicular Ad Hoc Networks

Journal

Journal NameIEEE Transactions on Vehicular Technology

Title of PaperSDN-Enabled Adaptive Broadcast Timer for Data Dissemination in Vehicular Ad Hoc Networks

PublisherIEEE

Volume Number70

Page Number8134-8147

Published YearJune 2021

ISSN/ISBN No1939-9359

Indexed INScopus

Feature Combination of Pauli and H/A/Alpha Decomposition for Improved Oil Spill Detection Using SAR

Conference

Title of PaperFeature Combination of Pauli and H/A/Alpha Decomposition for Improved Oil Spill Detection Using SAR

Proceeding NameRecent Trends in Image Processing and Pattern Recognition: Third International Conference, RTIP2R

PublisherSpringer

Year , VenueFebruary 2021 , Singapore

Page Number134-147

ISSN/ISBN No978-981-16-0507-9

On Performance Enhancement of Molecular Dynamics Simulation Using HPC Systems

Conference

Title of PaperOn Performance Enhancement of Molecular Dynamics Simulation Using HPC Systems

Proceeding NameProceedings of Second International Conference on Computing, Communications, and Cyber-Security

PublisherSpringer

Year , VenueJanuary 2021 , Singapiore

Page Number1031-1044

ISSN/ISBN No978-981-16-0733-2

CS2M: Cloud Security and SLA Management

Journal

Journal NameAnnals of the Romanian Society for Cell Biology (2021)

Title of PaperCS2M: Cloud Security and SLA Management

PublisherAssociation of Cell Biology Romania

Volume Number25

Page Number4459 - 4465

Published YearJanuary 2021

ISSN/ISBN No1583-6258

Indexed INScopus

C2B-SCHMS: Cloud Computing and Bots Security for COVID-19 Data and Healthcare Management Systems

Conference

Title of PaperC2B-SCHMS: Cloud Computing and Bots Security for COVID-19 Data and Healthcare Management Systems

Proceeding NameProceedings of Second International Conference on Computing, Communications, and Cyber-Security.

PublisherSpringer

Year , VenueDecember 2020 , Singapore

ISSN/ISBN No978-3-030-67490-8

Advance Cloud Data Analytics for 5G Enabled IoT

Book Chapter

Book NameBlockchain for 5G-Enabled IoT: The New Wave for Industrial Automation

PublisherSpringer, Cham

Page Number159-180

Chapter TitleAdvance Cloud Data Analytics for 5G Enabled IoT

Published YearDecember 2020

Monitoring and Prediction of SLA for IoT based Cloud

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperMonitoring and Prediction of SLA for IoT based Cloud

PublisherSCPE

Volume Number21

Page Number349-358

Published YearAugust 2020

Indexed INScopus, Others

Monitoring IaaS Cloud for Healthcare Systems: Healthcare Information Management and Cloud Resources Utilization

Journal

Journal NameInternational Journal of E-Health and Medical Communications (IJEHMC)

Title of PaperMonitoring IaaS Cloud for Healthcare Systems: Healthcare Information Management and Cloud Resources Utilization

PublisherIGI Global

Volume Number11

Page Number54-70

Published YearJuly 2020

Indexed INScopus, Others

SDN-Enabled Network Coding-Based Secure Data Dissemination in VANET Environment

Journal

Journal NameIEEE Internet of Things Journal

Title of PaperSDN-Enabled Network Coding-Based Secure Data Dissemination in VANET Environment

PublisherIEEE

Page Number6078-6087

Published YearJuly 2020

ISSN/ISBN No2327-4662

Establishing Trust in the Cloud Using Machine Learning Methods

Conference

Title of PaperEstablishing Trust in the Cloud Using Machine Learning Methods

Proceeding NameIn Proceedings of First International Conference on Computing, Communications, and Cyber-Security

PublisherSpringer

Year , VenueApril 2020 , Singapore

Page Number791-805

ISSN/ISBN No978-981-15-3369-3

Performance consequence of user space file systems due to extensive CPU sharing in virtual environment

Journal

Journal NameCluster Computing

Title of PaperPerformance consequence of user space file systems due to extensive CPU sharing in virtual environment

PublisherSpringer

Page Number3119-3137

Published YearFebruary 2020

Indexed INScopus, PubMed

Preserving SLA Parameters for Trusted IaaS Cloud: An Intelligent Monitoring Approach

Journal

Journal NameRecent Patents on Engineering

Title of PaperPreserving SLA Parameters for Trusted IaaS Cloud: An Intelligent Monitoring Approach

PublisherBentham Science

Volume Number14

Page Number530-540

Published YearJanuary 2020

ISSN/ISBN No2212-4047

Indexed INScopus

Achieving Trust using RoT in IaaS Cloud

Journal

Journal NameProcedia Computer Science

Title of PaperAchieving Trust using RoT in IaaS Cloud

PublisherElsevier

Volume Number167

Page Number487-495

Published YearJanuary 2020

Indexed INScopus

Efficient Resource Provisioning Through Workload Prediction in the Cloud System

Conference

Title of PaperEfficient Resource Provisioning Through Workload Prediction in the Cloud System

Proceeding Name Smart Trends in Computing and Communications

PublisherSpringer

Year , VenueDecember 2019 , Singapore

Page Number317-325

ISSN/ISBN No978-981-15-0077-0

Adaptive cloud resource management through workload prediction

Journal

Journal NameEnergy Systems

Title of PaperAdaptive cloud resource management through workload prediction

PublisherSpringer

Published YearNovember 2019

Software Defined Vehicular Networks: A Comprehensive Review

Journal

Journal NameInternational Journal of Communications:Software Defined Vehicular Networks: A Comprehensive Review

Title of PaperSoftware Defined Vehicular Networks: A Comprehensive Review

PublisherWiley

Volume Numberearly access

Page Numberearly access

Published YearJanuary

ISSN/ISBN No1099-1131

Indexed INScopus, Web of Science, EBSCO, UGC List, Others

Abstract

The recent breakthroughs in the automobile industries and telecommunication technologies along with the exceptional multimodal mobility services brought focus on Intelligent Transportation System (ITS), of which Vehicular Adhoc Networks (VANETs) gain much more attention. The distinctive features of Software Defined Networking (SDN) leverages the vehicular networks by its state of the centralized art having a comprehensive view of the network. Its potential to bring the flexibility, programmability and other extensive advancements to vehicular networks has set the stage for a novel networking paradigm termed as Software-Defined Vehicular Networks (SDVNs). Many researchers have demonstrated the SDN based VANETs with the various configuration of the SDN components in VANET architecture. However, a compilation of the work on the SDN based VANET system as a whole incorporating its architecture, use-cases, and opportunities is still inadequate. We start with the summary of the recent studies exist on the SDVNs, followed by the comprehensive explanation of its components. Next, we present the taxonomy of SDVN based on the architecture modes, protocols, access technologies and opportunities with trending technologies. Finally, we highlights the challenges, open research issues, and future research directions.

Trust Management and Monitoring at an IaaS Level of Cloud Computing

Conference

Title of PaperTrust Management and Monitoring at an IaaS Level of Cloud Computing

Proceeding NameSRRN Elsevier

PublisherSRRN Elsevier

Year , VenueJanuary , MNIT, Jaipur

Page Number-

ISSN/ISBN No1556-5068

Indexed INUGC List

Abstract

Now a days Cloud Computing is as a major utility, same as electricity and water bills where we pay as we go with the consumption of the said resources, as organization usages cloud computing services and pays as per their usage of the resources. In this research paper, the authors aspect are towards at what trust is and how trust value can be maintained to create its trust level among the end users and the cloud service provider with the help of on demand monitoring mechanism and invoking the monitoring techniques only when the trust fluctuates to maintain its dignity towards the trust shown by the end use .In monitoring the present status of the resources are analyzed and based upon the same the new instances will be created to satisfy the need of the end users to maintain the trust level.

Influence of Monitoring : Fog and Edge Computing

Journal

Journal NameScalable Computing: Practice and Experience Publishing

Title of PaperInfluence of Monitoring : Fog and Edge Computing

PublisherSCPE

Volume Number20

Published YearMay 2019

Indexed INScopus, Others

Influence of Montoring: Fog and Edge Computing

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperInfluence of Montoring: Fog and Edge Computing

PublisherSCPE

Volume Number20

Page Number365–376

Published YearMay 2019

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science, UGC List

Abstract

The evolution of the Internet of Things (IoT) has augmented the necessity for Cloud, edge and fog platforms. The chief benefit of cloud-based schemes is they allow data to be collected from numerous services and sites, which is reachable from any place of the world. The organizations will be benefited by merging the cloud platform with the on-site fog networks and edge devices and as result, this will increase the utilization of the IoT devices and end users too. The network traffic will reduce as data will be distributed and this will also improve the operational efficiency. The impact of monitoring in edge and fog computing can play an important role to efficiently utilize the resources available at these layers. This paper discusses various techniques involved for monitoring for edge and fog computing and its advantages. The paper ends with a case study to demonstarte the need of monitoring in fog and edge in the healthcare system.

Classification of crop types using C band SAR Data

Conference

Title of PaperClassification of crop types using C band SAR Data

Proceeding NameInternational Conference on Knowledge Discovery in Science and Technology-2019(ICKDST-19)

PublisherJAC

Year , VenueFebruary 2019 , Pune, India

Exploratory Learning of Resource Management in Private Cloud Environment

Journal

Journal NameInternational Journal of Recent Technology and Engineering

Title of PaperExploratory Learning of Resource Management in Private Cloud Environment

Volume Number8

Published YearJanuary 2019

ISSN/ISBN No2277-3878

Indexed INScopus

Prediction Based Efficient Resource Provisioning and Its Impact on QoS Parameters in the Cloud Environment

Journal

Journal NameInternational Journal of Electrical and Computer Engineering (IJECE)

Title of PaperPrediction Based Efficient Resource Provisioning and Its Impact on QoS Parameters in the Cloud Environment

PublisherInstitute of Advanced Engineering and Science (IAES)

Volume Number8

Page Number5359-5370

Published YearDecember 2018

ISSN/ISBN No2088-8708

Indexed INScopus, Others

Infrastructure as a Code in Cloud Environment for Dynamic Auto Scaling

Journal

Journal NameInternational Journal of Computing and Applications

Title of PaperInfrastructure as a Code in Cloud Environment for Dynamic Auto Scaling

PublisherSerial Publications, New Delhi (India)

Volume Number16

Page Number159-164

Published YearJune 2018

ISSN/ISBN No0973-5704

Reducing the Operative Resource Monitoring Mechanism Overhead in Cloud: An IaaS Perspective

Conference

Title of PaperReducing the Operative Resource Monitoring Mechanism Overhead in Cloud: An IaaS Perspective

Proceeding NameProceedings of 3rd International Conference on Internet of Things and Connected Technologies (ICIoTCT)

PublisherElsevier

Year , VenueMay 2018 , Jaipur, India

Chronicles of Assaults at Cloud Computing and its Influence at an IaaS

Conference

Title of PaperChronicles of Assaults at Cloud Computing and its Influence at an IaaS

Proceeding NameProceedings of 3rd International Conference on Internet of Things and Connected Technologies (ICIoTCT)

PublisherElsevier

Year , VenueMay 2018 , Jaipur, India

Performance Analysis of Local, Network and Distributed File Systems Running Inside User’s Virtual Machines in Cloud Environment

Journal

Journal NameAdvanced in Modelling and Analysis

Title of PaperPerformance Analysis of Local, Network and Distributed File Systems Running Inside User’s Virtual Machines in Cloud Environment

PublisherInternational Information and Engineering Technology Association (IIETA)

Page Number48-55

Published YearMarch 2018

Inspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

Journal

Journal NameProcedia computer science Elsevier:Inspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

Title of PaperInspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

PublisherElsevier

Volume Number132

Page Number1280-1289

Published YearFebruary 2018

ISSN/ISBN No1877-0509

Indexed INScopus, UGC List

Abstract

Cloud Computing is an example of the distributed system where the end user has to connect to the services given by the cloud which is maintained by the cloud service provider (CSP). The user has to have certain trust upon the cloud as finally, the end user has to migrate the jobs into the cloud of some third party, as the on-premises data or sources are to be kept across the globe,the CSP have to maintain the trust level so that the end user can opt for the services given by the certain trusted Cloud.Ultimately there will be various elements of levels happening at the CSP side to maintain the trust level, like the safety features for security has to be identified ,federation related or Virtual Machine migration techniques status has to be always monitored to maintain and avoid certain uncertainty which will affect the trust level of the cloud, which can lead to the compromised situation in between the end user and CSP, as a result the trust value will decrease, In this paper we are proposing a techniques where the security features and conditions for load balancing monitoring technique with proactive actions will be analyzed to maintain the specified trust level .

Varients of Software Defined Netwroks (SDN) Based Load Balancing in Cloud Computing: A Quick Review

Conference

Title of PaperVarients of Software Defined Netwroks (SDN) Based Load Balancing in Cloud Computing: A Quick Review

Proceeding NameInternational Conference on Future Internet Technologies and Trends,ICFITT 2017

PublisherSpringer, Cham

Page Number164-173

Published YearJanuary 2018

ISSN/ISBN No978-3-319-73712-6

Efficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

Conference

Title of PaperEfficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

Proceeding NameFuture Internet Technologies and Trends. ICFITT 2017

PublisherSpringer, Cham

Published YearJanuary 2018

Exhausting Autonomic Techniques for Meticulous Consumption of Resources at an IaaS Layer of Cloud Computing

Conference

Title of PaperExhausting Autonomic Techniques for Meticulous Consumption of Resources at an IaaS Layer of Cloud Computing

Proceeding NameFuture Internet Technologies and Trends (ICFITT)

PublisherSpringer, Cham

Page Number37-46

Published YearJanuary 2018

ISSN/ISBN No978-3-319-73712-6

Exhausting Autonomic Techniques for Meticulous Consumption of Resources at an IaaS Layer of Cloud Computing

Journal

Journal NameLNICST: Exhausting Autonomic Techniques for Meticulous Consumption of Resources at an IaaS Layer of Cloud Computing

Title of PaperExhausting Autonomic Techniques for Meticulous Consumption of Resources at an IaaS Layer of Cloud Computing

PublisherSpringer, Cham

Volume Number220

Page Number37-46

Published YearJanuary 2018

ISSN/ISBN No1867-8211

Indexed INScopus, UGC List

Abstract

Internet based computing has provided lots of flexibility with respect to the usages of resources, as per the current demand of the users, and granting them the said resources has its own benefits, if given in proper manner i.e. exactly what the user has asked. In this paper the autonomic computing concepts has been discussed which will be very useful for the better utilisation of the resources at an IaaS (Infrastructure as a Service) level of the cloud computing. As Cloud Computing is highly scalable and virtualisation has become an important means for the efficient utilisation of the resources. Seeking the right amount of the resources at right time should be the goal of any CSP (Cloud service provider), On the other hand the CSPs has to deal with the situation of over provisioning and under provisioning, there should be some self-managing scheme through which the resources should be made available to the requesting user in an efficient manner to satisfy the need of their requirement with an improved resource utilisation. We have discussed the usage of autonomic computing to enhance the resource utilisation in the IaaS of cloud computing through various ways.

SLA Based an Efficient and Reliable Resource Provisioning in Private Cloud

Journal

Journal NameInternational Journal of Computer Science and Communication

Title of PaperSLA Based an Efficient and Reliable Resource Provisioning in Private Cloud

PublisherComputer Science and Electronic Journals

Volume Number8

Page Number141-145

Published YearSeptember 2017

ISSN/ISBN No0973-7391

SLA Management in Cloud Federation

Conference

Title of PaperSLA Management in Cloud Federation

Proceeding NameInternational Conference on Information and Communication Technology for Intelligent Systems(ICTIS)

PublisherSpringer, Cham

Published YearAugust 2017

ISSN/ISBN No978-3-319-63645-0

Capacity Planning Through Monitoring of Context Aware Tasks at IaaS Level of Cloud Computing

Journal

Journal NameLNICST springer: Capacity Planning Through Monitoring of Context Aware Tasks at IaaS Level of Cloud Computing

Title of PaperCapacity Planning Through Monitoring of Context Aware Tasks at IaaS Level of Cloud Computing

PublisherSpringer, Cham

Volume Number220

Page Number66-74

Published YearAugust 2017

ISSN/ISBN No1867-8211

Indexed INScopus, UGC List

Abstract

Cloud Computing is the exercise of using a network of remote servers held on the Internet to store, manage, and process data which have the characteristics as an elasticity, scalability or scalable resource sharing managed by the resource management. Even the growing demand of cloud computing has radically increased the energy consumption of the data centres, which is a critical scenario in the era of cloud computing, hence the resources has to be used efficiently, which ultimately will minimise the energy. Resource management itself will get the data from resource monitoring and resource prediction for the smooth conduction of the tasks and its allocated resources. In this paper the monitoring mechanism in the cloud has been discussed and its results are used to trigger the prediction rule engine which provides the cloud service provider (CSP) to start allocating the resources in the efficient manner, even the concept of failure handling has been mentioned based upon the certain parameter which will also inform the CSP to handle the failure task and try to mitigate this and again re schedule the failed task.

Efficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

Journal

Journal NameLNICST springer:Efficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

Title of PaperEfficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

PublisherSpringer, Cham

Volume Number220

Page Number47-55

Published YearAugust 2017

ISSN/ISBN No1867-8211

Indexed INScopus, UGC List

Abstract

In this paper, we have discussed about the various techniques through which the cloud computing monitoring and prediction can be achieved, This paper provides the survey of the techniques related to monitoring and prediction for the efficient usages of the resources available at the IaaS level of cloud. As cloud provides the services, which are elastic, scalable or highly dynamic in nature, which binds us to make the correct usages of the resources, but in real situations the (Cloud Service Provider)CSP’s has to face the situation of under provisioning and over provisioning, where the resources are not fully utilized and being wasted, though this is the survey paper, it ends up with the proposed model where both the concepts of the Monitoring and Prediction will be combined together to give a better vision of the future resource demand in IaaS layer of Cloud Computing.

Performance Analysis of Microsoft Windows 2008 R2 Active Directory Server in Consolidated Virtualized Environment on IBM’s HS22 High Performance Blade

Conference

Title of PaperPerformance Analysis of Microsoft Windows 2008 R2 Active Directory Server in Consolidated Virtualized Environment on IBM’s HS22 High Performance Blade

Proceeding NameCommunication and Electronics Systems (ICCES 2016)

PublisherIEEE

Year , VenueOctober 2016 , Coimbatore

ISSN/ISBN No978-1-5090-1066-0

Design of efficient algorithm for secured key exchange over Cloud Computing

Conference

Title of PaperDesign of efficient algorithm for secured key exchange over Cloud Computing

Proceeding Name2016 6th International Conference-Cloud System and Big Data Engineering (Confluence)

PublisherIEEE

Year , VenueJuly 2016 , Noida, India

Page Number180-187

ISSN/ISBN No978-1-4673-8203-8

Enhancing Data Delivery with Density Controlled Clustering in Wireless Sensor Networks

Journal

Journal NameJournal of Micro System Technologies (Springer)

Title of PaperEnhancing Data Delivery with Density Controlled Clustering in Wireless Sensor Networks

PublisherSpringer

Page Number613-631

Published YearMay 2016

Resource provisioning strategies in cloud: a survey

Journal

Journal NameInternational Journal of Computer Science and Communication

Title of PaperResource provisioning strategies in cloud: a survey

PublisherComputer Science and Electronic Journals

Volume Number7

Page Number12-15

Published YearMarch 2016

ISSN/ISBN No0973-7391

Proposed Ontology Framework for Dynamic Resource Provisioning on Public Cloud

Journal

Journal NameInternational Journal of Advanced Research in Engineering and Technology (IJARET)

Title of PaperProposed Ontology Framework for Dynamic Resource Provisioning on Public Cloud

PublisherThe International Association of Engineering and Management Education (IAEME)

Page Number118-131

Published YearJanuary 2016

ISSN/ISBN No0976-6499

Efficient and dynamic resource provisioning strategy for data processing using cloud computing

Journal

Journal NameInternational Review on Computers and Software (I. RE. CO. S.)

Title of PaperEfficient and dynamic resource provisioning strategy for data processing using cloud computing

Volume Number11

Published YearJanuary 2016

Model based robust Peak Detection algorithm of Radiation Pulse Shape using limited samples

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperModel based robust Peak Detection algorithm of Radiation Pulse Shape using limited samples

Volume Number7

Page Number11-18

Published YearJanuary 2016

ISSN/ISBN No0973-7391

Improving Energy Estimation based Clustering with Energy Threshold for Wireless Sensor Networks

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperImproving Energy Estimation based Clustering with Energy Threshold for Wireless Sensor Networks

Published YearJanuary 2015

Indexed INEBSCO

Improving Data Delivery with Density Control based Clustering in Wireless Sensor Networks

Conference

Title of PaperImproving Data Delivery with Density Control based Clustering in Wireless Sensor Networks

Proceeding Name3rd International Conference on Computing, Communication and Sensor Network, CCSN2014

PublisherIEEE

Year , VenueDecember 2014 , Puri, Odisha, India

Performance Comparison of Various Clustering Techniques in Wireless Sensor Networks

Journal

Journal NameInternational Journal of Computer Science & communication

Title of PaperPerformance Comparison of Various Clustering Techniques in Wireless Sensor Networks

Volume Number5

Page Number116-123

Published YearSeptember 2014

ISSN/ISBN No0973-7391

NCloud - Experimenting with Architecting and Facilitating Utility Services for establishing Educational

Journal

Journal NameJournal of Mobile, Embedded and Distributed Systems

Title of PaperNCloud - Experimenting with Architecting and Facilitating Utility Services for establishing Educational

Volume Number5

Page Number58-62

Published YearJanuary 2013

Indexed INEBSCO

Classification of Weather Indices on Secured Computational Grid

Journal

Journal NameInternational Journal of u- and e- Service, Science and Technology

Title of PaperClassification of Weather Indices on Secured Computational Grid

Volume Number4

Published YearJune 2011

ISSN/ISBN No2005-4270

NGSched - An Efficient Scheduling Algorithm handling interactive jobs in Grid Environment

Journal

Journal NameInternational Journal of Grid and Distributed Computing IJGDC

Title of PaperNGSched - An Efficient Scheduling Algorithm handling interactive jobs in Grid Environment

Volume Number4

Published YearJune 2011

ISSN/ISBN No2005-4270

Single Sign on in Cloud Computing

Conference

Title of PaperSingle Sign on in Cloud Computing

Proceeding NameNUiCONE-2011, International Conference on Current Trends in Engineering

Year , VenueDecember 2010 , Nirma University, Ahmedabad, India

Development of QoS based scheduling algorithm in the grid environment

Conference

Title of PaperDevelopment of QoS based scheduling algorithm in the grid environment

Proceeding NameNUiCONE-2010, International Conference on Current Trends in Engineering

Year , VenueDecember 2010 , Nirma University, Ahmedabad India

Analyzing Cloud Possibility and limitations

Conference

Title of PaperAnalyzing Cloud Possibility and limitations

Proceeding NameNUiCONE-2010, International Conference on Current Trends in Engineering

Year , VenueDecember 2010 , Nirma University, Ahmedabad, India

Handling Complex Use scenarios for selection of best resources in grid environment

Conference

Title of PaperHandling Complex Use scenarios for selection of best resources in grid environment

Proceeding NameNUiCONE-2010, International Conference on Current Trends in Engineering

Year , VenueDecember 2010 , Nirma University, Ahmedabad India

Analysis of Multi Agent Based Interactive Grid Using Formal Methods - A Reliable Approach

Conference

Title of PaperAnalysis of Multi Agent Based Interactive Grid Using Formal Methods - A Reliable Approach

Proceeding NameIEEE International Conference on Engineering & Technology (ICETET)

Year , VenueNovember 2010 , BITS Pilani, Goa

User Centric Job Management in Grid Using Multiple Agents an Unified Approach

Journal

Journal NameNirma university Journal of Engineering and Technology

Title of PaperUser Centric Job Management in Grid Using Multiple Agents an Unified Approach

PublisherDirectory of Open Access Journals

Volume Number1

Published YearOctober 2010

Effective Resource Management in Clouds Using Advance Reservation

Conference

Title of PaperEffective Resource Management in Clouds Using Advance Reservation

Proceeding Name2010 International Conference on Intelligent Network and Computing (ICINC 2010)

Year , VenueJanuary 2010 , Malasiya

Page Number380-383

Scavenging Idle CPU Cycles for Creation of Inexpensive Supercomputing Power

Journal

Journal NameInternational Journal of Computer Theory and Engineering

Title of PaperScavenging Idle CPU Cycles for Creation of Inexpensive Supercomputing Power

Volume Number1

Published YearJanuary 2009

Indexed INEBSCO, Others

Performance Assessment of Computational Grid on Weather Indices from HOAPS data

Conference

Title of PaperPerformance Assessment of Computational Grid on Weather Indices from HOAPS data

Proceeding NameProceedings of International Conference on Cluster and Grid Computing systems

PublisherWASET (World Academy of Science, Engineering and Technology)

Published YearJanuary 2008

Performance Assessment of Computational Grid on Weather Indices from HOAPS Data

Journal

Journal NameInternational Journal of World Academy of Science, Engineering and Technology

Title of PaperPerformance Assessment of Computational Grid on Weather Indices from HOAPS Data

Published YearJanuary 2008

HEAL-SDN: Artificial Neural Network-based Secure Data Exchange Framework for SDN Controllers in Healthcare 4.0

Conference

Title of PaperHEAL-SDN: Artificial Neural Network-based Secure Data Exchange Framework for SDN Controllers in Healthcare 4.0

PublisherIEEE

Author NameMalaram Kumhar, Jitendra Bhatia, Nilesh Kumar Jadav, Ali Asgar Padaria, Rajesh Gupta, Sudeep Tanwar, Joel JPC Rodrigues

Year , VenueMarch 2024 , Kuala Lumpur, Malaysia

Page Number1832-1837

ISSN/ISBN No979-8-3503-7021-8

Indexed INScopus

IoMT-Enabled Smart Healthcare: State-of-the-Art, Security and Future Directions

Conference

Title of PaperIoMT-Enabled Smart Healthcare: State-of-the-Art, Security and Future Directions

PublisherIEEE

Author NameShivam Tripathi, Vatsalkumar Makwana, Malaram Kumhar, Harshal Trivedi, Jitendra Bhatia, Sudeep Tanwar, Hossein Shahinzadeh

Year , VenueFebruary 2024 , Online

Page Number36-43

ISSN/ISBN No979-8-3503-4942-9

Indexed INScopus

AI-based Intelligent SDN Controller to Optimize Onion Routing Framework for IoMT Environment

Conference

Title of PaperAI-based Intelligent SDN Controller to Optimize Onion Routing Framework for IoMT Environment

PublisherIEEE

Author NameMalaram Kumhar, Jitendra Bhatia, Nilesh Kumar Jadav, Rajesh Gupta, Sudeep Tanwar

Year , VenueOctober 2023 , Online

Page Number885-890

ISSN/ISBN No979-8-3503-3308-4

Indexed INScopus

Secure and Explainable Artificial Intelligence (XAI) in Cloud Ecosystems: Challenges and Opportunities

Book Chapter

Book Name Lecture Notes in Networks and Systems

PublisherSpringer Nature Singapore

Author NameDarshi Khalasi, Devang Bathwar, Jitendra Bhatia, Malaram Kumhar, Vinodray Thumar

Page Number553-567

Chapter TitleSecure and Explainable Artificial Intelligence (XAI) in Cloud Ecosystems: Challenges and Opportunities

Published YearSeptember 2023

ISSN/ISBN No2367-3389

Indexed INScopus

Deep Learning-Based Single-Image Super-Resolution: A Comprehensive Review

Journal

Journal NameIEEE Access

Title of PaperDeep Learning-Based Single-Image Super-Resolution: A Comprehensive Review

PublisherIEEE

Volume Number11

Page Number21811-21830

Published YearFebruary 2023

Indexed INScopus, Web of Science

An Overview of Fog Data Analytics for IoT Applications

Journal

Journal NameSensors

Title of PaperAn Overview of Fog Data Analytics for IoT Applications

PublisherMDPI

Volume Number23

Page Number1-32

Published YearDecember 2022

Indexed INScopus, Web of Science

Software-defined networks-enabled fog computing for IoT-based healthcare: Security, challenges and opportunities

Journal

Journal NameSecurity and Privacy

Title of PaperSoftware-defined networks-enabled fog computing for IoT-based healthcare: Security, challenges and opportunities

PublisherWiley

Volume Numbere291

Page Number1-15

Published YearNovember 2022

Indexed INScopus

Edge Computing in SDN-Enabled IoTBased Healthcare Frameworks: Challenges and Future Research Directions

Journal

Journal NameInternational Journal of Reliable and Quality E-Healthcare

Title of PaperEdge Computing in SDN-Enabled IoTBased Healthcare Frameworks: Challenges and Future Research Directions

PublisherIGI Global

Volume Number11

Page Number1-15

Published YearSeptember 2022

Indexed INScopus

Emerging Communication Technologies for 5G-Enabled Internet of Things Applications

Book Chapter

Book NameBlockchain for 5G-Enabled IoT

PublisherSpringer

Author NameMalaram Kumhar, Jitendra Bhatia

Page Number133-158

Chapter TitleEmerging Communication Technologies for 5G-Enabled Internet of Things Applications

Published YearMay 2021

ISSN/ISBN No978-3-030-67489-2

Indexed INScopus

Advances in Single Image Super-Resolution: A Deep Learning Perspective

Book Chapter

Book NameLecture Notes in Networks and Systems

PublisherSpringer

Author NameKaransingh Chauhan, Hrishikesh Patel, Ridham Dave, Jitendra Bhatia and Malaram Kumhar

Page Number443-455

Chapter TitleAdvances in Single Image Super-Resolution: A Deep Learning Perspective

Published YearMay 2020

ISSN/ISBN No978-981-15-3368-6

Indexed INScopus

Quality Evaluation Model for Multimedia Internet of Things (MIoT) Applications: Challenges and Research Directions

Book Chapter

Book NameAdvances in Intelligent Systems and Computing

PublisherSpringer

Author NameMalaram Kumhar, Gaurang Raval and Vishal Parikh

Page Number330-336

Chapter TitleQuality Evaluation Model for Multimedia Internet of Things (MIoT) Applications: Challenges and Research Directions

Published YearMarch 2020

ISSN/ISBN No978-3-030-39874-3

Indexed INScopus

Swine Flu Predication Using Machine Learning

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer

Author NameDvijesh Bhatt, Daiwat Vyas, Malaram Kumhar and Ajay Patel

Page Number611-617

Chapter TitleSwine Flu Predication Using Machine Learning

Published YearDecember 2018

ISSN/ISBN No978-981-13-1746-0

Indexed INScopus

Medical Diagnosis System Using Machine Learning

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperMedical Diagnosis System Using Machine Learning

PublisherIJCSC

Volume Number7

Page Number177-182

Published YearApril 2016

ISSN/ISBN No0973-7391

Indexed INOthers

Improving Security in P2P File Sharing Based on Network Coding for DTN

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperImproving Security in P2P File Sharing Based on Network Coding for DTN

PublisherIJCSC

Volume Number7

Page Number167-172

Published YearMarch 2016

ISSN/ISBN No0973-7391

Indexed INOthers

Ransomware: A Threat to Cyber security

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperRansomware: A Threat to Cyber security

PublisherIJCSC

Volume Number7

Page Number224-227

Published YearSeptember 2015

ISSN/ISBN No0973-7391

Indexed INOthers

Perspective Study on Load Balancing Paradigms in Cloud Computing

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperPerspective Study on Load Balancing Paradigms in Cloud Computing

PublisherIJCSC

Volume Number6

Page Number112-120

Published YearMarch 2015

ISSN/ISBN No0973-7391

Indexed INOthers

Survey on QoS Aware Routing Protocols for Wireless Multimedia Sensor Networks

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperSurvey on QoS Aware Routing Protocols for Wireless Multimedia Sensor Networks

PublisherIJCSC

Volume Number6

Page Number121-128

Published YearMarch 2015

ISSN/ISBN No0973-7391

Indexed INOthers

Healthcare-CT: SoLiD PoD and Blockchain-Enabled Cyber Twin Approach for Healthcare 5.0 Ecosystems

Journal

Journal NameIEEE Internet of Things Journal

Title of PaperHealthcare-CT: SoLiD PoD and Blockchain-Enabled Cyber Twin Approach for Healthcare 5.0 Ecosystems

PublisherIEEE

Volume Number11

Page Number6119-6130

Published YearFebruary 2024

ISSN/ISBN No2327-4662

Indexed INScopus, Web of Science

Abstract

The healthcare personals often use stored healthcare data to make crucial decisions, assess risk, and care for patients. The extraction of the required information from the saved healthcare data needs a healthcare ecosystem that can guarantee reliable data delivery. The reliability of cyber–physical data needs to be cross-examined using several sources of data of overlapping nature. The cross-examined data can be saved on blockchain and Solid PoD (SP) to preserve its reliability and privacy. Once the reliable healthcare data is stored on the blockchain and SP, the patients’ medical history can be delivered to data-operated systems to monitor, diagnose, and detect augmented healthcare anomalies. Cyber twins (CTs) combine the specific cyber–physical objects with digital tools portraying their actual settings. The creation of a live model for the delivery of healthcare services presents a novel opportunity in patient care comprising better evaluation of risk and assessment without hampering the activities of daily living. The introduction of blockchain technology can improve the notion of CTs by certifying transparency, decentralized data storage, data irreversibility, and person-to-person industrial communication. The storage and exchange of CT data in the healthcare ecosystem depend on disseminated ledgers and decentralized databases for storing and processing data to avoid single-point reliance. The present study develops an owner-centric decentralized sharing technique to fulfill the decentralized distribution of CT data.

Covertvasion: Depicting threats through covert channels based novel evasive attacks in android

Journal

Journal NameInternational Journal of Intelligent Networks

Title of PaperCovertvasion: Depicting threats through covert channels based novel evasive attacks in android

PublisherElsevier

Volume Number4

Page Number337-348

Published YearDecember 2023

ISSN/ISBN No2666-6030

Indexed INScopus

Abstract

Privacy and security issues concerning mobile devices have substantial consequences for individuals, groups, governments, and businesses. The Android operating system bolsters smartphone data protection by imposing restrictions on app behavior. Nevertheless, attackers conduct systematic resource analyses and divert privacy-sensitive information from plain view. They employ evasive mechanisms to evade system monitoring and create an illusion of benign and non-sensitive communication. Furthermore, covert channels amplify the impact of these malicious activities by facilitating information transfer through non-standard methods. The purpose of this research is to shed light on these novel threats targeting Android systems. The study delves into security and privacy attacks that compromise sensitive user information. The methodology leverages evasion concepts and employs sound-specific covert channel communication, particularly ultrasonic channels. This research work introduces novel evasive attacks, namely Prime-Composite Evasive Information Invasion (PCEII) and File-lock-based Evasive Information Invasion (FEII), both relying on covert channel communication. These unique variants of attacks successfully evade user data within a few milliseconds for both noisy as well as non-noisy environments and do not show any signs of detection by antivirus mechanisms like Anti-Virus Guard (AVG), 360 security, etc. and state-of-the-art tools such as TaintDroid, MockDroid and others. The paper not only assesses their impact on the privacy and security of information but also introduces avenues for their detection and mitigation.

FIMBISAE: A Multimodal Biometric Secured Data Access Framework for Internet of Medical Things Ecosystem

Journal

Journal NameIEEE Internet of Things Journal

Title of PaperFIMBISAE: A Multimodal Biometric Secured Data Access Framework for Internet of Medical Things Ecosystem

PublisherIEEE

Volume Number10

Page Number6259 - 6270

Published YearApril 2023

ISSN/ISBN No2327-4662

Indexed INScopus, Web of Science

Abstract

Information from the Internet of Medical Things (IoMT) domain demands building safeguards against illegitimate access and identification. Existing user identification schemes suffer from challenges in detecting impersonation attacks which leave systems vulnerable and susceptible to misuse. Significant advancement has been achieved in the domain of biometrics and health informatics. This can take a step ahead with the usage of multimodal biometrics for the identification of healthcare system users. With this aim, the proposed work explores the fingerprint and iris modality to develop a multimodal biometric data identification and access control system for the healthcare ecosystem. In the proposed approach, minutiae-based fingerprint features and a combination of local and global iris features are considered for identification. Further, an index space based on the dimension of the feature vector is created, which gives a 1-D embedding of the high-dimensional feature set. Next, to minimize the impact of false rejection, the approach considers the possible deviation in each element of the feature vector and then stores the data in possible locations using the predefined threshold. Besides, to reduce the false acceptance rate, linking of the modalities has been done for every individual data. The modality linking thus helps in carrying out an efficient search of the queried data, thereby minimizing the false acceptance and rejection rate. Experiments on a chimeric iris and fingerprint bimodal database resulted in an average of 95% reduction in the search space at a hit rate of 98%. The results suggest that the proposed indexing scheme has the potential to substantially reduce the response time without compromising the accuracy of identification.

Prediction of significant wave height using machine learning and its application to extreme wave analysis

Journal

Journal NameJournal of Earth System Science

Title of PaperPrediction of significant wave height using machine learning and its application to extreme wave analysis

PublisherSpringer

Volume Number132

Page Number51

Published YearMarch 2023

ISSN/ISBN No0973-774X

Indexed INScopus, Web of Science

Abstract

Waves of large size can damage offshore infrastructures and affect marine facilities. In coastal engineering studies, it is essential to have the probability estimates of the most extreme wave height expected during the lifetime of the structure. This study predicts significant wave height using the machine learning (ML) technique with generalized extreme value (GEV) theory and its application to extreme wave analysis. The wind speed, wind direction, sea temperature, and swell height data consisting of wave characteristics for 60 years has been obtained from the European Centre for Medium-Range Weather Forecasts (ECMWF). While analyzing extreme waves, the block maxima approach in GEV was used to incorporate the seasonal variations present in the data. The estimated scale parameter, shape parameter, and location parameter of GEV are used in the ML model to predict the significant wave heights along with their return periods. The ML algorithms such as linear regression (LR), artificial neural networks (ANN), and support vector machines (SVM) are evaluated in terms of R2 performance. The model comparison results suggested that the SVM model outperforms the LR and ANN models with an accuracy of 99.80%. Finally, the GEV analysis gives the extreme wave height results of 2.348, 3.470, and 4.713 m with a return period of 5, 20, and 100 yrs, respectively. Hence, the model developed is capable of predicting both significant wave height and extreme waves for the design of coastal structures.

AI-enabled radiologist in the loop: novel AI-based framework to augment radiologist performance for COVID-19 chest CT medical image annotation and classification from pneumonia

Journal

Journal NameNeural Computing and Applications

Title of PaperAI-enabled radiologist in the loop: novel AI-based framework to augment radiologist performance for COVID-19 chest CT medical image annotation and classification from pneumonia

PublisherSpringer

Volume Number35

Page Number14591–14609

Published YearMarch 2023

ISSN/ISBN No1433-3058

Indexed INScopus, Web of Science

Abstract

A SARS-CoV-2 virus-specific reverse transcriptase-polymerase chain reaction (RT-PCR) test is usually used to diagnose COVID-19. However, this test requires up to 2 days for completion. Moreover, to avoid false-negative outcomes, serial testing may be essential. The availability of RT-PCR test kits is currently limited, highlighting the need for alternative approaches for the precise and rapid diagnosis of COVID-19. Patients suspected to be infected with SARS-CoV-2 can be assessed using chest CT scan images. However, CT images alone cannot be used for ruling out SARS-CoV-2 infection because individual patients may exhibit normal radiological results in the primary phases of the disease. A machine learning (ML)-based recognition and segmentation system was developed to spontaneously discover and compute infection areas in CT scans of COVID-19 patients. The computable assessment exhibited suitable performance for automatic infection region allocation. The ML models developed were suitable for the direct detection of COVID-19 (+). ML was confirmed to be a complementary diagnostic technique for diagnosing COVID-19(+) by forefront medical specialists. The complete manual delineation of COVID-19 often requires up to 225.5 min; however, the proposed RILML method decreases the delineation time to 7 min after four iterations of model updating.

A composite approach of intrusion detection systems: hybrid RNN and correlation-based feature optimization

Journal

Journal NameElectronics

Title of PaperA composite approach of intrusion detection systems: hybrid RNN and correlation-based feature optimization

PublisherMDPI

Volume Number11

Page Number3529

Published YearOctober 2022

ISSN/ISBN No2079-9292

Indexed INScopus, Web of Science

Abstract

Detection of intrusions is a system that is competent in detecting cyber-attacks and network anomalies. A variety of strategies have been developed for IDS so far. However, there are factors that they lack in performance, creating scope for further research. The current trend shows that the Deep Learning (DL) technique has been proven better than traditional techniques for IDS. Throughout these studies, we presented a hybrid model that is a Deep Learning method called Bidirectional Recurrent Neural Network using Long Short-Term Memory and Gated Recurrent Unit. Through simulations on the public dataset CICIDS2017, we have shown the model’s effectiveness. It has been noted that the suggested model successfully predicted most of the network attacks with 99.13% classification accuracy. The proposed model outperformed the Naïve Bayes classifier in terms of prediction accuracy and False Positive rate. The suggested model managed to perform well with only 58% attributes of the dataset compared to other existing classifiers. Moreover, this study also demonstrates the performance of LSTM and GRU with RNN independently.

Eliciting relative preferences for the attributes of health insurance schemes among rural consumers in India

Journal

Journal NameInternational Journal of Health Economics and Management

Title of PaperEliciting relative preferences for the attributes of health insurance schemes among rural consumers in India

PublisherSpringer

Volume Number22

Page Number443-458

Published YearApril 2022

ISSN/ISBN No2199-9031

Indexed INScopus, Web of Science

Abstract

There is a limited understanding of the preferences of rural consumers in India for health insurance schemes. In this article, we investigate the preferences of the rural population for the attributes of a health insurance scheme by implementing a discrete choice experiment (DCE). We identified six attributes through qualitative and quantitative study: enrollment, management, benefit package, coverage, transportation facility, and monthly premium. A D-efficient design of 18 choices has been constructed, each comprising two health insurance choices. We collected the representative sample from 675 household heads of the rural population through personal interviews. The preferences for the attributes and attribute levels were estimated using the multinomial logit (MNL) and random-parameter logit (RPL) models. The analysis shows that all attribute levels significantly affect the choice behavior (P < 0.05). The relative order of preferences for attributes are; enrollment, benefit package, monthly premium, management, coverage, and transportation.

DBGC: Dimension-based generic convolution block for object recognition

Journal

Journal NameSensors

Title of PaperDBGC: Dimension-based generic convolution block for object recognition

PublisherMDPI

Volume Number22

Page Number1780

Published YearFebruary 2022

ISSN/ISBN No1424-8220

Indexed INScopus, Web of Science

Abstract

The object recognition concept is being widely used a result of increasing CCTV surveillance and the need for automatic object or activity detection from images or video. Increases in the use of various sensor networks have also raised the need of lightweight process frameworks. Much research has been carried out in this area, but the research scope is colossal as it deals with open-ended problems such as being able to achieve high accuracy in little time using lightweight process frameworks. Convolution Neural Networks and their variants are widely used in various computer vision activities, but most of the architectures of CNN are application-specific. There is always a need for generic architectures with better performance. This paper introduces the Dimension-Based Generic Convolution Block (DBGC), which can be used with any CNN to make the architecture generic and provide a dimension-wise selection of various height, width, and depth kernels. This single unit which uses the separable convolution concept provides multiple combinations using various dimension-based kernels. This single unit can be used for height-based, width-based, or depth-based dimensions; the same unit can even be used for height and width, width and depth, and depth and height dimensions. It can also be used for combinations involving all three dimensions of height, width, and depth. The main novelty of DBGC lies in the dimension selector block included in the proposed architecture. Proposed unoptimized kernel dimensions reduce FLOPs by around one third and also reduce the accuracy by around one half; semi-optimized kernel dimensions yield almost the same or higher accuracy with half the FLOPs of the original architecture, while optimized kernel dimensions provide 5 to 6% higher accuracy with around a 10 M reduction in FLOPs.

Amalgamation of blockchain and sixth‐generation‐envisioned responsive edge orchestration in future cellular vehicle‐to‐anything ecosystems: Opportunities and challenges

Journal

Journal NameTransactions on Emerging Telecommunications Technologies

Title of PaperAmalgamation of blockchain and sixth‐generation‐envisioned responsive edge orchestration in future cellular vehicle‐to‐anything ecosystems: Opportunities and challenges

PublisherWiley

Volume Numbere4410

Page Number123

Published YearDecember 2021

ISSN/ISBN Noe4410

Abstract

In modern decentralized cellular-vehicle-to-anything (C-V2X) infrastructures, connected autonomous smart vehicles (CASVs) exchange vehicular information with peer CASVs. To leverage responsive communication, sensors deployed in CASVs communicate through responsive edge computing (REC) infrastructures to support device-to-device- (D2D) based communication. To support low-latency, high-bandwidth, dense mobility, and high availability, researchers worldwide have proposed efficient 5G REC infrastructures to end vehicular users (VU). However, with the growing number of sensor units, intelligent automation, dense sensor integration at massive ultra-low latency is required. To address the issue, the focus has shifted toward sixth-generation (6G)-based intelligent C-V2X orchestration. However, the sensor data is exchanged through open channels, and thus trust and privacy among C-V2X nodes is a prime concern. Thus, blockchain (BC) is a potential solution to allow immutable exchange ledgers among CASV sensor units for secure data exchange. With this motivation, the proposed survey integrates BC and 6G-leveraged REC in C-V2X to address the issues of fifth-generation (5G)-REC through immutable, verified, and chronological timestamped data exchanged through 6G-envisioned terahertz (THz) channels, at high mobility, extremely low latency, and high availability. The survey also presents the open issues and research challenges in the 6G-envisioned BC-enabled REC C-V2X ecosystems via a proposed framework. A case study 6Edge is presented for smart 6G intelligent edge integration with BC-based ledgers. Finally, the concluding remarks and future direction of research are proposed. Thus, the proposed survey forms a guideline for automotive stakeholders, academicians, and researchers to explore the various opportunities of the possible integration in more significant detail.

CP-BDHCA: Blockchain-Based Confidentiality-Privacy Preserving Big Data Scheme for Healthcare Clouds and Applications

Journal

Journal NameIEEE Journal of Biomedical and Health Informatics

Title of PaperCP-BDHCA: Blockchain-Based Confidentiality-Privacy Preserving Big Data Scheme for Healthcare Clouds and Applications

Volume Number26

Page Number1937-1948

Published YearJanuary 2021

Indexed INScopus, Web of Science

Data Modeling Practices for E-Commerce.

Journal

Journal NameGrenze International Journal of Engineering & Technology (GIJET)

Title of PaperData Modeling Practices for E-Commerce.

Publisher Trivandrum GRENZE Scientific Society

Volume Number10(1)

Page Number613-622

Published YearJanuary 2024

ISSN/ISBN No2395-5295

Indexed INScopus, EBSCO

Document Store Schema Design Alternatives and Their Impact

Conference

Title of PaperDocument Store Schema Design Alternatives and Their Impact

Proceeding NameInternational Conference on Data Analytics & Management

PublisherSpringer Nature Singapore

Author NameMonika Shah, Amit Kothari

Page Number471-482

Published YearNovember 2023

ISSN/ISBN No978-981-99-6549-6

Indexed INScopus

Comparative analysis of detecting over-claim permissions from android apps

Conference

Title of PaperComparative analysis of detecting over-claim permissions from android apps

Proceeding Name2023 International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC)

PublisherIEEE

Author NameRaj J Majethiya, Monika Shah

Page Number1-8

Published YearFebruary 2023

Indexed INScopus

A comprehensive Survey on Energy Consumption Analysis for NoSQL

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperA comprehensive Survey on Energy Consumption Analysis for NoSQL

PublisherWest University of Timisoara

Volume Number23(1)

Page Number35-50

Published YearApril 2022

ISSN/ISBN No1895-1767

Indexed INScopus

Abstract

During the last few years, we are witnessing increasing development in the Internet of Things (IoT) and big data. To address increasing workload complexity with better performance and to handle scalability issues of such applications, non-relational (NoSQL) has started taking the place of relational databases. With increasing load, it is challenging to maintain NoSQL’s performance, scalability, and availability without expanding the capacity of hosts and power budget of computing resources [57]. Future scaling of data center capabilities depends on the improvement of server power efficiency [22, 33]. Considering the rise of energy costs and environmental sustainability, we can not ignore this high energy consumption caused by NoSQL. Despite the increasing popularity and share of NoSQL in the software market, little is still known about its energy footprint. To the best of our knowledge, there are no comprehensive studies that analyze the energy consumption by various modules of NoSQL. This article, therefore, conducts a comprehensive survey on the energy consumption analysis of NoSQL. There are limited proposals to reduce the energy consumption of NoSQL. This paper also provides a brief description of these little efforts on reducing the energy consumption of NoSQL. Based on the review, this paper discusses the research scope and opportunities for researchers to improve the energy conservation of NoSQL systems

Detecting over-claim permissions and recognising dangerous permission in Android apps

Journal

Journal NameInternational Journal of Information and Computer Security

Title of PaperDetecting over-claim permissions and recognising dangerous permission in Android apps

PublisherInderscience

Volume Number17(1)

Page Number204-218

Published YearFebruary 2022

ISSN/ISBN No17441765

Indexed INScopus

Abstract

Android's security is one of the hot research topics in the current days. This is mainly due to the leakage of user's privacy information from third-party apps on mobile. Even after the permission model defined by Android we all are witnessing leakage of our critical information. This is mainly due to: 1) the permission model is proportionally coarse granular; 2) insufficient knowledge of user makes him approve over-claim permission mistakenly. Henceforth this paper focuses on recognising dangerous over-claim permission. This starts with describing the permission model, over-claim permission, and some of the dangerous over-claim permission. This paper specifically proposes an algorithm to detect the signature of dangerous permission incorporated during the upgrading version of third-party software.

Influence of Schema Design in NoSQL Document Stores

Conference

Title of PaperInfluence of Schema Design in NoSQL Document Stores

Proceeding NameLecture Notes on Data Engineering and Communications Technologies

PublisherSpringer

Author NameMonika Shah

Year , VenueJuly 2021 , Nepal

Page Number435-452

ISSN/ISBN No23674512

Indexed INScopus

Abstract

Schema-free (flexible schema) is an attractive feature in the NoSQL document store, where users can access the database without referring to its schema. It reduces the stress of developers to design database schema and applications. Data modeling is defined as arranging application data using acceptable data structuring patterns and is the primary component of the schema design in the document store. In addition, studies have continued examining NoSQL’s energy consumption pattern. But, our recent survey does not observe any energy-efficienct analysis for NoSQL schema. This work therefore designs alternative schemes using a particular combination of document store structuring patterns and analyzes storage criteria for everything. In NoSQL, the use of indexing and application-level joints is widely adopted. This article also compares performance and energy requirements for query processing with/without indexing, and application-level join operations and also helps to design query optimization.

Identification of artificially ripen mango using aroma and texture features

Conference

Title of PaperIdentification of artificially ripen mango using aroma and texture features

Proceeding Name2021 International Conference on Intelligent Technologies, CONIT 2021

PublisherIEEE

Page Number1-6

Published YearJune 2021

ISSN/ISBN No978-172818583-5

Indexed INScopus

Abstract

Mango is known as a king of fruit. It has a unique sweet taste, flavor, and nutritionally rich attributes. Therefore, it is beloved by all age groups of people. Looking at the high popularity of ripening mangoes, vendors are attracted to artificial ripening using hazardous chemicals like calcium carbide. Most governments have banned the use of calcium carbide. Unfortunately, the use of calcium carbide still exists as per several reports. Today, the public is being aware and cautious to avoid buying such artificially ripened mango. But, it is difficult for humans to differentiate an artificially ripe and naturally ripe mango and that too specifically for some species like Kesar by the human eye. This paper proposes a non-destructive approach to identify an artificially ripened Kesar mango. The first phase uses image features and a decision tree to classify mango into ripe, unripe, and partially ripe categories with 93% accuracy. The second phase discards unripe mango images and processes to identify artificially ripened or ripening mango using GLSM based image processing and an MQ3 aroma sensor.

Efficient Classification of True Positive and False Positive XSS and CSRF Vulnerabilities Reported by the Testing Tool

Conference

Title of PaperEfficient Classification of True Positive and False Positive XSS and CSRF Vulnerabilities Reported by the Testing Tool

Proceeding NameProceedings of Second International Conference on Computing, Communications, and Cyber-Security

PublisherSpringer

Author NameMonika Shah, Himani Lad

Page Number871-884

Published YearOctober 2020

ISSN/ISBN No978-981160732-5

Indexed INScopus

Abstract

Security testing is essential for website and web applications in current days. It is easy for an attacker to invade the security and do malicious activities through web applications if they are not properly protected against known attacks. General practice in web application before release is using testing tools to recognize the possible set of vulnerabilities, which can be true-positive or false-positive. Then the developer team will be asked to revise code to protect against true-positive vulnerabilities. For that, the testing team needs to classify each reported vulnerability into true-positive and false-positive individually, which is very time-consuming. This article suggests innovation in this practice to reduce the time of recognizing true-positive vulnerabilities. It presents a novel approach to classify reported multiple vulnerabilities of different attacks using a single script and in single go. These attacks should share common triggering events or testing process. Cross-Site Scripting (XSS) and Cross-Site Request Forgery (CSRF) attacks are chosen to illustrate the approach

On Performance Enhancement of Molecular Dynamics Simulation Using HPC Systems

Conference

Title of PaperOn Performance Enhancement of Molecular Dynamics Simulation Using HPC Systems

Proceeding NameProceedings of Second International Conference on Computing, Communications, and Cyber-Security

Author NameTejal Rathod, Monika Shah, Madhuri Bhavsar, Niraj Shah, Gaurang Raval

Page Number1031-1044

Published YearOctober 2020

ISSN/ISBN No978-981160732-5

Indexed INScopus

A Comprehensive Survey on Energy-Efficient Power Management Techniques

Journal

Journal NameProcedia Computer Science

Title of PaperA Comprehensive Survey on Energy-Efficient Power Management Techniques

PublisherElsevier

Volume Number167

Page Number1189-1199

Published YearJanuary 2020

ISSN/ISBN No18770509

Indexed INScopus

Design and simulation of single electron transistor based SRAM and its memory controller at room temperature

Journal

Journal NameInternational Journal of Integrated Engineering

Title of PaperDesign and simulation of single electron transistor based SRAM and its memory controller at room temperature

Volume Number11

Page Number186-195

Published YearSeptember 2019

Parallelization of Velvet using Hybrid Computing

Conference

Title of PaperParallelization of Velvet using Hybrid Computing

PublisherAcademic Science

Page Number62-67

Published YearDecember 2016

ISSN/ISBN No978-81-932712-2-3

Indexed INUGC List

Abstract

Advances in DNA sequencing technologies have revolutionized the field of genomics by providing solutions which are cost effective and provide high throughput. In the verge of achieving this goal researchers and academicians are putting efforts for optimizi ng bioinformatics operations using HPC and advanced computing. Sequence assembling is a primitive component in Bioinformati

One dimensional ocean waves displacement prediction system expanding mathematical string equation

Conference

Title of PaperOne dimensional ocean waves displacement prediction system expanding mathematical string equation

PublisherIEEE

OrganizationNirma University International Conference on Engineering (NUiCONE)

Year , VenueNovember 2015 , Ahmedabad, India

ISSN/ISBN No978-1-4799-9991-0

Indexed INScopus, UGC List

Abstract

Oceanography comprises of parameters like wave-height, ocean-pressure, ocean-density, ocean-winds, ocean-depth, surface tension, sea-surface topography, etc. Predictions of upcoming changes are made using these parameters as inputs. Real-time sensors are deployed under the ocean to fetch real time measurements of parameters. Our research describes the work with respect to ocean wave-height paramet

Sparse Matrix Sparse Vector Multiplication - A Novel Approach

Conference

Title of PaperSparse Matrix Sparse Vector Multiplication - A Novel Approach

PublisherIEEE

Organization44th International Conference on Parallel Processing Workshops

Year , VenueSeptember 2015 , Beijing, China

Page Number67-73

ISSN/ISBN No1530-2016

Indexed INScopus

Abstract

The terabytes of information available on the internet creates a severe demand of scalable information retrieval systems. Sparse Matrix Vector Multiplication (SpMV) is a well-known kernel for such computing applications in science and engineering world. This raises need of designing an efficient SpMV. Researchers are putting their continuous effort to optimize SpMV that deal with wide class of spa

A comprehensive survey on oceanography parameters for developing ocean wave displacement prediction system - *Best Paper

Journal

Journal NameJournal of Chemical and Pharmaceutical Sciences

Title of Paper A comprehensive survey on oceanography parameters for developing ocean wave displacement prediction system - *Best Paper

PublisherSPB Pharma society

Volume Number8

Page Number273-278

Published YearJune 2015

ISSN/ISBN No0974-2115

Indexed INScopus

Abstract

Earth is widely covered by ocean. There are many calamities observed as a result of various unpredicted behaviour of ocean wave movements, and Landscaping under ocean along with response to weather change. These dynamic and drastic behaviours of oceans can be measured by various parameters like. The paper describes in depth learning of various concerned parameters which cover impact of par

Optimizing Parallel Scan Smith Waterman Algorithm

Conference

Title of Paper Optimizing Parallel Scan Smith Waterman Algorithm

PublisherIRAJ

Page Number86-89

Published YearSeptember 2014

ISSN/ISBN No320 - 2106

Indexed INOthers

Abstract

Smith - Waterman is a well - known local sequence alignment algorithm that is used for finding regions of maximum similarity between two biological sequences and is known to be a highly compute intensive task. As it is based on dynamic programming it guarantees optimal results. But Dynamic Programming has its own drawbacks such as hea vy memory consumption and significant amount

An Efficient Sparse Matrix Multiplication for skewed matrix on GPU

Conference

Title of PaperAn Efficient Sparse Matrix Multiplication for skewed matrix on GPU

PublisherIEEE

Year , VenueOctober 2012 , Liverpool, UK

Page Number1301-1306

ISSN/ISBN No978-1-4673-2164-8

Indexed INScopus, UGC List

Abstract

This paper presents a new sparse matrix format ALIGNED_COO, an extension to COO format to optimize performance of large sparse matrix having skewed distribution of non-zero elements. Load balancing, alignment and synchronization free distribution of work load are three important factors to improve performance of sparse matrices representing power-law graph. Coordinate (COO) format is selected for

PROS - An Omnipresent Operating System

Journal

Journal NameInternational Journal of Recent Trends in Engineering

Title of PaperPROS - An Omnipresent Operating System

PublisherInternational Journal of Recent Trends in Engineering

Volume Number1

Page Number144-148

Published YearMay 2009

ISSN/ISBN No1797-9617

Indexed INOthers

Abstract

The central idea presented in this paper is to show the architecture and working of an Operating System running over the network, thus leading to global computing. "PROS", as it is named, provides transparency meaning it would work same as a real operating system on the PC without need of static installation. PROS would load up on the user's PC irrespective of the location along with user’s

Design and Analysis of Low-Power High-Speed Shared Charge Reset Technique based Dynamic Latch Comparator

Journal

Journal NameMicroelectronics Journal, Elsevier Journals

Title of PaperDesign and Analysis of Low-Power High-Speed Shared Charge Reset Technique based Dynamic Latch Comparator

PublisherElsevier

Volume Number74

Page Number116-126

Published YearApril 2018

ISSN/ISBN No2226-2692

Indexed INScopus

Abstract

Circuit intricacy, high-speed, low-power, small area requirement, and high resolution are crucial factors for high-speed and low-power applications like analog-to-digital converters (ADCs). The delay analysis of classical dynamic latch comparators is presented to add more insight of their design parameters, which effects the performance parameter. In this research, a new architecture of dynamic latch comparator is presented, which is able to provide high-speed, consumes low-power and requires smaller die area. The proposed comparator benefits from a new shared charge logic based reset technique to achieve high-speed with low-power consumption. It is shown by simulation and analysis that the delay time is significantly reduced compared to a conventional dynamic latched comparator. The proposed circuit is designed and simulated in 90 nm CMOS technology. The results show that, for the proposed comparator, the delay is 51.7 ps and consumes only 33.62  μW power, at 1 V supply voltage and 1 GHz clock frequency. In addition, the proposed dynamic latch comparator has a layout size of 7.2μm × 8.1μm.

Scalable Edge Computing Environment Based on the Containerized Microservices and Minikube

Journal

Journal NameInternational Journal of Software Science and Computational Intelligence (IJSSCI)

Title of PaperScalable Edge Computing Environment Based on the Containerized Microservices and Minikube

PublisherIGI Global

Volume Number14

Page Number1-14

Published YearOctober 2022

ISSN/ISBN No1942-9045

Indexed INWeb of Science

Abstract

The growing number of connected IoT devices and their continuous data collection will generate huge amounts of data in the near future. Edge computing has emerged as a new paradigm in recent years for reducing network congestion and offering real-time IoT applications. Processing the large amount of data generated by such IoT devices requires the development of a scalable edge computing environment. Accordingly, applications deployed in an edge computing environment need to be scalable enough to handle the enormous amount of data generated by IoT devices. The performance of MSA and monolithic architecture is analyzed and compared to develop a scalable edge computing environment. An auto-scaling approach is described to handle multiple concurrent requests at runtime. Minikube is used to perform auto-scaling operation of containerized microservices on resource constraint edge node. Considering performance of both the architecture and according to the results and discussions, MSA is a better choice for building scalable edge computing environment.

Evaluating the Performance of Monolithic and Microservices Architectures in an Edge Computing Environment

Journal

Journal NameInternational Journal of Fog Computing (IJFC)

Title of Paper Evaluating the Performance of Monolithic and Microservices Architectures in an Edge Computing Environment

PublisherIGI Global

Volume Number5

Page Number1-18

Published YearSeptember 2022

ISSN/ISBN No2572-4908

Indexed INOthers

Abstract

Edge computing has become a popular paradigm in recent years for reducing network congestion and serving real-time IoT applications by providing services close to end-user devices. It is difficult to develop applications in an edge computing environment due to resource constraints and the diverse and distributed nature of edge computing nodes. The authors compared the performance of monolithic architecture and MicroServices Architecture (MSA) in edge computing environments to determine which architecture can better meet the diverse requirements imposed by edge computing environments. A single application has been developed using both MSA and monolithic architecture for water requirement prediction for irrigation in rice crop. In terms of peak throughput, MSA outperformed monolithic architecture by about 22%, and similarly for peak response times, MSA outperformed monolithic architecture by about 28%. The average CPU usage of MSA is about 49.26% less than the monolithic architecture.

Integration of Edge Computing and Deep Convolutional Neural Network for Potato Plant Diseases Detection in Real-Time

Book Chapter

Book NameChanging Perspectives of Research with Higher Education 4.0: Challenges and Opportunities

PublisherALLIED PUBLISHERS PVT. LTD.

Author NameNitin Rathore, Anand Rajavat

Page Number118-129

Chapter TitleIntegration of Edge Computing and Deep Convolutional Neural Network for Potato Plant Diseases Detection in Real-Time

Published YearMarch 2021

ISSN/ISBN No978-93-87997-53-0

Indexed INOthers

Abstract

Agriculture is the basic foundation of any nation’s economy in the world. By 2050, the world needs to enhance food production to about 70% to feed an estimated overall population of over 9 billion people. Potato is consumed worldwide and its production plays an important part in agriculture. Early blight and late blight are the two main diseases that affect potato crop production severely. In order to detect these diseases in real time AlexNet, MobileNet and VGG16 three deep convolutional neural networks (CNN) were explored. All 3 CNN models were trained on cloud with a dataset of 7128 images containing healthy and diseased leaves images of potato plants. Even if training is outsourced, trained models still require a large size of RAM, so the prime goal of this work was to identify lightweight CNN that can be fitted into resource constrained devices easily. In this study lightweight deep CNN were identified and deployed at the edge node to detect diseases in real time by utilizing leaf images captured by camera devices in-place to enhance potato crop productivity and reduce economic losses. The advantage of the proposed approach is that by classifying potato leaf images in real time on-premises, there is no need to send images to the cloud, which unnecessarily increases network congestion, for possible disease detection. Results show that the identified lightweight CNN model obtained 99.87% accuracy for both train and test images and require only 22.5 MB memory. Precision, recall (sensitivity) and F1 score were also presented to visualise the model’s performance.

Investigations of Microservices Architecture in Edge Computing Environment

Book Chapter

Book NameSocial Networking and Computational Intelligence

PublisherSpringer

Author NameNitin Rathore, Anand Rajavat and Margi Patel

Page Number77-84

Chapter TitleInvestigations of Microservices Architecture in Edge Computing Environment

Published YearMarch 2020

ISSN/ISBN No978-981-15-2070-9

Indexed INScopus

Abstract

Purpose of Internet of Thing (IoT) is to carry each entity on the web, consequently creating tremendous measure of information that can crush network data transfer capacity. To provide cloud services in boundary of end user edge computing turned into promising fashion, to conquer such problem, from centralized computation to decentralized computation. Over the last one decade the advancement of Internet services has constrained outlook changes in the course of the monolithic architectures to Service Oriented Architecture (SOA) and thusly from SOA to microservices. So in this paper we will try to investigate the suitability of microservices architecture style in edge computing environment and determine some similarities in the goals of microservices architecture style and edge computing environment.

Detection and prevention mechanism for TTL field tampering form of DDoS attack in MANET’s

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperDetection and prevention mechanism for TTL field tampering form of DDoS attack in MANET’s

PublisherFoundation of Computer Science

Volume Number975

Published YearJanuary 2015

ISSN/ISBN No2348-2281

Indexed INOthers

Review on Basic Clustering Techniques for Heterogeneous Wireless Sensor Networks

Journal

Journal NameInternational Journal of Scientific and Research Publications

Title of PaperReview on Basic Clustering Techniques for Heterogeneous Wireless Sensor Networks

Volume Number4

Page Number1-4

Published YearAugust 2014

ISSN/ISBN No2250-3153

Indexed INOthers

Smart Farming Based on IoT Edge Computing: Applying Machine Learning Models for Disease and Irrigation Water Requirement Prediction in Potato Crop Using Containerized Microservices

Book Chapter

Book NamePrecision Agriculture for Sustainability Use of Smart Sensors, Actuators, and Decision Support Systems

PublisherApple Academic and CRC Press

Author NameNitin Rathore, Anand Rajavat

Chapter TitleSmart Farming Based on IoT Edge Computing: Applying Machine Learning Models for Disease and Irrigation Water Requirement Prediction in Potato Crop Using Containerized Microservices

Published YearJuly 2023 (forthcoming)

ISSN/ISBN No971774913734

Indexed INScopus, Web of Science

Do digital images tell the truth?

Book Chapter

Book NameDigital Image Security

PublisherCRC Press

Author NameA Bruno, P Oza, F Adedoyin, M Tliba, MA Kerkouri, A Sekhri, A Chetouani, M Gao

Page Number247-265

Chapter TitleDo digital images tell the truth?

Published YearMarch 2024

Indexed INScopus, Web of Science

Digital mammography dataset for breast cancer diagnosis research (DMID) with breast mass segmentation analysis

Journal

Journal NameBiomedical Engineering Letters

Title of PaperDigital mammography dataset for breast cancer diagnosis research (DMID) with breast mass segmentation analysis

PublisherSpringer

Volume Number14

Page Number317-330

Published YearMarch 2024

ISSN/ISBN No2093-9868

Indexed INScopus, Web of Science

Exploring the Benefits of Data Augmentation for Breast Cancer Classification using Transfer Learning

Book Chapter

Book NameWorld Conference on Information Systems for Business Management

PublisherSpringer Nature Singapore

Author NameAaditya Darakh, Aditya Shah, Parita Oza

Page Number509-520

Chapter TitleExploring the Benefits of Data Augmentation for Breast Cancer Classification using Transfer Learning

Published YearFebruary 2024

Indexed INScopus, Web of Science

Breast lesion classification from mammograms using deep neural network and test-time augmentation

Journal

Journal Name2024/2 Journal Neural Computing and Applications

Title of PaperBreast lesion classification from mammograms using deep neural network and test-time augmentation

PublisherSpringer

Volume Number36

Page Number2101-2117

Published YearFebruary 2024

Indexed INScopus, Web of Science

AI in breast imaging: Applications, challenges, and future research

Book Chapter

Book NameComputational intelligence and modelling techniques for disease detection in mammogram images

PublisherAcademic Press

Author NameParita Oza

Page Number39-54

Chapter TitleAI in breast imaging: Applications, challenges, and future research

Published YearJanuary 2024

Indexed INScopus, Web of Science

Social Distance Detection using Customized YOLOv4 (SDDYv4) Model

Journal

Journal NameInternational Journal of Computing and Digital Systems

Title of PaperSocial Distance Detection using Customized YOLOv4 (SDDYv4) Model

PublisherUniversity of Bahrain

Volume Number14

Page Number10481-10489

Published YearDecember 2023

Indexed INScopus

Evaluating the Igraph Community Detection Algorithms on Different Real Networks

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperEvaluating the Igraph Community Detection Algorithms on Different Real Networks

Volume Number24

Published YearJuly 2023

Indexed INScopus, Web of Science

Selection of best machine learning model to predict delay in passenger airlines

Journal

Journal NameIEEE Access

Title of PaperSelection of best machine learning model to predict delay in passenger airlines

Published YearJuly 2023

Indexed INScopus, Web of Science

Patch Extraction and Classifier for Abnormality Classification in Mammography Imaging

Book Chapter

Book NameLecture Notes in Networks and Systems , Third Congress on Intelligent Systems: Proceedings of CIS 2022

PublisherSpringer

Author NameParita Oza, Paawan Sharma, Samir Patel

Page Number1-9

Chapter TitlePatch Extraction and Classifier for Abnormality Classification in Mammography Imaging

Published YearMay 2023

ISSN/ISBN No978-981-19-9379-4

Indexed INScopus

Artificial Intelligence and Graph Theory Application for Diagnosis of Neurological Disorder Using fMRI

Book Chapter

Book NameLecture Notes in Electrical Engineering, Proceedings of International Conference on Recent Innovations in Computing: ICRIC 2022

PublisherSpringer

Author NameBansari Prajapati, Parita Oza, Smita Agrawal

Page Number41-56

Chapter TitleArtificial Intelligence and Graph Theory Application for Diagnosis of Neurological Disorder Using fMRI

Published YearMay 2023

ISSN/ISBN No978-981-19-9876-8

Indexed INScopus

CoviDistBand: IoT-Based Wearable Smart Band to Ensure Social Distancing

Book Chapter

Book NameRenewable Energy Optimization, Planning and Control: Proceedings of ICRTE 2022

PublisherSpringer

Author NameVraj Bhatt, Jaimin Topiwala, Smita Agrawal, Parita Oza

Page Number71-79

Chapter TitleCoviDistBand: IoT-Based Wearable Smart Band to Ensure Social Distancing

Published YearMarch 2023

ISSN/ISBN No978-981-19-8963-6

Data Encryption Approach Using Hybrid Cryptography and Steganography with Combination of Block Ciphers

Book Chapter

Book NameAdvancements in Smart Computing and Information Security

PublisherSpringer Nature

Author NameHet Shah, Parita Oza, Smita Agrawal

Page Number59-69

Chapter TitleData Encryption Approach Using Hybrid Cryptography and Steganography with Combination of Block Ciphers

Published YearJanuary 2023

Indexed INScopus

Sentiment Analysis of Customer Feedback and Reviews for Airline Services using Language Representation Model

Journal

Journal NameProcedia Computer Science

Title of PaperSentiment Analysis of Customer Feedback and Reviews for Airline Services using Language Representation Model

PublisherElsevier

Volume Number218

Page Number2459-2467

Published YearJanuary 2023

Indexed INScopus

Deep ensemble transfer learning-based framework for mammographic image classification

Journal

Journal NameThe Journal of Supercomputing

Title of PaperDeep ensemble transfer learning-based framework for mammographic image classification

PublisherSpringer

Published YearDecember 2022

Indexed INScopus, Web of Science

Transfer Learning Assisted Classification of Artefacts Removed and Contrast Improved Digital Mammograms

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperTransfer Learning Assisted Classification of Artefacts Removed and Contrast Improved Digital Mammograms

Volume Number23

Page Number115-127

Published YearOctober 2022

Indexed INScopus

Computer-Aided Breast Cancer Diagnosis: A Comparative Analysis of Breast Imaging Modalities and Mammogram Repositories.

Journal

Journal NameCurrent Medical Imaging

Title of PaperComputer-Aided Breast Cancer Diagnosis: A Comparative Analysis of Breast Imaging Modalities and Mammogram Repositories.

PublisherBentham Science Publishers

Volume Number19

Page Number456 - 468

Published YearAugust 2022

Indexed INScopus, Web of Science

A Transfer Representation Learning Approach for Breast Cancer Diagnosis from Mammograms using EfficientNet Models

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperA Transfer Representation Learning Approach for Breast Cancer Diagnosis from Mammograms using EfficientNet Models

Volume Number23

Page Number51-58

Published YearAugust 2022

Indexed INScopus

A Secure DBA Management System: A Comprehensive Study

Book Chapter

Book NameLecture Notes in Networks and Systems (Proceedings of Third International Conference on Computing, Communications, and Cyber-Security.)

PublisherSpringer

Author NameParita Oza

Chapter TitleA Secure DBA Management System: A Comprehensive Study

Published YearJuly 2022

Indexed INScopus

Concurrency Control in Distributed Database Systems: An In-Depth Analysis

Book Chapter

Book NameLecture Notes in Networks and Systems

PublisherSpringer

Author NameParita Oza

Chapter TitleConcurrency Control in Distributed Database Systems: An In-Depth Analysis

Published YearJuly 2022

Indexed INScopus

Towards automating irrigation: a fuzzy logic-based water irrigation system using IoT and deep learning

Journal

Journal NameModeling Earth Systems and Environment

Title of PaperTowards automating irrigation: a fuzzy logic-based water irrigation system using IoT and deep learning

Published YearJuly 2022

ISSN/ISBN No2363-6203

Indexed INScopus

Image Augmentation Techniques for Mammogram Analysis

Journal

Journal NameJournal of Imaging

Title of PaperImage Augmentation Techniques for Mammogram Analysis

PublisherMDPI

Volume Number8

Published YearMay 2022

ISSN/ISBN No2313-433X

Indexed INScopus, PubMed, Web of Science

Deep convolutional neural networks for computer-aided breast cancer diagnostic: a survey

Journal

Journal NameNeural Computing and Applications

Title of PaperDeep convolutional neural networks for computer-aided breast cancer diagnostic: a survey

PublisherSpringer London

Published YearNovember 2021

Indexed INScopus, Web of Science

Enhanced Secure ATM authentication using NFC Technology and Iris Verification

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperEnhanced Secure ATM authentication using NFC Technology and Iris Verification

Volume Number22

Page Number273-282

Published YearSeptember 2021

Indexed INScopus

A bottom-up review of image analysis methods for suspicious region detection in mammograms

Journal

Journal NameJournal of Imaging

Title of PaperA bottom-up review of image analysis methods for suspicious region detection in mammograms

Volume Number7

Published YearSeptember 2021

ISSN/ISBN No2313-433X

Indexed INScopus, Web of Science

A Comprehensive Study of Mammogram Classification Techniques

Book Chapter

Book NameTracking and Preventing Diseases with Artificial Intelligence

PublisherSpringer, Cham

Page Number217-238

Chapter TitleA Comprehensive Study of Mammogram Classification Techniques

Published YearJuly 2021

Indexed INScopus

Machine learning applications for computer-aided medical diagnostics

Book Chapter

Book NameLecture Notes in Networks and Systems (Proceedings of Second International Conference on Computing, Communications, and Cyber-Security)

PublisherSpringer, Singapore

Author NameParita Oza, Paawan Sharma, Samir Patel

Page Number377-392

Chapter TitleMachine learning applications for computer-aided medical diagnostics

Published YearMay 2021

ISSN/ISBN No978-981-16-0733-2

Indexed INScopus

Diabetes prediction using machine learning

Book Chapter

Book NameLecture Notes in Networks and Systems (Proceedings of Second International Conference on Computing, Communications, and Cyber-Security)

PublisherSpringer, Singapore

Author NameHarsh Patel, Parita Oza, Smita Agrawal

Page Number703-715

Chapter TitleDiabetes prediction using machine learning

Published YearMay 2021

Indexed INScopus

A drive through computer-aided diagnosis of breast cancer: a comprehensive study of clinical and technical aspects

Book Chapter

Book NameRecent Innovations in Computing

PublisherSpringer

Author NameParita Oza, Paawan Sharma, Samir Patel

Page Number233-249

Chapter TitleA drive through computer-aided diagnosis of breast cancer: a comprehensive study of clinical and technical aspects

Published YearMarch 2021

Indexed INScopus

AI Approaches for Breast Cancer Diagnosis: A Comprehensive Study

Conference

Title of PaperAI Approaches for Breast Cancer Diagnosis: A Comprehensive Study

Proceeding NameProceedings of International Conference on Innovative Computing and Communications

PublisherSpringer, Singapore

Author NameHarsh Patel, Parita Oza, Smita Agrawal

Year , VenueFebruary 2021 , Delhi

Page Number393-419

Indexed INScopus

Review of machine learning techniques in health care

Book Chapter

Book NameLecture Notes in Electrical Engineering (Proceedings of ICRIC 2019)

PublisherSpringer, Cham

Page Number103-111

Chapter TitleReview of machine learning techniques in health care

Published YearNovember 2019

ISSN/ISBN No978-3-030-29407-6

Indexed INScopus

Homomorphic Cryptography and Its Applications in Various Domains

Book Chapter

Book NameLecture Notes in Networks and Systems

PublisherSpringer

Page Number269-278

Chapter TitleHomomorphic Cryptography and Its Applications in Various Domains

Published YearNovember 2018

ISSN/ISBN No978-981-13-2324-9

Indexed INScopus

Encryption Algorithm using Rubik’s Cube Principle for Secure Transmission of Multimedia Files

Conference

Title of PaperEncryption Algorithm using Rubik’s Cube Principle for Secure Transmission of Multimedia Files

Proceeding Name3ICMRP2016Conferenceproceeding

PublisherResearch and Scientific Innovation Society

Year , VenueDecember 2016 , AMA, IIM-A Road, Ahmedabad

Page Number239-243

Indexed INOthers

Wearable live streaming gadget using Raspberry pi

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperWearable live streaming gadget using Raspberry pi

Volume Number7

Page Number69-75

Published YearMarch 2016

ISSN/ISBN No0973-7391

Indexed INUGC List

Performance Evaluation of Unicast and Multicast Routing in Wireless Ad-hoc Networks

Conference

Title of PaperPerformance Evaluation of Unicast and Multicast Routing in Wireless Ad-hoc Networks

Proceeding NameICCCCIT 2015 conference proceeding

OrganizationTECHNICAL RESEARCH ORGANISATION INDIA

Year , VenueJuly 2015 , Bhopal

Page Number1-3

ISSN/ISBN No978-93-85225-37-6

Indexed INOthers

Tracking Cancer Patients Medical History Using Wireless Emerging Technology: Near Field Communication

Journal

Journal NameInternational Journal of VLSI design & Communication Systems (VLSICS)

Title of PaperTracking Cancer Patients Medical History Using Wireless Emerging Technology: Near Field Communication

Volume Number6

Published YearFebruary 2015

ISSN/ISBN No0976 - 1527

Indexed INEBSCO

Performance Evaluation of Ad-Hoc on-Demand Distance Vector Routing Protocol and its Multi-Path Variant AOMDV

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperPerformance Evaluation of Ad-Hoc on-Demand Distance Vector Routing Protocol and its Multi-Path Variant AOMDV

Volume Number5

Page Number51-53

Published YearMarch 2014

ISSN/ISBN No0973-7391

Indexed INUGC List

Optimized Data Aggregation Protocol in WSN for Automation of water Sprinklers

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperOptimized Data Aggregation Protocol in WSN for Automation of water Sprinklers

Volume Number5

Page Number46-50

Published YearMarch 2014

ISSN/ISBN No0973-7391

Indexed INUGC List

A Comparative Study on MANET Routing Protocols

Journal

Journal NameInternational Journal of Computer Science and Technology

Title of PaperA Comparative Study on MANET Routing Protocols

Volume Number3

Page Number821-832

Published YearJuly 2012

ISSN/ISBN No0976-8491

Indexed INOthers

Toward the internet of things forensics: A data analytics perspective

Journal

Journal NameSecurity and Privacy

Title of PaperToward the internet of things forensics: A data analytics perspective

PublisherWiley Periodicals, Inc.

Volume Numbere306

Published YearMarch 2023

ISSN/ISBN No2475-6725

Indexed INWeb of Science, Others

The Evolution of Ad Hoc Networks for Tactical Military Communications: Trends, Technologies, and Case Studies

Conference

Title of PaperThe Evolution of Ad Hoc Networks for Tactical Military Communications: Trends, Technologies, and Case Studies

Proceeding NameProceedings of Third International Conference on Sustainable Expert Systems

PublisherSpringer, Singapore

Author NameZalak Patel, Pimal Khanpara, Sharada Valiveti & Gaurang Raval

Page Number331-346

Published YearFebruary 2023

ISSN/ISBN No2367-3389

Indexed INScopus, Others

Image-based Seat Belt Fastness Detection using Deep Learning

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperImage-based Seat Belt Fastness Detection using Deep Learning

Volume Number23

Page Number441-455

Published YearDecember 2022

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science, EBSCO

A context‐aware internet of things‐driven security scheme for smart homes

Journal

Journal NameSecurity and Privacy

Title of PaperA context‐aware internet of things‐driven security scheme for smart homes

PublisherWiley Periodicals, Inc.

Volume Numbere269

Published YearSeptember 2022

ISSN/ISBN No2475-6725

Indexed INWeb of Science

Graph Neural Network based Recommender System

Conference

Title of PaperGraph Neural Network based Recommender System

Proceeding NameProceedings of the Seventh International Conference on Communication and Electronics Systems (ICCES 2022)

PublisherIEEE

Author NameRachana Mehta, Kruti Lavingia, Pimal Khanpara, Vijay Dhulera

Page Number1377-1381

Published YearJune 2022

ISSN/ISBN No 978-1-6654-9634-6

Indexed INScopus

Blockchain-based E-Voting Technology: Opportunities and Challenges

Conference

Title of PaperBlockchain-based E-Voting Technology: Opportunities and Challenges

Proceeding NameProceedings of the Seventh International Conference on Communication and Electronics Systems (ICCES 2022)

PublisherIEEE

Author NamePimal Khanpara, Shivam Patel, Sharada Valiveti

Page Number855-861

Published YearJune 2022

ISSN/ISBN No 978-1-6654-9634-6

Indexed INScopus

Predicting Stock Market Trends using Random Forest: A Comparative Analysis

Conference

Title of PaperPredicting Stock Market Trends using Random Forest: A Comparative Analysis

Proceeding NameProceedings of the Seventh International Conference on Communication and Electronics Systems (ICCES 2022)

PublisherIEEE

Author NameKruti Lavingia, Pimal Khanpara, Rachana Mehta, Niket Kothari, Karan Parekh

Page Number1544-1550

Published YearJune 2022

ISSN/ISBN No978-1-6654-9634-6

Indexed INScopus

Robust and secure routing protocols for MANET-based internet of things systems—A survey

Book Chapter

Book NameEmergence of Cyber Physical System and IoT in Smart Automation and Robotics

PublisherSpringer

Author NameRajvi Trivedi, Pimal Khanpara

Page Number175-188

Chapter TitleRobust and secure routing protocols for MANET-based internet of things systems—A survey

Published YearMay 2021

ISSN/ISBN No978-3-030-66222-6

Indexed INScopus

Blockchain for industry 4.0: A comprehensive review

Journal

Journal NameIEEE Access

Title of PaperBlockchain for industry 4.0: A comprehensive review

PublisherIEEE

Volume Number8

Page Number79764-79800

Published YearApril 2020

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science, EBSCO

Abstract

Due to the proliferation of ICT during the last few decades, there is an exponential increase in the usage of various smart applications such as smart farming, smart healthcare, supply-chain & logistics, business, tourism and hospitality, energy management etc. However, for all the aforementioned applications, security and privacy are major concerns keeping in view of the usage of the open channel, i.e., Internet for data transfer. Although many security solutions and standards have been proposed over the years to enhance the security levels of aforementioned smart applications, but the existing solutions are either based upon the centralized architecture (having single point of failure) or having high computation and communication costs. Moreover, most of the existing security solutions have focussed only on few aspects and fail to address scalability, robustness, data storage, network latency, auditability, immutability, and traceability. To handle the aforementioned issues, blockchain technology can be one of the solutions. Motivated from these facts, in this paper, we present a systematic review of various blockchain-based solutions and their applicability in various Industry 4.0-based applications. Our contributions in this paper are in four fold. Firstly, we explored the current state-of-the-art solutions in the blockchain technology for the smart applications. Then, we illustrated the reference architecture used for the blockchain applicability in various Industry 4.0 applications. Then, merits and demerits of the traditional security solutions are also discussed in comparison to their countermeasures. Finally, we provided a comparison of existing blockchain-based security solutions using various parameters to provide deep insights to the readers about its applicability in various applications.

Additive manufacturing: concepts and technologies

Book Chapter

Book NameA Roadmap to Industry 4.0: Smart Production, Sharp Business and Sustainable Development

PublisherSpringer

Author NamePimal Khanpara, Sudeep Tanwar

Page Number171-185

Chapter TitleAdditive manufacturing: concepts and technologies

Published YearNovember 2019

ISSN/ISBN No978-3-030-14544-6

Indexed INScopus

Energy conservation in multimedia big data computing and the Internet of Things—A challenge

Book Chapter

Book NameMultimedia Big Data Computing for IoT Applications

PublisherSpringer

Author NamePimal Khanpara, Kruti Lavingia

Page Number37-57

Chapter TitleEnergy conservation in multimedia big data computing and the Internet of Things—A challenge

Published YearJuly 2019

ISSN/ISBN No978-981-13-8759-3

Indexed INScopus

A Survey on Security Issues in MANETs

Conference

Title of PaperA Survey on Security Issues in MANETs

OrganizationAET

Year , VenueJune 2018 , Mumbai

Survivability in MANETs

Journal

Journal NameInternational Journal of Advanced Research in Computer Engineering & Technology

Title of PaperSurvivability in MANETs

PublisherIJARCET

Volume Number7

Page Number7-10

Published YearJanuary 2018

Indexed INUGC List

Survey of Techniques Used for Tolerance of Flooding Attacks in DTN

Book Chapter

Book NameInformation and Communication Technology for Intelligent Systems

PublisherSpringer, Singapore

Page Number599-607

Chapter TitleSurvey of Techniques Used for Tolerance of Flooding Attacks in DTN

Published YearJanuary 2018

ISSN/ISBN No978-981-13-1742-2

Indexed INScopus, UGC List

Security in Mobile Ad Hoc Networks

Book Chapter

Book NameProceedings of International Conference on Communication and Networks

PublisherSpringer, Singapore

Author NamePimal Khanpara, Bhushan Trivedi

Page Number501-511

Chapter TitleSecurity in Mobile Ad Hoc Networks

Published YearApril 2017

ISSN/ISBN No978-981-10-2750-5

Indexed INScopus, UGC List

Abstract

Due to the proliferation of mobile devices, Mobile Ad hoc Networks (MANETs) are increasing in popularity. However, security of such networks is an important issue as MANETs are vulnerable to various attacks occurring at different layers of TCP/IP protocol suite. This paper focuses on the Network layer vulnerabilities as this layer is responsible for one of the basic MANET functions, routing.

A REVIEW ON FUZZY LOGIC BASED ROUTING IN AD HOC NETWORKS

Journal

Journal NameInternational Journal of Advanced Research in Engineering and Technology

Title of PaperA REVIEW ON FUZZY LOGIC BASED ROUTING IN AD HOC NETWORKS

PublisherIAEME

Volume Number5

Page Number75-81

Published YearMay 2014

Indexed INOthers

Routing in Ad Hoc Network Using Ant Colony Optimization

Book Chapter

Book NameCommunication and Networking

PublisherSpringer, Berlin, Heidelberg

Page Number393-404

Chapter TitleRouting in Ad Hoc Network Using Ant Colony Optimization

Published YearMarch 2011

ISSN/ISBN No978-3-642-17604-3

Indexed INScopus, UGC List

Abstract

The ad hoc networks have a dynamic topology and are infrastructure less. So it is required to implement a new network protocol for providing an efficient end to end communication based on TCP/IP structure. There is a need to re-define or modify the functions of each layer of TCP/IP model to provide end to end communication between nodes.

Machine Learning Based Approach for Traffic Rule Violation Detection

Conference

Title of PaperMachine Learning Based Approach for Traffic Rule Violation Detection

Proceeding NameIEEE 7th International Conference on Recent Advances and Innovations in Engineering (ICRAIE)

PublisherIEEE Xplore

Author NameK. Lavingia, M. Vaja, P. Chaturvedi and A. Lavingia

OrganizationNational Institute of Technology Surathkal

Year , VenueDecember 2022 , Surathkal

Page Number244-249

ISSN/ISBN No978-1-6654-8910-2

Indexed INScopus

Abstract

The goal of this paper is to design an automated system model to monitor the violation of traffic rules, specifically the number of people sitting on a two-wheeler. Typically, in areas near the security offices, people tend to follow the rules, but in areas where no one is watching, people violate the rules. In our case of an organizational campus, if there are three people traveling on a two-wheeler but when they encounter a security guard, one of the persons gets down and walks ahead of the guarded area and then again sits back on the vehicle. In such cases, efficient methods are required to monitor the violation of specified traffic rules without human intervention. For the above-mentioned challenge, a deep learning-based solution is provided where the process starts with object recognition using YOLOv3 (You Only Look Once) model, using which a person sitting on any particular vehicle is identified based on a minimum threshold distance. Also, for the distance calculation, a depth estimation algorithm which helps us in finding the 3-D distance between objects from a 2-D image is implemented. Moreover, the number plate of the vehicle violating the above-mentioned rule is identified for easy identification of the person violating the rule. The proposed approach is implemented on a real time video streaming dataset. The simulation results show the efficiency of the proposed approach in terms of accuracy, precision and recall as 91%, 86% and 94% respectively.

A Deep Learning Based Target Coverage Protocol for Edge Computing Enabled Wireless Sensor Networks

Book Chapter

Book NameExplainable Edge AI: A Futuristic Computing Perspective

PublisherSpringer

Author NamePooja Chaturvedi, AK Daniel, Umesh Bodkhe

Page Number161-181

Chapter TitleA Deep Learning Based Target Coverage Protocol for Edge Computing Enabled Wireless Sensor Networks

Published YearNovember 2022

ISSN/ISBN No978-3-031-18292-1

Indexed INScopus, EBSCO

Abstract

The sensor networks have attracted a numerous research attention due to its diverse applications ranging from surveillance and monitoring applications. The sensor nodes are usually characterized as having scarce resources; hence energy efficient mechanisms which can enhance the resource utilization are of great significance. The integration of edge computing framework with the sensor network can aid in the data collection, dissemination and decision making. Scheduling approaches which divide the nodes into a number of set covers and monitor the given points of interest with the desired confidence level along with the objective of maximizing coverage and network lifetime have been proved a prominent approach. The determination of set covers is a NP hard problem and is dependent on different network parameters such as node contribution, trust values and coverage probability. In this scheme, the node has to monitor the neighboring node parameters at regular intervals, which incurs a huge number of communication overhead. The nodes in sensor network can employ the learning strategy to determine its best possible action to enhance the network coverage as well as network lifetime. The chapter proposes a LSTM based strategy for an edge computing enabled WSN to determine the status of the node depending on the network parameters such as number of communications, number of packets transmitted and initial energy of the nodes. The proposed protocol is implemented using tensor flow and keras libraries in the python language. The keras tuner package has been used to determine the best parameters such as number of hidden layers and number of neurons in each layer. The obtained parameters are used to construct a hyper model and the efficiency of the model is evaluated in terms of the loss function. The explainability of the proposed model is investigated using the Local Interpretable Model-agnostic Explanations (LIME) framework and the effect of all the features on the status prediction have been determined.

Neural Network Based Forecasting Technique for Wireless Sensor Networks

Journal

Journal NameNeural Processing Letters

Title of PaperNeural Network Based Forecasting Technique for Wireless Sensor Networks

PublisherSpringer

Page Number1-17

Published YearJune 2022

ISSN/ISBN No1573-773X

Indexed INScopus, Web of Science, EBSCO

Abstract

The diversified and huge applicability of sensor networks has attracted the researchers in this field. The nodes in the sensor networks are distinguished by the scarce resources; hence energy conservation approaches are of great significance. The node scheduling approaches aims to schedule the nodes in a number of set covers, which can be activated periodically to monitor the given points of interest with the desired confidence level along with the objective of maximizing coverage and network lifetime. The determination of set covers is considered as a NP hard problem and is dependent on different network parameters such as node contribution, trust values and coverage probability.. The main motivation of the proposed approach is to reduce this complexity by employing the prediction technique based on learning through neural network. The paper presents the neural network based prediction model to determine the activation status of the nodes in the set cover. In this scheme, the node has to monitor the neighboring node parameters at regular intervals, which incurs a huge number of communications and overhead. The data prediction technique can reduce this overhead by autonomously determining the node activation status. The paper proposes a neural network-based prediction technique for sensor networks in combination with the node scheduling strategy. The different node parameters are provided as input to train the network for prediction of node status. The performance of the different prediction models have been evaluated in terms of precision, recall, f1 score and accuracy for the training and test datasets. The binary cross entropy-based loss function is analyzed in training the neural networks. The accuracy of the model is evaluated for the validation split size as 20%. The simulation results show that the accuracy in the prediction of the node status is maximum for the NAdam based optimizer i.e. 87% and 76% for the training and the testing dataset respectively.

A Comprehensive Review on Scheduling Based Approaches for Target Coverage in WSN

Journal

Journal NameWireless Personal Communications

Title of PaperA Comprehensive Review on Scheduling Based Approaches for Target Coverage in WSN

PublisherSpringer

Page Number1-53

Published YearOctober 2021

ISSN/ISBN No1572-834X

Indexed INScopus, Web of Science, EBSCO

Abstract

Wireless sensor network (WSN) is an emerging research field in recent years. The advancement in sensory device and communication technologies has enabled the deployment of diverse sensor networks such as random network consisting of thousand sensors or carefully deployed deterministic network. Despite the plethora of applicability of sensor networks, there are some limitations too such as energy efficiency, lifetime, coverage, localization etc. As the sensor nodes are battery driven so conservation of energy becomes crucial in the hazardous applications. Coverage is also considered as the major quality of service (QoS) metric which aim to maximize the observation quality of the target region. Several approaches have been proposed in the literature to address the coverage problem but most of the approaches have the same objective to achieve the maximum lifetime while ignoring the QoS parameters. The real world applications of WSN require addressing of several QoS parameters too such as reliability, throughput, delay in packet transmission etc. This review paper provides the exhaustive study of the coverage problem concepts, issues and challenges. The paper provides the classification of coverage approaches especially related to that of target coverage. The paper provides a comprehensive comparison of different categories of target coverage approaches. The paper also discusses the future research direction in the field of target coverage which also considers the QoS considerations.

A Hybrid Protocol based on Fuzzy Logic and Rough Set Theory for Target Coverage in Wireless Sensor Networks”,

Journal

Journal NameRecent Advances in Computer Science and Communications,

Title of PaperA Hybrid Protocol based on Fuzzy Logic and Rough Set Theory for Target Coverage in Wireless Sensor Networks”,

PublisherBentham

Volume Number14 2

Page Number467-476

Published YearMay 2021

ISSN/ISBN No2666-2566,

Indexed INScopus

Abstract

Background: Target coverage is considered a significant problem in the area of wireless sensor networks, which usually aims at monitoring a given set of targets with the required confidence level so that network lifetime can be enhanced while considering the constraints of the resources. Objective: To maximize the lifetime of the sensor network and minimize the overhead involved in the scheduling approach, such that the pre specified set of targets is monitored for a longer duration with the required confidence level. Methods: The paper uses a fuzzy logic system based on Mamdani inference in which the node status to remain in the active state is determined on the basis of coverage probability, trust values and node contribution. The rule set for determining the set cover is optimized by using the rough set theory, which aims to determine the node validity for the trust calculation. Results: The results show that the proposed approach improved the network performance in terms of processing time, throughput and energy conservation by a factor of 50%, 74% and 74%, respectively, as compared to the existing approaches. Conclusion: The paper proposes a scheduling strategy of the nodes for target coverage as an enhancement to the Energy Efficient Coverage Protocol (EECP) on the basis of rough set theory. The rule set for determining the set cover is optimized by using the rough set theory so that the network performance is improved in terms of the processing time, throughput and energy consumption.

A Novel Sleep/Wake Protocol for Target Coverage Based on Trust Evaluation for a Clustered Wireless Sensor Networks

Journal

Journal NameInternational Journal of Mobile Network Design and Innovation

Title of PaperA Novel Sleep/Wake Protocol for Target Coverage Based on Trust Evaluation for a Clustered Wireless Sensor Networks

PublisherInderscience

Volume Number7 3/4

Page Number199-209

Published YearJuly 2017

ISSN/ISBN No1744-2850,

Indexed INScopus

Abstract

The advancement in the field of nanotechnology and its impact on processor technology has made the wireless communication more powerful and popular. Coverage and lifetime maximisation are two major challenges. The node scheduling approaches address these problems: 1) achieving the connectivity and desired coverage while keeping the optimal nodes in active state; 2) resolving conflicts while determining the nodes to keep in sleep state; 3) finding strategies that avoid waking up redundant nodes. A node scheduling protocol for target coverage as an extension of energy efficient coverage preserving protocol (EECP), which determined the set covers based on the coverage probability and trust values is proposed. The clustering mechanism based on residual energy, distance and degree of the nodes is used for the dynamic selection of cluster heads. The simulation results show that the proposed enhancement achieves the improvement in the network performance than the disjoint set cover (DSC) approach.

A Hybrid Scheduling Protocol for Target Coverage Based on Trust Evaluation for Wireless Sensor Networks

Journal

Journal NameIAENG International Journal of Computer Science

Title of PaperA Hybrid Scheduling Protocol for Target Coverage Based on Trust Evaluation for Wireless Sensor Networks

PublisherIAENG

Volume Number44 1

Page Number87-104,

Published YearFebruary 2017

ISSN/ISBN No1819-9224

Indexed INScopus

Abstract

Coverage is an intriguing problem in the domain of wireless sensor networks for supervising and tracking applications as an indicator of quality of service (QoS). Target coverage problem pertains to maximize the network lifetime while considering the resource scarcity. The paper proposes a hybrid scheduling protocol for target coverage for wireless sensor networks which determines the number of set covers for monitoring all the targets using the probabilistic coverage model, node contribution and trust values. The optimal observation probability is obtained for the parameter values of the sensing and communication characteristics of the nodes using Analytic Hierarchy Process (AHP) and probabilistic coverage model. The proposed protocol uses a node scheduling technique using Fuzzy Logic to activate the nodes to form the set covers. The proposed protocol is validated for a smaller network and is simulated for a real large network. The simulation results show that the performance of proposed protocol improves the network efficiency in terms of coverage, network lifetime and reliability in terms of trust factor. The comparison results show that the proposed protocol improves the performance in terms of the number of set covers, network lifetime and number of active nodes compared to disjoint set cover protocol. The simulation results show that the network lifetime and performance under constant performance is improved up to 200%.

Crop classification with Hyperspectral images : A transfer learning approach

Journal

Journal NameModeling Earth Systems and Environment

Title of PaperCrop classification with Hyperspectral images : A transfer learning approach

Page Number1 to 11

Published YearNovember 2022

ISSN/ISBN NoP - 02363-6203, E- 2363-6211

Indexed INScopus, Web of Science, Others

IoT based Ambient Assisted Living Technologies for Healthcare: Concepts and Design Challenges

Conference

Title of PaperIoT based Ambient Assisted Living Technologies for Healthcare: Concepts and Design Challenges

Author NameP Purohit, P Khanpara, U Patel, P Kathiria

Page Number111-116

Published YearNovember 2022

Indexed INScopus

Document Classification using Deep Neural Network with word embedding techniques

Journal

Journal NameInt. J. of Web Engineering and Technology

Title of PaperDocument Classification using Deep Neural Network with word embedding techniques

Volume Number17

Page Number203-22

Published YearSeptember 2022

ISSN/ISBN No1476-1289

Indexed INScopus, Others

Hyperspectral Image Classification using Transfer Learning

Book Chapter

Book NameLecture Notes in Networks and Systems

Author NameUsha Patel,Preeti Kathiria, Smit Patel

Page Number545-556

Chapter TitleHyperspectral Image Classification using Transfer Learning

Published YearAugust 2022

ISSN/ISBN Noe-ISSN 2367-3389, P-ISSN 2367-3370

Indexed INScopus

Fuzzy Logic Inference-Based Automated Water Irrigation System

Journal

Journal NameInternational Journal of Ambient Computing and Intelligence (IJACI)

Title of PaperFuzzy Logic Inference-Based Automated Water Irrigation System

Volume Number13

Page Number1 to 15

Published YearJuly 2022

ISSN/ISBN No1941-6245

Indexed INScopus, Web of Science, Others

Trend analysis and forecasting of publication activities by Indian computer science researchers during the period of 2010–23

Journal

Journal NameExpert Systems -Wiley

Title of PaperTrend analysis and forecasting of publication activities by Indian computer science researchers during the period of 2010–23

Volume Number39

Page Number1 to 24

Published YearJune 2022

ISSN/ISBN No1468-0394

Indexed INScopus, Web of Science, Others

Smart Crop Recommendation System: A Machine Learning Approach for Precision Agriculture

Conference

Title of PaperSmart Crop Recommendation System: A Machine Learning Approach for Precision Agriculture

Author NamePreeti Kathiria, Usha Patel, Shriya Madhwani and Chand Sahil Mansuri

Published YearMarch 2022

Indexed INScopus, Others

NEUROMORPHIC COMPUTING: REVIEW OF ARCHITECHTURE, ISSUES,APPLICATIONS AND RESEARCH OPPORTUNITIES

Conference

Title of PaperNEUROMORPHIC COMPUTING: REVIEW OF ARCHITECHTURE, ISSUES,APPLICATIONS AND RESEARCH OPPORTUNITIES

Author NameHitesh Vora, Preeti Kathiria, Smita Agrawal , Usha Patel

Published YearJune 2021

Indexed INScopus

DRONE DEVELOPMENT AND EMBELLISHING IT INTO CROP MONITORING AND PROTECTION ALONG WITH PESTICIDE SPRAYING MECHANISM

Conference

Title of PaperDRONE DEVELOPMENT AND EMBELLISHING IT INTO CROP MONITORING AND PROTECTION ALONG WITH PESTICIDE SPRAYING MECHANISM

Author NameSmita Agrawal, Preeti Kathiria, Vishwam Rawal and Trushit Vyas

Published YearApril 2021

Indexed INScopus

Recommendation Systems based on Collaborative Filtering using Autoencoders: Issues and Opportunities

Conference

Title of PaperRecommendation Systems based on Collaborative Filtering using Autoencoders: Issues and Opportunities

Author NameRia Banerjee, Preeti Kathiria, Deepika Shukla

Published YearJune 2020

Indexed INScopus

Document Clustering based on Phrase and Single Term Similarity using Neo4j

Journal

Journal NameInternational Journal of Innovative Technology and Exploring Engineering (IJITEE)

Title of PaperDocument Clustering based on Phrase and Single Term Similarity using Neo4j

Volume Number Volume-9 Issue-3,

Page Number3188-3192

Published YearJanuary 2020

ISSN/ISBN NoISSN: 2278-3075

Indexed INScopus, Others

IoT Based Home Automation with Smart Fan and AC using NodeMCU

Book Chapter

Book NameLecture Notes in Electrical Engineering(LNEE)

Author NameRaj Desai, Abhishek Gandhi, Preeti Kathiria, Smita Agrawal and Parita Oza

Page Number197-207

Chapter TitleIoT Based Home Automation with Smart Fan and AC using NodeMCU

Published YearNovember 2019

ISSN/ISBN NoISBN- 978 3 030 29406 -9

Indexed INScopus

Smart Auditorium Automation System Based on Object Recognition

Journal

Journal NameInternational Journal of Recent Technology and Engineering (IJRTE)

Title of PaperSmart Auditorium Automation System Based on Object Recognition

Volume NumberVolume-8 issue -4

Page Number11305-11310

Published YearNovember 2019

ISSN/ISBN No2277-3878(Online)

Indexed INScopus, Others

Study of Different Document Representation Models for Finding Phrase Based Similarity.

Journal

Journal Namesmart innovation, systems and technologies - Springer

Title of PaperStudy of Different Document Representation Models for Finding Phrase Based Similarity.

Volume Number106

Page Number455-464

Published YearDecember 2018

ISSN/ISBN No21903018

Indexed INScopus

Study of Different Document Representation Models for Finding Phrase Based Similarity.

Journal

Journal Namesmart innovation, systems and technologies - Springer

Title of PaperStudy of Different Document Representation Models for Finding Phrase Based Similarity.

PublisherSpringer

Volume Number1

Page Number455-464

Published YearDecember 2018

ISSN/ISBN No21903018

Indexed INScopus, Others

Study of Various Methods Used in Reverse Engineering

Journal

Journal NameInternational Journal of Research in Electronics AND Computer Engineering

Title of PaperStudy of Various Methods Used in Reverse Engineering

Volume Number6

Page Number1457-1459

Published YearJune 2018

ISSN/ISBN No2393-9028

Indexed INOthers

IoT Based approach for Controlling Electrical Peripheral Devices of Auditorium

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperIoT Based approach for Controlling Electrical Peripheral Devices of Auditorium

Volume NumberVolume 8, No. 5,

Page Number2777-2781

Published YearJune 2017

ISSN/ISBN No0976-5697

Indexed INEBSCO, Others

Web Crawler : Review of Different Types of Web Crawler, Its Issues, Applications and Research Opportunities

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperWeb Crawler : Review of Different Types of Web Crawler, Its Issues, Applications and Research Opportunities

Volume NumberVolume 8, No. 3

Page Number1199-1202

Published YearApril 2017

ISSN/ISBN No0976-5697

Indexed INEBSCO, Others

Performance evaluation of counting words from files using OpenMP

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperPerformance evaluation of counting words from files using OpenMP

Volume NumberVolume 7 No. 1

Page Number59-63

Published YearMarch 2016

ISSN/ISBN No0973-7391

Indexed INIndian citation Index, Others

A NAIVE METHOD FOR ONTOLOGY CONSTRUCTION

Journal

Journal NameInternational Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)

Title of PaperA NAIVE METHOD FOR ONTOLOGY CONSTRUCTION

Volume NumberVol.5, No.1

Page Number53-62

Published YearFebruary 2016

ISSN/ISBN No2321–404X

Indexed INIndian citation Index, Others

A Geo-Location based Mobile Service that Dynamically Locates and Notifies the nearest Blood Donors for Blood Donation during Medical Emergencies

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperA Geo-Location based Mobile Service that Dynamically Locates and Notifies the nearest Blood Donors for Blood Donation during Medical Emergencies

Volume NumberVolume 88 – No.3

Page Number34-39

Published YearFebruary 2014

ISSN/ISBN No0975 – 8887

Indexed INEBSCO

Quantum-Inspired Clustering for Hazardous Asteroid Prediction in Quantum Machine Learning

Journal

Journal NameQuantum Machine Learning

Title of PaperQuantum-Inspired Clustering for Hazardous Asteroid Prediction in Quantum Machine Learning

PublisherSpringer

Published YearSeptember 2024

Review of Quantum Algorithms for Prediction of Hazardous Asteroid

Journal

Journal NameComputing and Artificial Intelligence

Title of PaperReview of Quantum Algorithms for Prediction of Hazardous Asteroid

PublisherAcademic Publishing

Published YearMay 2024

Securing the Future: A Comprehensive Review of Security Challenges and Solutions in Advanced Driver Assistance Systems

Journal

Journal NameIEEE Access

Title of PaperSecuring the Future: A Comprehensive Review of Security Challenges and Solutions in Advanced Driver Assistance Systems

PublisherIEEE

Volume Number12

Page Number643-678

Published YearJanuary 2024

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Scalable clustering for EO data using efficient raster representation

Journal

Journal NameMultimedia Tools and Applications

Title of PaperScalable clustering for EO data using efficient raster representation

PublisherSpringer US

Volume Number82

Page Number12303–12319

Published YearMarch 2023

ISSN/ISBN No1573-7721

Indexed INScopus

Identification of handwritten Gujarati alphanumeric script by integrating transfer learning and convolutional neural networks

Journal

Journal NameSadhana

Title of PaperIdentification of handwritten Gujarati alphanumeric script by integrating transfer learning and convolutional neural networks

PublisherSpringer India

Volume Number47

Page Number653-674

Published YearJune 2022

ISSN/ISBN No0973-7677

Indexed INScopus

Addressing Item Cold Start Problem in Collaborative Filtering-Based Recommender Systems Using Auxiliary Information

Conference

Title of PaperAddressing Item Cold Start Problem in Collaborative Filtering-Based Recommender Systems Using Auxiliary Information

Proceeding NameIOT with Smart Systems: Proceedings of ICTIS 2022, Volume 2

PublisherSpringer Nature Singapore

Author NameRonakkumar Patel, Priyank Thakkar

Year , VenueApril 2022 , Ahmedabad

Page Number133-142

ISSN/ISBN No978-981-19-3575-6

Indexed INScopus

A dynamic scenario‐driven technique for stock price prediction and trading

Journal

Journal NameJournal of Forecasting

Title of PaperA dynamic scenario‐driven technique for stock price prediction and trading

PublisherWiley

Volume Number41

Page Number653-674

Published YearApril 2022

ISSN/ISBN No1099-131X

Indexed INScopus, Web of Science

Text Summarization Approaches Under Transfer Learning and Domain Adaptation Settings—A Survey

Conference

Title of PaperText Summarization Approaches Under Transfer Learning and Domain Adaptation Settings—A Survey

Proceeding NameComputational Intelligence and Data Analytics: Proceedings of ICCIDA 2022

PublisherSpringer Nature Singapore

Author NameMeenaxi Tank, Priyank Thakkar

OrganizationVasavi College of Enginnering

Year , VenueJanuary 2022 , Hyderabad

Page Number73-88

ISSN/ISBN No978-981-19-3391-2

Indexed INScopus

Predicting stock price movement using a stack of multi-sized filter maps and convolutional neural networks

Journal

Journal NameInternational Journal of Computational Science and Engineering

Title of PaperPredicting stock price movement using a stack of multi-sized filter maps and convolutional neural networks

PublisherInderscience Publishers (IEL)

Volume Number25

Page Number22-33

Published YearJanuary 2022

ISSN/ISBN No1742-7193

Indexed INScopus, Web of Science, Others

Image Denoising with Self-adaptive Multi-UNET Valve

Conference

Title of PaperImage Denoising with Self-adaptive Multi-UNET Valve

Proceeding NameSoft Computing for Problem Solving, Advances in Intelligent Systems and Computing

PublisherSpringer

Author NameYash Thesia, Meera Suthar, Tirth Pandya, Priyank Thakkar

OrganizationIIT Indore

Year , VenueDecember 2020 , IIT Indore (Online)

Page Number647-659

ISSN/ISBN No2194-5365

Indexed INOthers

Next-generation artificial intelligence techniques for satellite data processing

Book Chapter

Book NameArtificial Intelligence Techniques for Satellite Image Analysis

PublisherSpringer, Cham

Author NameNeha Sisodiya, Nitant Dube, Priyank Thakkar

Page Number235-254

Chapter TitleNext-generation artificial intelligence techniques for satellite data processing

Published YearJanuary 2020

ISSN/ISBN No978-3-030-24178-0

Indexed INScopus

Extreme Weather Prediction Using 2-Phase Deep Learning Pipeline

Conference

Title of PaperExtreme Weather Prediction Using 2-Phase Deep Learning Pipeline

Proceeding NameComputer Vision and Image Processing, Communications in Computer and Information Science

PublisherSpringer, Singapore

Author NameVidhey Oza, Yash Thesia, Dhananjay Rasalia, Priyank Thakkar, Nitant Dube & Sanjay Garg

Year , VenueSeptember 2019 , Jaipur

Page Number266-282

ISSN/ISBN No978-981-15-4015-8

Indexed INScopus

Combining user-based and item-based collaborative filtering using machine learning

Conference

Title of PaperCombining user-based and item-based collaborative filtering using machine learning

Proceeding NameInformation and Communication Technology for Intelligent Systems, Smart Innovation, Systems and Technologies

PublisherSpringer, Singapore

Author NamePriyank Thakkar, Krunal Varma, Vijay Ukani, Sapan Mankad & Sudeep Tanwar

Year , VenueApril 2018 , Ahmedabad

Page Number173-180

ISSN/ISBN No978-981-13-1747-7

Indexed INScopus

Software Defined Network-Based Vehicular Adhoc Networks for Intelligent Transportation System: Recent Advances and Future Challenges

Conference

Title of PaperSoftware Defined Network-Based Vehicular Adhoc Networks for Intelligent Transportation System: Recent Advances and Future Challenges

Proceeding NameInternational Conference on Futuristic Trends in Network and Communication Technologies

PublisherSpringer, Singapore

Page Number325-337

Published YearFebruary 2018

Indexed INScopus

Outcome fusion-based approaches for user-based and item-based collaborative filtering

Conference

Title of PaperOutcome fusion-based approaches for user-based and item-based collaborative filtering

Proceeding NameInformation and Communication Technology for Intelligent Systems, Smart Innovation, Systems and Technologies

PublisherSpringer, Singapore

Author NamePriyank Thakkar, Krunal Varma, Vijay Ukani

Year , VenueMarch 2017 , Ahmedabad

Page Number127-135

ISSN/ISBN No978-3-319-63645-0

Indexed INScopus

Personalized Resource Recommendations using Learning from Positive and Unlabeled Examples

Journal

Journal NameNirma University Journal of Engineering and Technology

Title of PaperPersonalized Resource Recommendations using Learning from Positive and Unlabeled Examples

PublisherNirma University

Volume Number5

Page Number12-20

Published YearAugust 2016

ISSN/ISBN No2231-2870

Indexed INOthers

Predicting stock market index using fusion of machine learning techniques

Journal

Journal NameExpert Systems with Applications

Title of PaperPredicting stock market index using fusion of machine learning techniques

PublisherElsevier

Volume Number42

Page Number2162-2172

Published YearMarch 2015

ISSN/ISBN No0957-4174

Indexed INScopus, UGC List

Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques

Journal

Journal NameExpert Systems with Applications

Title of PaperPredicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques

PublisherElsevier

Volume Number42

Page Number259-268

Published YearJanuary 2015

ISSN/ISBN No0957-4174

Indexed INScopus, UGC List

Opinion spam detection using feature selection

Conference

Title of PaperOpinion spam detection using feature selection

Proceeding Name2014 International Conference on Computational Intelligence and Communication Networks (CICN)

PublisherIEEE

Page Number560-564

Published YearNovember 2014

A Cryptanalysis of the Authentication Protocol for IoD Security

Conference

Title of PaperA Cryptanalysis of the Authentication Protocol for IoD Security

Proceeding NamePriyanshi Thakkar

PublisherInternational Conference on Emerging Applications of Artificial Intelligence, Machine Learning and Cybersecurity

Author NamePriyanshi

OrganizationPANDIT DEENDAYAL ENERGY UNIVERSITY

Year , VenueMay 2024 , New Delhi

Page Number8

Indexed INScopus

Abstract

The emergence of smart cities and the growing demand for drones have led to the rise of Internet of Drones (IoD), offering numerous benefits in academia and industry. IoD integrates infrastructure, Internet of Things (IoT), and Flying Ad-Hoc Networks (FANET) to provide services including applications like traffic and environmental monitoring within smart city settings. However, IoD communication faces security vulnerabilities due to insecure channels, especially in unattended environments. In response to these challenges, in 2023, the authors introduced SLAP-IoD, a secure and lightweight authentication protocol employing Physical Unclonable Functions (PUF) to guarantee dependable services in smart cities. It establishes the security of SLAP-IoD through formal and informal analyses, comparing its performance with related schemes and claimed it to be secure against various attacks. However, in this paper we have done the cryptanalysis of the SLAP-IoD and prove that it is vulnerable to various attacks.

Enhancing Security Measures for Internet of Medical Things (IoMT): Analysis and Future Directions

Conference

Title of PaperEnhancing Security Measures for Internet of Medical Things (IoMT): Analysis and Future Directions

Proceeding NamePriyanshi Thakkar

PublisherInternational Conference on Computational Modelling And Sustainable Energy

Author NamePriyanshi Thakkar

OrganizationPANDIT DEENDAYAL ENERGY UNIVERSITY

Year , VenueDecember 2023 , Gandhinagar

Page Number10

Indexed INScopus

Abstract

The integration of the healthcare sector with the Internet of Things (IoT) framework has given rise to the Internet of Medical Things (IoMT). IoMT enables the generation, transmission, and examination of medical information through interconnected healthcare IT systems, sensors, and management software. Given the continual progress in IoT technology and the worldwide repercussions of the COVID-19 pandemic, IoMT has gained considerable notice for its capacity in personalized medical data administration, live health surveillance, and distant therapy. However, the sensitive nature of medical data in the IoMT environment has raised concerns regarding security, necessitating robust security protocols for safeguarding medical systems and IoT devices. This paper presents an in-depth exploration and evaluation of an IoMT scheme that incorporates a hybrid security approach, combining password-based authentication with a fuzzy extractor for biometric authentication. A novel system model and attack model are proposed to address the limitations identified in previous work. By conducting formal and informal analyses, we assess the security strengths of the proposed scheme, alongside a comprehensive evaluation of computational costs, thereby highlighting its comparative efficiency in relation to existing schemes.

A Review on Verifiable Image Licensing Approaches

Conference

Title of PaperA Review on Verifiable Image Licensing Approaches

Proceeding NamePriyanshi Thakkar

Publisher8th International Conference on Convergence and Technology

Author NamePriyanshi Thakkar

OrganizationPANDIT DEENDAYAL ENERGY UNIVERSITY

Year , VenueJanuary 2023 , Goa

Page Number8

Indexed INScopus

Abstract

Licensing an image refers to grant permission to use your image not to sell it full. Granting permission allows the person to edit, commerce and advertise usage also referred as the industry-standard method. Licensing the image allows to modify signing an agreement lays out the parameters, classification, and restrictions for utilizing an image. While techniques such as process of acme and perception ciphering can be used to verify the authenticity of an image and any modification specified in the contract, they are not able to determine who made the edits. Gradually gathering all the information of cryptographic. In past papers they have identified two key characteristics: 1. Authorized Use: Only a licensed individual or entity who follows the conditions outlined in a usage deal can create legitimate photos; 2. Productivity: validation of veritable image licensing system is fast and not affected by the number of edits or photos dimension.

IoT-based smart climate agriculture system for precision agriculture using WSN

Book Chapter

Book NameThe Convergence of Self-Sustaining Systems With AI and IoT

PublisherIGI Global

Author NamePurnima Gandhi

Page Number227-241

Chapter TitleIoT-based smart climate agriculture system for precision agriculture using WSN

Published YearAugust 2024

ISSN/ISBN No979-836931703-7, 979-836931702-0

Indexed INScopus, Web of Science, EBSCO

Advanced Application Development in Agriculture—Issues and Challenges

Conference

Title of PaperAdvanced Application Development in Agriculture—Issues and Challenges

Proceeding NameLecture Notes in Networks and Systems

PublisherSpringer

Author NamePurnima Gandhi

Page Number625 - 635

Published YearJanuary 2023

ISSN/ISBN No 23673389 23673370

Indexed INScopus

Developing Big Data Analytics Architecture for Spatial Data

Conference

Title of PaperDeveloping Big Data Analytics Architecture for Spatial Data

Proceeding NameInternational Conference on Very Large Data Bases, PhD Workshop

PublisherCEUR Workshop Proceedings

Author NamePurnima Shah

Year , VenueAugust 2019 , Los Ageless, California, USA

Indexed INScopus

Big Data Analytics and Integration Platform for Agriculture

Conference

Title of PaperBig Data Analytics and Integration Platform for Agriculture

Proceeding NameIn the Proceedings of Research Frontiers in Precession Agriculture (Extended Data Analytics, Abstract), AFITA/WCCA 2018 Conference

Author NamePurnima Shah

Published YearJanuary 2018

Indexed INIndian citation Index, Others

Big Data Analytics Framework for Spatial Data

Conference

Title of PaperBig Data Analytics Framework for Spatial Data

Proceeding NameInternational Conference on Big Data Analytics

PublisherSpringer

Author NamePurnima Shah

Published YearJanuary 2018

Indexed INScopus

Towards development of spark based agricultural information system including geo-spatial data

Conference

Title of PaperTowards development of spark based agricultural information system including geo-spatial data

Proceeding NameIEEE International Conference on Big Data (Big Data)

PublisherIEEE

Author NamePurnima Shah

Published YearJanuary 2017

Indexed INScopus

Big data analytics architecture for agro advisory system

Conference

Title of PaperBig data analytics architecture for agro advisory system

Proceeding NameHigh Performance Computing Workshops (HiPCW)

PublisherIEEE

Published YearDecember 2016

Indexed INScopus

ICT Interventions to Improve the Performance of Canal Irrigation Sector in India

Conference

Title of PaperICT Interventions to Improve the Performance of Canal Irrigation Sector in India

Proceeding NameProceedings of the Eighth International Conference on Information and Communication Technologies and Development

PublisherACM

Published YearJanuary 2016

Indexed INScopus

Big Data Analytics for Crop Recommendation System

Conference

Title of PaperBig Data Analytics for Crop Recommendation System

Proceeding NameInternational Workshop on Big DataBenchmarking (WBDB)

Published YearJanuary 2015

Indexed INOthers

A Detailed Study on Text Mining using Genetic Algorithm

Journal

Journal NameInternational Journal of Engineering Development and Research (IJEDR)

Title of PaperA Detailed Study on Text Mining using Genetic Algorithm

Published YearJanuary 2014

Indexed INOthers

Job Resource Ratio Based Priority Driven Scheduling in Cloud Computing

Journal

Journal NameInternational Journal for Scientific Research & Development

Title of PaperJob Resource Ratio Based Priority Driven Scheduling in Cloud Computing

Published YearJanuary 2013

Indexed INOthers

An Adaptive Load Balancing Algorithm in Heterogeneous Distributed System Using Central Scheduler – GA Based Approach

Conference

Title of PaperAn Adaptive Load Balancing Algorithm in Heterogeneous Distributed System Using Central Scheduler – GA Based Approach

Proceeding NameInternational Conference on Emerging Trends in Computer Science and Information Technology

Published YearJanuary 2012

Indexed INOthers

Energy efficient threshold based approach for migration at cloud data center

Journal

Journal NameInternational Journal of Engineering Research & Technology

Title of PaperEnergy efficient threshold based approach for migration at cloud data center

Published YearJanuary 2012

Indexed INOthers

Load Balancing in Distributed System using Genetic Algorithm

Journal

Journal NameInternational Journal of Computer Applications,Special issues on IP Multimedia Communications

Title of PaperLoad Balancing in Distributed System using Genetic Algorithm

Published YearJanuary 2011

Indexed INOthers

Trust Exploitation in Graph based Social Recommender Systems: A Survey

Conference

Title of PaperTrust Exploitation in Graph based Social Recommender Systems: A Survey

Proceeding Name2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE)

PublisherIEEE

Author NameRachana Mehta, Shakti Mishra

Year , VenueFebruary 2024 , VIT,Vellore

Page Number1-9

Indexed INScopus

Information visualization in big data and IoT: A review

Conference

Title of PaperInformation visualization in big data and IoT: A review

Proceeding NameAIP Conference Proceedings

PublisherAIP Publishing

Author NameRachana Mehta, Smita Darandale, Nidhi Periwal

Published YearDecember 2023

Indexed INScopus

Unleashing the power of SDN and GNN for network anomaly detection: State‐of‐the‐art, challenges, and future directions

Journal

Journal NameSecurity and Privacy

Title of PaperUnleashing the power of SDN and GNN for network anomaly detection: State‐of‐the‐art, challenges, and future directions

PublisherWiley

Volume Number7

Published YearJuly 2023

Indexed INScopus, Web of Science

Robotics and process automation technologies for healthcare informatics

Book Chapter

Book NameInnovations in Healthcare Informatics: From Interoperability to Data Analysis

PublisherIET

Author NameVivek Kumar Prasad, Rachana Mehta, Madhuri Bhavsar, Sudeep Tanwar, Mahima Bakshi

Page Number207

Chapter TitleRobotics and process automation technologies for healthcare informatics

Published YearJune 2023

Indexed INScopus

Evolving technologies: IoT and artificial intelligence for healthcare informatics

Book Chapter

Book NameInnovations in Healthcare Informatics: From Interoperability to Data Analysis

PublisherIET

Author NameRachana Mehta, Vivek Kumar Prasad, Shakti Mishra, Sudeep Tanwar, Yash Patel

Page Number231

Chapter TitleEvolving technologies: IoT and artificial intelligence for healthcare informatics

Published YearJanuary 2023

Indexed INScopus

A Secure Mechanism for Safeguarding Cloud Infrastructure

Conference

Title of PaperA Secure Mechanism for Safeguarding Cloud Infrastructure

Proceeding NameAdvancements in Smart Computing and Information Security: First International Conference, ASCIS 2022, Part II

PublisherSpringer Nature

Author NameKhare Pratyush, Vivek Kumar Prasad, Rachana Mehta, Madhuri Bhavsar

Page Number144-158

Published YearJanuary 2023

Indexed INScopus

Review of Crop Yield Estimation using Machine Learning and Deep Learning Techniques

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperReview of Crop Yield Estimation using Machine Learning and Deep Learning Techniques

Volume Number23

Page Number59-80

Published YearAugust 2022

Predicting Stock Market Trends using Random Forest: A Comparative Analysis

Conference

Title of PaperPredicting Stock Market Trends using Random Forest: A Comparative Analysis

Proceeding Name2022 7th International Conference on Communication and Electronics Systems (ICCES)

PublisherIEEE

Author NameKruti Lavingia, Pimal Khanpara, Rachana Mehta, Karan Patel, Niket Kothari

Page Number1544-1550

Published YearJune 2022

Indexed INScopus

Risk Assessment and Management using Machine Learning Approaches

Conference

Title of PaperRisk Assessment and Management using Machine Learning Approaches

Proceeding Name2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC)

PublisherIEEE

Author NameSmita Darandale, Rachana Mehta

Published YearJune 2022

Indexed INScopus

Graph Neural Network based Recommender System

Conference

Title of PaperGraph Neural Network based Recommender System

Proceeding Name2022 7th International Conference on Communication and Electronics Systems (ICCES)

PublisherIEEE

Author NameRachana Mehta, Kruti Lavingia, Pimal Khanpara, Vijay Dulera

Page Number1377-1381

Published YearJune 2022

Indexed INScopus

Information retrieval and data analytics in internet of things: current perspective, applications and challenges

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperInformation retrieval and data analytics in internet of things: current perspective, applications and challenges

Volume Number23

Page Number23-34

Published YearApril 2022

Indexed INScopus, Web of Science

Pattern Matching Algorithms: A Survey

Book Chapter

Book Name Advances in Intelligent Systems and Computing

PublisherSpringer

Author NameRachana Mehta

Page Number397-404

Chapter TitlePattern Matching Algorithms: A Survey

Published YearJanuary 2022

ISSN/ISBN No978-981-16-4537-2

Indexed INScopus

Comparison Analysis of Extracting Frequent Itemsets Algorithms Using MapReduce

Conference

Title of PaperComparison Analysis of Extracting Frequent Itemsets Algorithms Using MapReduce

Proceeding NameIntelligent Data Communication Technologies and Internet of Things: Proceedings of ICICI 2020

PublisherSpringer

Author NameRachana Mehta

OrganizationNirma University

Page Number199

Published YearFebruary 2021

Indexed INScopus

Evolution of singular value decomposition in recommendation systems: a review

Journal

Journal NameInternational Journal of Business Intelligence and Data Mining

Title of PaperEvolution of singular value decomposition in recommendation systems: a review

PublisherInderscience Publishers

Volume NumberVol.14 No.4

Page Number20

Published YearApril 2019

Indexed INScopus

A review on matrix factorization techniques in recommender systems

Conference

Title of PaperA review on matrix factorization techniques in recommender systems

Proceeding Name2nd International Conference on Communication Systems, Computing and IT Applications (CSCITA)

PublisherIEEE

Author NameRachana Mehta, Keyur Rana

Year , VenueApril 2017 , Mumbai, India

Page Number4

ISSN/ISBN No978-1-5090-4381-1

Indexed INScopus

An empirical analysis on SVD based recommendation techniques

Conference

Title of PaperAn empirical analysis on SVD based recommendation techniques

Proceeding NameInnovations in Power and Advanced Computing Technologies (i-PACT)

PublisherIEEE

Author NameRachana Mehta, Keyur Rana

Year , VenueApril 2017 , Vellore, India

Page Number7

ISSN/ISBN No978-1-5090-5682-8

Indexed INScopus

A Permissioned Blockchain Approach for Real-Time Embedded Control Systems

Conference

Title of PaperA Permissioned Blockchain Approach for Real-Time Embedded Control Systems

Proceeding NameLecture Notes in Computer Science ((LNAI,volume 13924))

PublisherSpringerLink

Author NamePronaya Bhattacharya, Sudip Chatterjee, Rajan Datt, Ashwin Verma, Pushan Kumar Dutta

OrganizationMining Intelligence and Knowledge Exploration

Year , VenueJune 2023 , Springer Nature Switzerland

Page Numberpp 341–352

Indexed INScopus

AutoBots: A Botnet Intrusion Detection Scheme using Deep Autoencoders

Conference

Title of PaperAutoBots: A Botnet Intrusion Detection Scheme using Deep Autoencoders

PublisherLNNS Springer

Author Name Ashwin Verma, Pronaya Bhattacharya, Vivek Prasad, Rajan Datt, Sudeep Tanwar

Published YearDecember 2022

Indexed INScopus

Student Attendance Management SystemUsing Fingerprint Scanner

Journal

Journal NameInternational Journal of Pure and Applied Mathematics

Title of PaperStudent Attendance Management SystemUsing Fingerprint Scanner

Volume Number119

Page Number2273-2277

Published YearJune 2018

Abstract

in order to identify person uniquely various things are used such as iris, lip print, fingerprint. In this paper we have developed Student Attendance Management System which is used to identify the students uniquely using their Fingerprints. For the development of this system we have used Raspberry Pi 3, Serial 16x2 Serial LCD and Fingerprint Scanner tools. By using this we have developed system which isstoring information of the student, verifying detail and generate report for the future use. During the attendance verification student keep his finger against the scanner and system will find whether the record is existing in the database or not, display proper message. We have also test system with various test case and found good results. By using this system teacher can save their time and increase accuracy in the results.

DATA EXCHANGE MODEL USING WEB SERVICE FOR HEROGENEOUS DATABASES

Journal

Journal NameINTERNATIONAL JOURNAL OF ADVANCED RESEARCH IN ENGINEERING AND TECHNOLOGY (IJARET)

Title of PaperDATA EXCHANGE MODEL USING WEB SERVICE FOR HEROGENEOUS DATABASES

PublisherIAEME

Volume Number6

Page Number107-111

Published YearApril 2015

ISSN/ISBN No0976 - 6499

Indexed INUGC List

Abstract

In this paper, we have purpose method to exchange the data between the various databases that are not having a same formats, due to the heterogeneous structure of the databases. Now in the information technology field there is fast development is there, due to that people are using different network, operating system and applications of heterogeneous platforms. So in order to sharing of information between the various databases we have purposed model using web service to exchange the data between the heterogeneous databases. This model is used to exchange data of various databases using some functions of databases, SOAP, XML, WSDL and UDDI.

Efficient Technique for FingerPrint Recognition

Journal

Journal NameInt. J. of Data Modeling and Knowledge Management

Title of PaperEfficient Technique for FingerPrint Recognition

PublisherMind Reader Publications

Volume Number1

Page Number45-50

Published YearDecember 2011

METHODOLOGY FOR DATA TRANSFER WITH ATTACHMENT USING WEB SERVICE

Journal

Journal NameINTERNATIONAL JOURNAL OF EMERGING TECHNOLOGIES AND APPLICATIONS IN ENGINEERING, TECHNOLOGY AND SCIENCES

Title of PaperMETHODOLOGY FOR DATA TRANSFER WITH ATTACHMENT USING WEB SERVICE

Volume Number4

Page Number409-411

Published YearJuly 2011

ISSN/ISBN No0974-3588

Abstract

Web service is supporting very simple requests with simple parameters to fully supporting modern, object-oriented languages. XML-RPC, arguably one of the earliest forms of Web services, only supported simple types -- strings, integers, Boolean etc. SOAP took this one step further with its encoding rules for object. In this paper we are going describe how binary data is transfer using web service. Binary data can be useful in many security applications to encrypt a data, multimedia application to work with image, movies, music and for some engineering application to represent data efficiently.

Classification of Potentially Hazardous Asteroids Using Supervised Quantum Machine Learning

Journal

Journal NameIEEE Access

Title of PaperClassification of Potentially Hazardous Asteroids Using Supervised Quantum Machine Learning

PublisherIEEE

Volume Number11

Page Number75829 - 75848

Published YearJuly 2023

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Quantum computing (QC) and quantum machine learning (QML) are emerging technologies with the potential to revolutionize the way we approach complex problems in mathematics, physics, and other fields. The increasing availability of data and computing power has led to a rise in using Artificial Intelligence (AI) to solve real-time problems. In space science, employing AI-based approaches to address various challenges, including the potential risks posed by asteroids, is becoming increasingly necessary. Potentially Hazardous Asteroids (PHAs) can cause significant harm to humans and biodiversity through wind blasts, overpressure shock, thermal radiation, cratering, seismic shaking, ejecta deposition, and even tsunamis. Machine Learning (ML) algorithms have been employed to detect hazardous asteroids based on their parameters. Still, there are limitations to the current techniques, and the results have reached a saturation point. To address this issue, we propose a Quantum Machine Learning (QML)-based approach for asteroid hazard prediction, employing Variational Quantum Circuits (VQC) and PegasosQSVC algorithms. The proposed work aims to leverage the quantum properties of the data to improve the accuracy and precision of asteroid classification. Our study focuses on the impact of PHAs, and the proposed supervised QML-based method aims to detect whether an asteroid with specific parameters is hazardous or not. We compared several classification algorithms and found that the proposed QML-based approach employing VQC and PegasosQSVC outperformed the other methods, with an accuracy of 98.11% and an average F1-score of 92.69%.

Fusion of artificial intelligence and game theory for resource allocation in non-orthogonal multiple access-assisted device-to-device cooperative communication

Journal

Journal NameInternational Journal of Communication Systems

Title of PaperFusion of artificial intelligence and game theory for resource allocation in non-orthogonal multiple access-assisted device-to-device cooperative communication

PublisherWiley

Page Number1-12

Published YearJune 2023

Indexed INScopus, Web of Science

Abstract

Device-to-device (D2D) communication offers a low-cost paradigm where two devices in close proximity can communicate without needing a base station (BS). It significantly improves radio resource allocation, channel gain, communication latency, and energy efficiency and offers cooperative communication to enhance the weak user's network coverage. The cellular mobile users (CMUs) share the spectral resources (e.g., power, channel, and spectrum) with D2D mobile users (DMUs), improving spectral efficiency. However, the reuse of radio resources causes various interferences, such as intercell and intracell interference, that degrade the performance of overall D2D communication. To overcome the aforementioned issues, this paper presents a fusion of AI and coalition game for secure resource allocation in non-orthogonal multiple access (NOMA)-based cooperative D2D communication. Here, NOMA uses the successive interference cancellation (SIC) technique to reduce the severe impact of interference from the D2D systems. Further, we utilized a coalition game theoretic model that efficiently and securely allocates the resources between CMUs and DMUs. However, in the coalition game, all DMUs participate in obtaining resources from CMUs, which increases the computational overhead of the overall system. For that, we employ artificial intelligence (AI) classifiers that bifurcate the DMUs based on their channel quality parameters, such as reference signal received power (RSRP), received signal strength indicator (RSSI), signal-to-noise ratio (SNR), and channel quality indicator (CQI). It only forwards the DMUs that have better channel quality parameters into the coalition game, thus reducing the computational overhead of the overall D2D communication. The performance of the proposed scheme is evaluated using various statistical metrics, for example, precision score, accuracy, recall, F1 score, overall sum rate, and secrecy capacity, where an accuracy of 99.38% is achieved while selecting DMUs for D2D communication.

A systematic review on performance evaluation metric selection method for IoT-based applications

Journal

Journal NameMicroprocessors and Microsystems

Title of PaperA systematic review on performance evaluation metric selection method for IoT-based applications

PublisherElsevier, Science Direct

Volume Number101

Page Number1-15

Published YearJune 2023

ISSN/ISBN No1872-9436

Indexed INScopus, Web of Science

Abstract

Internet of Things (IoT) has evolved many day-to-day objects into smart objects, which humans can control when they are connected via Internet. Its practical implementation came into existence a few years back. Since the advent of IoT, it has tackled many challenges such as management, tracking, observation, etc. It has contributed to various fields such as Healthcare 4.0, smart grid, smart agriculture, Intelligent Transportation Systems (ITS), smart cities, smart homes, smart cars, and many more. It has applications through almost all domains, but the question arises: the performance evaluating parameters about specific IoT applications to consider to detect flaws in it. As per literature, there exist no such article helps beginners in selecting performance evaluation parameters for IoT-enabled applications. Motivated from the aforementioned facts, this paper presents a survey on performance evaluation metrics’ systematic study for various IoT applications. We then graphically present the comparison of multiple parameters of domains security, energy efficiency, data storage, and network performance. From the analysis, we can infer that, in the smart city, latency is the most usable parameter, i.e., 77%. In contrast, in Healthcare 4.0, equal importance is given to latency and network bandwidth, which is 50%. Also, in Industry 4.0, scalability is the most opted performance parameter by the researchers, which is 100%. The smart grid application uses latency and delay are the most valuable parameters, i.e., 60%.

LEAF: A Federated Learning-Aware Privacy Preserving Framework for Healthcare Ecosystem

Journal

Journal NameIEEE Transactions on Network and Service Management

Title of PaperLEAF: A Federated Learning-Aware Privacy Preserving Framework for Healthcare Ecosystem

PublisherIEEE

Page Number1-13

Published YearJune 2023

ISSN/ISBN No1932-4537

Indexed INScopus, Web of Science

Abstract

Over the last decades, the healthcare industry has been revolutionized like anything, especially after the Covid-19 surge. Various artificial intelligence approaches have also been explored during this era for their applicability in healthcare. However, traditional AI techniques and algorithms are prone to overfitting with minimum robustness to unseen or untrained data. So, there is a requirement for new techniques which can counterfeit the issues mentioned earlier. Federated learning (FL) can help to make specific AI services for the network of hospitals with less overfitting and more robust modules. However, with the inclusion of FL, the problem related to user privacy is the biggest challenge, making using FL in the real world a grand challenge. Most solutions presented in the literature used blockchain technology to mitigate the issues mentioned earlier. However, it prevents third-party systems from penetrating the decision process, but the network devices can access shared data. Moreover, blockchain implementation requires new paradigms and infrastructure with an additional overhead cost. Motivated by these facts, the paper presents a limited access encryption algorithm incorporating FL (LEAF) framework, i.e., an encryption technique that solves privacy issues with the help of edge-enabled AI models. The proposed LEAF framework preserves user privacy and minimizes overhead costs. The authors have evaluated the performance of the LEAF framework using extensive simulations and achieved superior results. The achieved accuracy of the proposed LEAF framework is 3% more than that of the traditional centralized and FL-based systems advantages without compromising user privacy. In the best scenario, the proposed framework’s encryption process also compresses the data size by 4-5 times.

An Improved Dense CNN Architecture for Deepfake Image Detection

Journal

Journal NameIEEE Access

Title of PaperAn Improved Dense CNN Architecture for Deepfake Image Detection

PublisherIEEE

Volume Number11

Page Number22081 - 22095

Published YearMarch 2023

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Recent advancements in computer vision processing need potent tools to create realistic deepfakes. A generative adversarial network (GAN) can fake the captured media streams, such as images, audio, and video, and make them visually fit other environments. So, the dissemination of fake media streams creates havoc in social communities and can destroy the reputation of a person or a community. Moreover, it manipulates public sentiments and opinions toward the person or community. Recent studies have suggested using the convolutional neural network (CNN) as an effective tool to detect deepfakes in the network. But, most techniques cannot capture the inter-frame dissimilarities of the collected media streams. Motivated by this, this paper presents a novel and improved deep-CNN (D-CNN) architecture for deepfake detection with reasonable accuracy and high generalizability. Images from multiple sources are captured to train the model, improving overall generalizability capabilities. The images are re-scaled and fed to the D-CNN model. A binary-cross entropy and Adam optimizer are utilized to improve the learning rate of the D-CNN model. We have considered seven different datasets from the reconstruction challenge with 5000 deepfake images and 10000 real images. The proposed model yields an accuracy of 98.33% in AttGAN, [Facial Attribute Editing by Only Changing What You Want (AttGAN)] 99.33% in GDWCT,[Group-wise deep whitening-and-coloring transformation (GDWCT)] 95.33% in StyleGAN, 94.67% in StyleGAN2, and 99.17% in StarGAN [A GAN capable of learning mappings among multiple domains (StarGAN)] real and deepfake images, that indicates its viability in experimental setups.

EmReSys: AI-based Efficient Employee Ranking and Recommender System for Organizations

Conference

Title of PaperEmReSys: AI-based Efficient Employee Ranking and Recommender System for Organizations

Proceeding Name2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

PublisherIEEE

Author NameDhairya Jadav; Dev Patel; Somya Thacker; Anuja Nair; Rajesh Gupta; Nilesh Kumar Jadav; Sudeep Tanwar

OrganizationIEEE

Year , VenueFebruary 2023 , Sharda University, Grater Noida, UP

Page Number1-6

ISSN/ISBN Nohttps://ieeexplore.ieee.org/document/10037656

Indexed INScopus, Web of Science

Abstract

According to Jorge Paulo Lemann, “the greatest asset of a company is its people.” An organization consists of many areas where technologies supporting decision-making, i.e., artificial intelligence, can assist organizations in organization aspects, business strategies, and people management. The objective of decision-making technologies is not based on subjective factors but on objective data analysis. One such application area is to provide incentives to employees without any human interaction or intervention. It is an organization’s job to find good employees and recognize their efforts by offering incentives. However, handpicking potentially outstanding employees in a workplace where biases have penetrated gets perplexing. To overcome this barrier, EmReSys, an employee recommendation System for large-scale organizations, is developed, which does not require any human interaction to recognize personnel potential. It uses Machine Learning (ML) techniques to recommend the employee for promotion, increment, etc. The EmReSys system is installed at the edge network to perform ML tasks efficiently and the communication is established via the 5G network. The suggested method automates the procedure using a Support Vector Machine (SVM), an ML technique with a 98.9% accuracy.

Blockchain-Driven Real-Time Incentive Approach for Energy Management System

Journal

Journal NameMathematics

Title of PaperBlockchain-Driven Real-Time Incentive Approach for Energy Management System

PublisherMDPI

Volume Number11

Page Number1-17

Published YearFebruary 2023

ISSN/ISBN No2227-7390

Indexed INScopus, Web of Science

Abstract

In the current era, the skyrocketing demand for energy necessitates a powerful mechanism to mitigate the supply–demand gap in intelligent energy infrastructure, i.e., the smart grid. To handle this issue, an intelligent and secure energy management system (EMS) could benefit end-consumers participating in the Demand–Response (DR) program. Therefore, in this paper, we proposed a real-time and secure incentive-based EMS for smart grid, i.e., RI-EMS approach using Reinforcement Learning (RL) and blockchain technology. In the RI-EMS approach, we proposed a novel reward mechanism for better convergence of the RL-based model using a Q-learning approach based on the greedy policy that guides the RL-agent for faster convergence. Then, the proposed RI-EMS approach designed a real-time incentive mechanism to minimize energy consumption in peak hours and reduce end-consumers’ energy bills to provide incentives to the end-consumers. Experimental results show that the proposed RI-EMS approach induces end-consumer participation and increases customer profitabilities compared to existing approaches considering the different performance evaluation metrics such as energy consumption for end-consumers, energy consumption reduction, and total cost comparison to end-consumers. Furthermore, blockchain-based results are simulated and analyzed with the help of deployed smart contracts in a Remix Integrated Development Environment (IDE) with the parameters such as transaction efficiency and data storage cost

Blockchain and artificial intelligence-empowered smart agriculture framework for maximizing human life expectancy

Journal

Journal NameComputers and Electrical Engineering, Elsevier

Title of PaperBlockchain and artificial intelligence-empowered smart agriculture framework for maximizing human life expectancy

PublisherElsevier, Science Direct

Volume Number105

Page Number1-13

Published YearJanuary 2023

ISSN/ISBN No1879-0755

Indexed INScopus, Web of Science

Abstract

The massive population growth and rising environmental issues raise several challenges in the agriculture sector, such as agricultural land scarcity, overuse of pesticides, and global food demand. To meet global food demand, farmer uses large quantities of pesticides to enhance crop quality and quantity. However, consuming food from pesticide crops reduces human life expectancy. To overcome the aforementioned issue and improve human life expectancy, we proposed a blockchain and artificial intelligence (AI)-empowered smart agriculture framework to predict pesticide crop’s beyond the threshold. The blockchain is integrated to confront the data manipulation attack, where the crop that uses minimum pesticides is securely stored inside the blockchain’s immutable ledger. Finally, the proposed framework is evaluated with performance metrics, such as accuracy, blockchain scalability, and latency. The result shows that the proposed framework outperforms in terms of accuracy, scalability, and latency compared to the baseline approaches.

GeFL: Gradient Encryption-Aided Privacy Preserved Federated Learning for Autonomous Vehicles

Journal

Journal NameIEEE Access

Title of PaperGeFL: Gradient Encryption-Aided Privacy Preserved Federated Learning for Autonomous Vehicles

PublisherIEEE

Volume Number11

Page Number1825 - 1839

Published YearJanuary 2023

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Autonomous vehicles (AVs) are getting popular because of their usage in a wide range of applications like delivery systems, self-driving taxis, and ambulances. AVs utilize the power of machine learning (ML) and deep learning (DL) algorithms to improve their self-driving learning experiences. The sudden surge in the number of AVs raises the need for distributed learning ecosystem to optimize their self-driving experiences at a rapid pace. Toward this goal, federated learning (FL) benefits, which can create a distributed learning environment for AVs. But, the traditional FL transfers the raw input data directly to a server, which leads to privacy concerns among the end-users. The concept of blockchain helps us to protect privacy, but it requires additional computational infrastructure. The extra infrastructure increases the operational cost for the company handling and maintaining the AVs. Motivated by this, in this paper, the authors introduced the concept of gradient encryption in FL, which preserves the users’ privacy without the additional computation requirements. The computational power present in the edge devices helps to fine-tune the local model and encrypt the input data to preserve privacy without any drop in performance. For performance evaluation, the authors have built a German traffic sign recognition system using a convolutional neural network (CNN) algorithm-based classification system and GeFL. The simulation process is carried out over a wide range of input parameters to analyze the performance at scale. Simulation results of GeFL outperform the conventional FL-based algorithms in terms of accuracy, i.e., 2% higher. Also, the amount of data transferred among the devices in the network is nearly three times less in GeFL compared to the traditional FL.

Blockchain and federated learning-based security solutions for telesurgery system: a comprehensive review

Journal

Journal NameTurkish Journal of Electrical Engineering & Computer Sciences

Title of PaperBlockchain and federated learning-based security solutions for telesurgery system: a comprehensive review

PublisherTUBITAK

Volume Number30

Page Number1-43

Published YearNovember 2022

ISSN/ISBN No1300-0632

Indexed INScopus, Web of Science

Abstract

The advent of telemedicine with its remote surgical procedures has effectively transformed the working of healthcare professionals. The evolution of telemedicine facilitates the remote monitoring of patients that lead to the advent of telesurgery systems, i.e. one of the most critical applications in telemedicine systems. Apart from gaining popularity, the telesurgery system may encounter security and trust issues of patients? data while communicating with the surgeon for their remote treatment. Motivated by this, we have presented a comprehensive survey on secure telesurgery systems comprising healthcare, surgical robots, traditional telesurgery systems, and the role of artificial intelligence to deal with the numerous security attacks associated with the patients' health data. Furthermore, we propose a blockchain and federated learning-based secure telesurgery system to secure the communication between patient and surgeon. The results of the proposed system are better than those of the traditional system in terms of improved latency, low data storage cost, and enhanced data offloading. Finally, we explore the research challenges and issues associated with the telesurgery system.

Database Creation for Marathi QA System

Conference

Title of PaperDatabase Creation for Marathi QA System

Proceeding NameProceedings of the International Conference on Smart Data Intelligence (ICSMDI 2021)

PublisherSSRN

Author NameBharat A. Shelke ,Ramesh R. Naik, C. Namrata Mahender

OrganizationSSRN

Published YearMay 2021

Indexed INOthers

Abstract

The use of the internet has grown extremely over the last two decades, resulting in the proliferation of massive volumes of data on the internet. Since there is so much data available online, researchers are interested in the Question Answering era, in which users ask questions and obtain correct answers. A classic NLP programme is answering questions although work on some Indian regional languages, such as Tamil, Punjabi, Hindi, Malayalam, and Bengali, is ongoing; there is little work available for Question Answering (QA) Systems in Marathi. The construction of a text corpus, question generation, and question classification for a Marathi question answering method were the key topics of this paper.

Author Identification for Marathi Language

Journal

Journal NameAdvances in Science, Technology and Engineering Systems Journal

Title of PaperAuthor Identification for Marathi Language

PublisherASTESJ

Volume NumberVol. 5, No. 2

Published YearApril 2020

ISSN/ISBN No2415-6698

Indexed INScopus

Abstract

This is era of new technology; most of information is collected from internet, web sites. Some people uses data from research papers, thesis, and website as it is and publish as their own research without giving proper acknowledgement. This term is known as plagiarism. There are two types of plagiarism detection methods, i) Extrinsic plagiarism detection ii) Intrinsic plagiarism detection. Through extrinsic plagiarism utilizing reference corpus plagiarism is observed, while in intrinsic plagiarism identification, using author's writing style, plagiarism can be identified. If the anonymous text is written by unknown author. By using authorship analysis we can find original author of text. Authorship analysis is having three types i)Author identification ii) Author characterization and iii) Similarity detection. This paper mainly focuses on author identification for Marathi language. To calculate projection in two different files, we used feature vectors of main author file and summary file of other authors. The result of average projection shows, there is similarity in main author file and summary file of different authors, it also shows summary file of each author is having impact of main author file.

Word Level Plagiarism Detection of Marathi Text Using N-Gram Approach

Journal

Journal NameSpringer Nature Singapore

Title of PaperWord Level Plagiarism Detection of Marathi Text Using N-Gram Approach

PublisherSpringer Nature Singapore

Published YearJuly 2019

ISSN/ISBN No978-981-13-9187-3

Indexed INScopus

Abstract

Plagiarism is increasing day by day. Plagiarism detection is one of the most complex, but a must requirement. This paper deals with word level plagiarism detection for Marathi text by using N-gram language model and a Marathi corpus. This is most simple in form still provides good depth for understanding and emphasing copy-paste and paraphrased plagiarism detection. It forms basis for sentence as well as paragraph level processing

A Proposed Model to Identify Paraphrasing in Marathi Text

Journal

Journal NameInternational Journal for Research in Engineering Application and Management

Title of PaperA Proposed Model to Identify Paraphrasing in Marathi Text

PublisherIJREAM

Published YearJanuary 2019

ISSN/ISBN No2454-9150

Indexed INOthers

Abstract

Paraphrasing is an essential resources of linguistic and literature, as it provides the power of expression such as poems, stories. It also becomes confusing or difficult in some context like proverb those have dual means, moral of the stories. Even it is noteworthy to understand reinterpretation of same sentence may be different by different people. Thus to convey desirable semantics of a word/sentence. Paraphrasing is very important. When working with Marathi language many difficulties comes due to the linguistic aspect of language: 1) Marathi language is agglutinative, 2) Need of Dependency parser as it is object based, 3) Contextually some words can change meaning in a sentence, 4) Adjectives do not inflect under they end in Long /a/, in which case they agree with nouns in gender, number and case. In this paper we are proposing a doc2vec and word2vec based model for identifying the regions of paraphrasing in a given Marathi text.

UnRevealing Paraphrasing Aspects in Marathi Text-Using Machine Learning

Conference

Title of PaperUnRevealing Paraphrasing Aspects in Marathi Text-Using Machine Learning

Proceeding NameProceedings of the International Conference on Inventive Computation Technologies

PublisherIEEE

Author NameRamesh R. Naik,Maheshkumar B. Landge,C. Namrata Mahender

OrganizationIEEE

Year , VenueOctober 2018 , Coimbatore

ISSN/ISBN No978-1-5386-4984-8

Indexed INScopus

Abstract

Paraphrasing enhances the power of expression, as the same sentence can be expressed in many ways. This is also very important for NLP task like NLP understanding, Machine translation, question answering, and summarization and plagiarism detection. The present work focuses on the word/phrase level paraphrase identification using synonym, POS tags and N-gram technique for Marathi text.

Author Impression on Dependent Authors Using Wordtovector Method

Journal

Journal NameSpringer Nature Singapore

Title of PaperAuthor Impression on Dependent Authors Using Wordtovector Method

PublisherSpringer Nature Singapore

Page Number689–695

Published YearSeptember 2018

Indexed INScopus

Abstract

This paper provides an introduction to types of authorship analysis which is important in many applications of NLU, QA, Plagiarism detection etc. Author profiling helps to identify the traits of an author in the given text/texts, which finally leads to predict whether those traits are present in other text that reflects the important characteristics of the original author. The original author normally observed to have some sort of his impact or impression on dependent writers or authors The main focus of this paper is identifying the weight of impact of original author on dependent author. Word to vector technique is been used in this work to identify impact of original author on dependent authors

Comparative analysis of similarity measures on Marathi text Document for plagiarism detection

Journal

Journal NameInternational Journal for Research in Engineering Application and Management

Title of PaperComparative analysis of similarity measures on Marathi text Document for plagiarism detection

PublisherIJREAM

Published YearAugust 2018

ISSN/ISBN No2454-9150

Indexed INOthers

Abstract

This paper provides a comparative analysis of Marathi text documents based on similarity measures. Various similarity measures have been applied on of textual contents for many different languages especially English, French etc. In this paper selective similarity measures are applied for similarity analysis considering their parameters which were found helpful according to the structure of Marathi language for text plagiarism detection. The first task was development of corpus as no standard corpus is available for Marathi language, second collection and normalization [conversion in same format] of data as numerous fonts are available. The collected data is converted to Unicode format standard UTF-8. Comparative analysis shows that sequence matcher is best similarity measure as compare to cosine similarity and Jaccard similarity

Rule Based Part-of-Speech Tagger for Marathi Language

Journal

Journal NameInternational Journal of Scientific Research in Science and Technology

Title of PaperRule Based Part-of-Speech Tagger for Marathi Language

PublisherIJSRST

Published YearMarch 2018

ISSN/ISBN No2395-6011

Indexed INOthers

Abstract

A part of speech (POS) tagging is one of the best studied problems in the field of Natural Language Processing (NLP). POS tagging is the process of assigning a part-of-speech like noun, verb, adjective, adverb to each word in a sentence. In this paper we present a Marathi part of speech tagger. It is morphologically rich language. It is spoken by the native people of Maharashtra. POS tagging is difficult for Marathi language due to unavailability of corpus for computational processing. In this paper, a POS Tagger for Marathi language using Rule based technique is presented. Our proposed system which tokenizes the string into tokens, find root word using morphological analyzer and compare the root word with the WordNet to assign appropriate tag. If word has assigned more than one tags then by using Marathi grammar rules ambiguity is removed. Meaningful rules are provided to improve the performance of the system.

Novel Features for plagiarism detection in Marathi Language

Journal

Journal NameInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Title of PaperNovel Features for plagiarism detection in Marathi Language

PublisherIJSRCSEIT

Volume NumberVolume 3

Published YearJanuary 2018

ISSN/ISBN No2456-3307

Indexed INOthers

Abstract

Plagiarism is stealing information or idea from someone without giving proper acknowledgement. Currently plagiarism is increasing in different fields like education, industry. There is need to prevent plagiarism. There are four types of stylometric features available namely: lexical, syntactic, semantic, content specific. In this paper we have added three new features for detecting plagiarism namely noun, adjective and rhyming words. For calculating these features, we have used our own Marathi text corpus. These features will be useful for detecting plagiarism and linguistic researchers.

Measuring Author Impression Using Cosine Similarity Algorithm

Journal

Journal NameIOSR Journal of Computer Engineering

Title of PaperMeasuring Author Impression Using Cosine Similarity Algorithm

PublisherIOSR-JCE

Page NumberPP 24-28

Published YearOctober 2017

ISSN/ISBN No2278-0661

Indexed INOthers

Abstract

In this research we are focused on measuring the impact of main author on dependent author/followers. When dependent author use the work of main author, the dependent author may carry some impression of main author in his writing. Text similarity is comparison between query text and text from main document. This comparison gives most similar documents to user. Text similarity is important in the classifying the text as well as document. Using cosine similarity algorithm we can measure similarity between two different documents and also we can find impression of main author on dependent author. Up till now this work is not available for Marathi and English language it’s the first attempt in this direction where significance of author. This will also be applied in detection of plagiarism

Plagiarism Detection in Marathi Language Using Semantic Analysis

Journal

Journal NameInternational Journal of Strategic Information Technology and Applications

Title of PaperPlagiarism Detection in Marathi Language Using Semantic Analysis

PublisherIJSITA

Published YearJanuary 2017

ISSN/ISBN No1947-3095

Indexed INOthers

Abstract

In this article, the authors have proposed a method to detect plagiarism in the Marathi language by using semantic analysis. Nowadays, plagiarism is a challenging task in educational and research fields. Currently, there are some tools available to detect the plagiarism on the basis of similarity of words. But there is no tool available to detect the plagiarism semantically. In this article, the authors have applied preprocessing to a database i.e. tokenization, removed stop words and punctuations, for the goal of calculating the frequency of words. Then searching the same word or synonyms of words in wordnet to detect the semantic plagiarism. It is useful for many researchers who are working in this domain.

Development of Marathi Text Corpus for Plagiarism Detection in Marathi Language

Conference

Title of PaperDevelopment of Marathi Text Corpus for Plagiarism Detection in Marathi Language

Proceeding NameICKE

PublisherNA

Author NameRamesh R. Naik,Maheshkumar B. Landge,C. Namrata Mahender

OrganizationDepartment of CS and IT Dr BAMU Aurangabad Maharahtra

Year , VenueDecember 2016 , Department of CS and IT Dr BAMU Aurangabad

ISSN/ISBN NoISBN 978-93-86751-04-1

Indexed INOthers

A Review on Plagiarism Detection Tools

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperA Review on Plagiarism Detection Tools

PublisherIJCA

Volume NumberVolume 125 No11

Published YearSeptember 2015

ISSN/ISBN No0975 8887

Indexed INOthers

Abstract

Plagiarism has become an increasingly serious problem in the academic world. It is aggravated by the easy access to and the ease of cutting and pasting from a wide range of materials available on the internet. It constitutes academic theft - the offender has 'stolen' the work of others and presented the stolen work as if it were his or her own. It goes to the integrity and honesty of a person. It stifles creativity and originality, and defeats the purpose of education The plagiarism is a widespread and growing problem in the academic process. The traditional manual detection of plagiarism by human is difficult, not accurate, and time consuming process as it is difficult for any person to verify with the existing data. The main purpose of this paper is to present existing tools about in regards with plagiarism detection. Plagiarism detection tools are useful to the academic community to detect plagiarism of others and avoid such unlawful activity. This paper describes some of the plagiarism detection tools available for plagiarism checking and types of plagiarism.

Marathi WordNet Development

Journal

Journal NameInternational Journal Of Engineering And Computer Science

Title of PaperMarathi WordNet Development

PublisherIJECS

Volume NumberVolume - 3 Issue - 8

Page NumberPage No. 7622-7624

Published YearAugust 2014

ISSN/ISBN No2319-7242

Indexed INOthers

Abstract

WordNet is a dictionary of word meanings/concepts. Hence there must be a standard representation of the concepts in order to simulate a lexical matrix on a machine. Marathi is an Indo-Aryan language spoken by about 71 million people mainly in the Indian state of Maharashtra and neighboring states. In WordNet, which is basically a semantic network, the different lexical categories of words (nouns, verbs,..) are organized into 'Synsets' (sets of synonyms). Each synset represents a lexical concept and they can be linked by different types of relation (Hypernymy, antonym, etc.). The WordNet for Marathi 36842 unique words grouped in more than 26988 Synsets, linked synset 24398 [1]. We would like to increase unique words, with that we want to give special efforts on wards which are oriented towards Marathi culture only for example culture aspects of words like that Lawani, Abhang, Fugaddi, Ringan etc.

A triplanar ensemble model for brain tumor segmentation with volumetric multiparametric magnetic resonance images

Journal

Journal NameHealthcare Analytics

Title of PaperA triplanar ensemble model for brain tumor segmentation with volumetric multiparametric magnetic resonance images

PublisherElsevier

Volume Number5

Page Number1-10

Published YearJune 2024

ISSN/ISBN No2772-4425

Indexed INScopus

Abstract

Automated segmentation methods can produce faster segmentation of tumors in medical images, aiding medical professionals in diagnosis and treatment plans. A 3D U-Net method excels in this task but has high computational costs due to large model parameters, which limits their application under resource constraints. This study targets an optimized triplanar (2.5D) model ensemble to generate accurate segmentation with fewer parameters. The proposed triplanar model uses spatial and channel attention mechanisms and information from multiple orthogonal planar views to predict segmentation labels. In particular, we studied the optimum filter size to improve the accuracy without increasing the network complexity. The model generated output is further post-processed to fine-tune the segmentation results. The Dice similarity coefficients (Dice-score) of the Brain Tumor Segmentation (BraTS) 2020 training set for enhancing tumor (ET), whole tumor (WT), and tumor core (TC) are 0.736, 0.896, and 0.841, whereas, for the validation set, they are 0.713, 0.873, and 0.778, respectively. The proposed base model has only 10.25𝑀 parameters, three times less than BraTS 2020’s best-performing model (ET 0.798, WT 0.912, TC 0.857) on the validation set. The proposed ensemble model has 93.5𝑀 parameters, 1.6 times less than the top-ranked model and two times less than the third-ranked model (ET 0.793, WT 0.911, TC 0.853 on validation set) of BraTS2020 challenge.

Customer Segmentation with RFM Analysis using Support Vector Machine

Conference

Title of PaperCustomer Segmentation with RFM Analysis using Support Vector Machine

Proceeding NameSpringer

PublisherSpringer

Author NameRupal A. Kapdi, Kuheli Bose, Jitali Patel, Jigna Patel

OrganizationAmity University

Year , VenueMarch 2024 , Amity University, Andhra Pradesh

Page Number-

ISSN/ISBN No-

Indexed INScopus

Abstract

Many company, academic, and marketing executives have been interested in customer segmentation. Customer segmentation involves the practice of grouping or segmenting an organization’s customer base according to comparable traits, including demographics, purchasing patterns, interests, and preferences. Finding groups of customers with similar requirements or behaviours is the goal of customer segmentation. It enables businesses to create focused marketing campaigns and customize their goods and services to satisfy those demands. Customer cognition, which includes identifying their differences and evaluating them, is one of the significant issues faced by customer-based organizations. We can build a very effective framework using machine learning algorithms and data processing to understand customer desires and behaviours better and respond accordingly to meet those demands. The paper shows the separate study of Recency(R), Frequency(F) and Monetary(M) along with the combination of these three for the overall score. The combined RFM score is used to segment customers into three segments to predict the next purchase possibility based on a time period of 30 days.

Concolla – A Smart Emotion-Based Music Recommendation System For Drivers

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperConcolla – A Smart Emotion-Based Music Recommendation System For Drivers

PublisherUniversitatea de vest

Volume Number24

Page Number919-940

Published YearNovember 2023

ISSN/ISBN No1895-1767

Indexed INScopus

Abstract

Music recommender system is an area of information retrieval system that suggests customized music recommendations to users based on their previous preferences and experiences with music. While existing systems often overlook the emotional state of the driver, we propose a hybrid music recommendation system-ConCollA to provide a personalized experience based on user emotions. By incorporating facial expression recognition, ConCollA accurately identifies the driver’s emotions using convolution neural network(CNN) model and suggests music tailored to their emotional state. ConCollA combines collaborative filtering, a novel content based recommendation system named Mood Adjusted Average Similarity (MAAS), and apriori algorithm to generate personalized music recommendations. The performance of ConCollA is assessed using various evaluation parameters. The results show that proposed emotion-aware model outperforms a collaborative based recommender system.

Yoga Pose Estimation Using Machine Learning

Book Chapter

Book NameProceedings of Fourth International Conference on Computing, Communications, and Cyber-Security

Page Number425-441

Chapter TitleYoga Pose Estimation Using Machine Learning

Published YearJuly 2023

Indexed INScopus

Multi-view brain tumor segmentation (MVBTS): An ensemble of planar and triplanar attention UNets

Journal

Journal NameTurkish Journal of Electrical Engineering and Computer Sciences

Title of PaperMulti-view brain tumor segmentation (MVBTS): An ensemble of planar and triplanar attention UNets

PublisherScientific and Technological Research Council, Turkey

Volume Number31

Page Number908-927

Published YearJuly 2023

Indexed INScopus

Abstract

3D UNet has achieved high brain tumor segmentation performance but requires high computation, large memory, abundant training data, and has limited interpretability. As an alternative, the paper explores using 2D triplanar (2.5D) processing, which allows images to be examined individually along axial, sagittal, and coronal planes or together. The individual plane captures spatial relationships, and combined planes capture contextual (depth) information. The paper proposes and analyzes an ensemble of uniplanar and triplanar UNets combined with channel and spatial attention for brain tumor segmentation. It investigates the significance of each plane and analyzes the impact of uniplanar and triplanar ensembles with attention to segmentation. We tested the performance of these variants on the BraTS2020 training and validation datasets. The best dice similarity coefficients for enhancing tumor, whole tumor, and tumor core over the training set are 0.712, 0.897, and 0.837, while they are 0.699, 0.875, and 0.782, over the validation set, respectively (obtained through BraTS model evaluation platform). The scores are at par with the leading 2D and 3D BraTS models. Therefore, the proposed approach with fewer parameters (almost 3× less) demonstrates comparable performance to that of a 3D model, making it suitable for brain tumor segmentation in resource-limited settings.

WEED RECOGNITION IN BRINJAL CROP USING DEEP LEARNING

Conference

Title of PaperWEED RECOGNITION IN BRINJAL CROP USING DEEP LEARNING

Proceeding NameLecture Notes in Electrical Engineering

OrganizationCyber Security Research Lab

Year , VenueJuly 2023 , Ghaziabad

Indexed INScopus

SMART WASTE MANAGEMENT SYSTEM USING MACHINE LEARNING AND BLOCKCHAIN TECHNOLOGY

Conference

Title of PaperSMART WASTE MANAGEMENT SYSTEM USING MACHINE LEARNING AND BLOCKCHAIN TECHNOLOGY

Proceeding NameLecture Notes in Electrical Engineering

Author NameJigna Patel, Jitali Patel, Rupal A. Kapdi

OrganizationCyber Security Research Lab

Year , VenueJuly 2023 , Ghaziabad

Indexed INScopus

Interpretability of Segmentation and Overall Survival for Brain Tumors

Book Chapter

Book NameExplainable AI in Healthcare Unboxing Machine Learning for Biomedicine

PublisherCRC Press, Taylor and Francis Group

Author NameRupal A. Kapdi, Snehal Rajput, Monehdra Roy, Mehul S. Raval

Page Number111-130

Chapter TitleInterpretability of Segmentation and Overall Survival for Brain Tumors

Published YearJuly 2023

ISSN/ISBN No9781003333425

Explainable AI in Healthcare: Unboxing Machine Learning for Biomedicine

Book

PublisherCRC Press, Taylor and Francis Group

Published YearJuly 2023

ISSN/ISBN No9781003333425

Abstract

This book combines technology and the medical domain. It covers advances in computer vision (CV) and machine learning (ML) that facilitate automation in diagnostics and therapeutic and preventive health care. The special focus on eXplainable Artifi cial Intelligence (XAI) uncovers the black box of ML and bridges the semantic gap between the technologists and the medical fraternity. Explainable AI in Healthcare: Unboxing Machine Learning for Biomedicine intends to be a premier reference for practitioners, researchers, and students at basic, intermediary levels and expert levels in computer science, electronics and communications, information technology, instrumentation and control, and electrical engineering. This book will benefi t readers in the following ways: • Explores state of art in computer vision and deep learning in tandem to develop autonomous or semi-autonomous algorithms for diagnosis in health care • Investigates bridges between computer scientists and physicians being built with XAI • Focuses on how data analysis provides the rationale to deal with the challenges of healthcare and making decision-making more transparent • Initiates discussions on human-AI relationships in health care • Unites learning for privacy preservation in health care

Interpretable machine learning model to predict survival days of malignant brain tumor patients

Journal

Journal NameMachine Learning: Science and Technology

Title of PaperInterpretable machine learning model to predict survival days of malignant brain tumor patients

PublisherIOP

Volume Number4

Page Number2

Published YearMay 2023

ISSN/ISBN No2632-2153

Indexed INScopus, Web of Science

Abstract

An artificial intelligence (AI) model’s performance is strongly influenced by the input features. Therefore, it is vital to find the optimal feature set. It is more crucial for the survival prediction of the glioblastoma multiforme (GBM) type of brain tumor. In this study, we identify the best feature set for predicting the survival days (SD) of GBM patients that outrank the current state-of-the-art methodologies. The proposed approach is an end-to-end AI model. This model first segments tumors from healthy brain parts in patients’ MRI images, extracts features from the segmented results, performs feature selection, and makes predictions about patients’ survival days (SD) based on selected features. The extracted features are primarily shape-based, location-based, and radiomics-based features. Additionally, patient metadata is also included as a feature. The selection methods include recursive feature elimination, permutation importance (PI), and finding the correlation between the features. Finally, we examined features’ behavior at local (single sample) and global (all the samples) levels. In this study, we find that out of 1265 extracted features, only 29 dominant features play a crucial role in predicting patients’ SD. Among these 29 features, one is metadata (age of patient), three are location-based, and the rest are radiomics features. Furthermore, we find explanations of these features using post-hoc interpretability methods to validate the model’s robust prediction and understand its decision. Finally, we analyzed the behavioral impact of the top six features on survival prediction, and the findings drawn from the explanations were coherent with the medical domain. We find that after the age of 50 years, the likelihood of survival of a patient deteriorates, and survival after 80 years is scarce. Again, for location-based features, the SD is less if the tumor location is in the central or back part of the brain. All these trends derived from the developed AI model are in sync with medically proven facts. The results show an overall 33% improvement in the accuracy of SD prediction compared to the top-performing methods of the BraTS-2020 challenge.

THREE CLASS CLASSIFICATION OF ALZHEIMER’S DISEASE USING DEEP NEURAL NETWORKS

Journal

Journal NameCurrent Medical Imaging

Title of PaperTHREE CLASS CLASSIFICATION OF ALZHEIMER’S DISEASE USING DEEP NEURAL NETWORKS

PublisherBentham Science

Volume Number19

Page Number855-864

Published YearMarch 2023

ISSN/ISBN No1875-6603

Indexed INScopus, PubMed, Web of Science

Abstract

Alzheimer’s disease (AD) is a prevalent type of dementia that can cause neurological brain disorders, poor decision making, impaired memory, mood swings, unstable emotions, and personality change. Deep neural networks are proficient in classifying Alzheimer's disease based on MRI images. This classification assists human experts in diagnosing AD and predicts its future progression. The paper proposes various Deep Neural Networks (DNN) for early AD detection to save cost and time for doctors, radiologists, and caregivers. A 3330-image-based Kaggle dataset is used to train the DNN, including 52 images of AD, 717 images of Mild Cognitive Impairment (MCI), and the remaining images of Cognitive Normal (CN). Stratified partitioning splits the dataset into 80% and 20% proportions for training and validation datasets. Proposed models include DenseNet169, DenseNet201, and Res- Net152 DNNs with additional three fully-connected layers and softmax and Kullback Leibler Divergence (KLD) loss function. These models are trained considering pre-trained, partially pre-trained, and fully re-trained extended base models. The KLD loss function reduces the error and increases accuracy for all models. The partially pre-trained DenseNet201 model outperformed all the other models. DenseNet201 gives the highest accuracy of 99.98% for training, 99.07% for validation, and 95.66% for test datasets. The DenseNet201 model has the highest accuracy in comparison to other state-of-artmethods.

IMAGE-BASED SEAT BELT FASTNESS DETECTION USING DEEP LEARNING

Journal

Journal NameSCALABLE COMPUTING: PRACTICE AND EXPERIENCE

Title of PaperIMAGE-BASED SEAT BELT FASTNESS DETECTION USING DEEP LEARNING

PublisherUniversitatea de vest

Volume Number23

Page Number441-455

Published YearDecember 2022

ISSN/ISBN No1895-1767

Indexed INScopus

YOGA POSE ESTIMATION USING MACHINE LEARNING

Conference

Title of PaperYOGA POSE ESTIMATION USING MACHINE LEARNING

PublisherFOURTH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATIONS AND CYBER SECURITY (IC4S-2022)

Author NameIshika Shah, Greeva Khant, Jitali Patel, Jigna Patel, Rupal A. Kapdi

OrganizationKRISHNA ENGINEERING COLLEGE, GHAZIABAD

Year , VenueDecember 2022 , KRISHNA ENGINEERING COLLEGE, GHAZIABAD

Page Number1-6

Indexed INScopus

SURVIVAL PREDICTION OF MALIGNANT BRAIN TUMOR PATIENTS

Conference

Title of PaperSURVIVAL PREDICTION OF MALIGNANT BRAIN TUMOR PATIENTS

Proceeding NameRECENT AND FUTURE TRENDS IN SMART ELECTRONICS SYSTEM AND MANUFACTURING

OrganizationSYMBIOSIS INSTITUTE OF TECHNOLOGY, PUNE

Year , VenueDecember 2022 , SYMBIOSIS INSTITUTE OF TECHNOLOGY, PUNE

Page Number1-11

Indexed INScopus

An Optimized Search-Enabled Hotel Recommender System

Conference

Title of PaperAn Optimized Search-Enabled Hotel Recommender System

OrganizationCentral University of Jammu, J & K

Published YearMay 2022

Indexed INScopus

Brain Tumor Segmentation using Fully Convolution Neural Network

Conference

Title of PaperBrain Tumor Segmentation using Fully Convolution Neural Network

OrganizationCentral University of Jammu, J & K

Published YearMay 2022

Indexed INScopus

VeDrishti: Big Data doctor with visionary emotion detection system

Conference

Title of PaperVeDrishti: Big Data doctor with visionary emotion detection system

OrganizationDepartment of Computer Applications and Department of Computer Science, Kattankulathur

Published YearFebruary 2022

Indexed INScopus

Big data Warehouse in Healthcare-Opportunities and Challenges

Conference

Title of PaperBig data Warehouse in Healthcare-Opportunities and Challenges

Author NameJigna S. Patel, Jitali Patel, Rupal A. Kapdi

OrganizationDepartment of Computer Applications and Department of Computer Science, Kattankulathur

Published YearFebruary 2022

Indexed INScopus

Early Onset Alzheimer Disease Classifi cation using Convolution Neural Network

Conference

Title of PaperEarly Onset Alzheimer Disease Classifi cation using Convolution Neural Network

Proceeding NameSmart Innovation, Systems and Technologies (SIST) Series

PublisherSpringer

Author NameHappy Ramani, Rupal Kapdi

OrganizationAditya Institute of Technology and Management

Year , VenueDecember 2021 , AITAM, Aandhra Pradesh, India

Indexed INScopus

3D Semantic Segmentation of Brain Tumor for Overall Survival Prediction

Journal

Journal NameLecture Notes in Computer Science

Title of Paper3D Semantic Segmentation of Brain Tumor for Overall Survival Prediction

PublisherSpringer

Volume Number12659

Page Number215-227

Published YearMarch 2021

ISSN/ISBN No1611-3349 / 978-3-030-72087-2

Indexed INScopus

Abstract

Glioma, a malignant brain tumor, requires immediate treatment to improve the survival of patients. The heterogeneous nature of Glioma makes the segmentation difficult, especially for sub-regions like necrosis, enhancing tumor, non-enhancing tumor, and edema. Deep neural networks like full convolution neural networks and an ensemble of fully convolution neural networks are successful for Glioma segmentation. The paper demonstrates the use of a 3D fully convolution neural network with a three-layer encoder-decoder approach. The dense connections within the layer help in diversified feature learning. The network takes 3D patches from T1, T2, T1c, and FLAIR modalities as input. The loss function combines dice loss and focal loss functions. The Dice similarity coefficient for training and validation set is 0.88, 0.83, 0.78 and 0.87, 0.75, 0.76 for the whole tumor, tumor core and enhancing tumor, respectively. The network achieves comparable performance with other state-of-the-art ensemble approaches. The random forest regressor trains on the shape, volumetric, and age features extracted from ground truth for overall survival prediction. The regressor achieves an accuracy of 56.8% and 51.7% on the training and validation sets.

A Survey and Analysis on Automated Glioma Brain Tumor Segmentation and Overall Patient Survival Prediction

Journal

Journal NameArchives of Computational Methods in Engineering

Title of PaperA Survey and Analysis on Automated Glioma Brain Tumor Segmentation and Overall Patient Survival Prediction

PublisherSpringer

Published YearMarch 2021

Indexed INScopus

Abstract

Glioma is the deadliest brain tumor with high mortality. Treatment planning by human experts depends on the proper diagnosis of physical symptoms along with Magnetic Resonance (MR) image analysis. Highly variability of a brain tumor in terms of size, shape, location, and a high volume of MR images make the analysis time-consuming. Automatic segmentation methods achieve a reduction in time with excellent reproducible results. The article aims to survey the advancement of automated methods for Glioma brain tumor segmentation. It is also essential to make an objective evaluation of various models based on the benchmark. Therefore, the 2012–2019 BraTS challenges evaluate the state-of-the-art methods. The complexity of the tasks facing this challenge has grown from segmentation (Task 1) to overall survival prediction (Task 2) to uncertainty prediction for classification (Task 3). The paper covers the complete gamut of brain tumor segmentation using handcrafted features to deep neural network models for Task 1. The aim is to showcase a complete change of trends in automated brain tumor models. The paper also covers end to end joint models involving brain tumor segmentation and overall survival prediction. All the methods are probed, and parameters that affect performance are tabulated and analyzed.

Brain Tumor Segmentation and Survival Prediction

Journal

Journal NameLecture Notes in Computer Science

Title of PaperBrain Tumor Segmentation and Survival Prediction

PublisherSpringer, Cham

Volume Number11992

Page Number338-348

Published YearMay 2020

ISSN/ISBN No1611-3349 / 978-3-030-46640-4

Indexed INScopus

Abstract

The paper demonstrates the use of the fully convolutional neural network for glioma segmentation on the BraTS 2019 dataset. Three-layers deep encoder-decoder architecture is used along with dense connection at the encoder part to propagate the information from the coarse layers to deep layers. This architecture is used to train three tumor sub-components separately. Sub-component training weights are initialized with whole tumor weights to get the localization of the tumor within the brain. In the end, three segmentation results were merged to get the entire tumor segmentation. Dice Similarity of training dataset with focal loss implementation for whole tumor, tumor core, and enhancing tumor is 0.92, 0.90, and 0.79, respectively. Radiomic features from the segmentation results predict survival. Along with these features, age and statistical features are used to predict the overall survival of patients using random forest regressors. The overall survival prediction method outperformed the other methods for the validation dataset on the leaderboard with 58.6% accuracy. This finding is consistent with the performance on the test set of BraTS 2019 with 57.9% accuracy.

Prediction of Overall Survival of Brain Tumor Patients

Conference

Title of PaperPrediction of Overall Survival of Brain Tumor Patients

Proceeding NameIEEE

PublisherIEEE

Author NameRupal A. Kapdi

OrganizationIEEE Region 10, Kochi

Year , VenueOctober 2019 , Kochi, India, India

Page Number31-35

Indexed INScopus

Abstract

Automated brain tumor segmentation plays an important role in the diagnosis and prognosis of the patient. In addition, features from the tumorous brain help in predicting patients’ overall survival. The main focus of this paper is to segment tumor from BRATS 2018 benchmark dataset and use age, shape and volumetric features to predict the overall survival of patients. The random forest classifier achieves overall survival accuracy of 59% on the test dataset and 67% on the dataset with resection status as gross total resection. The proposed approach uses fewer features but achieves better accuracy than state-of-the- art methods.

Brain Tumor Segmentation Using K-means–FCM Hybrid Technique

Journal

Journal NameAdvances in Intelligent Systems and Computing

Title of PaperBrain Tumor Segmentation Using K-means–FCM Hybrid Technique

PublisherSpringer

Volume Number696

Published YearMay 2018

ISSN/ISBN No2194-5357

Indexed INScopus, UGC List

Abstract

Automatic brain tumor segmentation and detection is always very challenging and difficult task with respect to accuracy which is more important as brain surgery is a critical and complicated process. The medical professional can interpret magnetic resonance images (MRI), but this task is time-consuming, error-prone and tedious. So automatic segmentation technique is needed which is the unsolved ch

Deep Learning for Automated Brain Tumor Segmentation in MRI Images

Book Chapter

Book NameSoft Computing based Medical Image Analysis

PublisherElsevier

Page Number183-201

Chapter TitleDeep Learning for Automated Brain Tumor Segmentation in MRI Images

Published YearJanuary 2018

ISSN/ISBN No978-0-12-813087-2

Indexed INScopus

Object Detection Using Deep Neural Network

Conference

Title of PaperObject Detection Using Deep Neural Network

Proceeding NameInternational Conference on Intelligent Computing and Control Systems

PublisherIEEE Explore

Author NameMalay Shah, Rupal Kapdi

OrganizationVaigai College of Engineering, Madurai, India

Year , VenueMay 2017 , Vaigai College of Engineering, Madurai, India

Page Number787-790

Indexed INScopus

Abstract

The problem discussed in this article is object detection using deep neural network especially convolution neural networks. Object detection was previously done using only conventional deep convolution neural network whereas using regional based convolution network [3] increases the accuracy and also decreases the time required to complete the program. The dataset used is PASCAL VOC 2012 which contains 20 labels. The dataset is very popular in image recognition, object detection, and other image processing problems. Supervised learning is also possible in implementing the problem using Decision trees or more likely SVM. But neural network works best in image processing because they can handle images well.

Case Study

Case Study TitleBrain Tumor Segmentation – Towards a better life

PublisherCSI Communication of India

Published YearDecember 2016

ISSN/ISBN No0970 647X

Indexed INScopus

Copy Move Forgery Detection Using SIFT and GMM

Conference

Title of PaperCopy Move Forgery Detection Using SIFT and GMM

Proceeding NameIEEE Explore

PublisherIEEE Explore

Author NameNeetu Yadav, Rupal Kapdi

OrganizationNirma University

Year , VenueNovember 2015 , Nirma University

Page Number1-4

ISSN/ISBN No978-1-4799-9990-3

Indexed INScopus

Abstract

Modifying or enhancing an image is ubiquitous but, when enhancement tends to change the interpretation of the image they are termed as an attempt of forgery on digital images. Copy move forgery (CMF) is a simple technique and has a number of well built tools in a number of image enhancement software. CMF detection techniques often tend to establish similarity between copied and pasted region on the same image as both are from same original image. Keypoint and block based techniques are used to determine the CMF. SIFT keypoints are combined with different techniques to accurately localize forgery. High imensionality of feature vector acts as a bottleneck in SIFT based analysis. We propose a method to detect CMF using SIFT descriptors which are clustered using GMM and segment the obtained suspect region speeding up the analysis.

Copy Move Forgery Detection Using SIFT Features – An Analysis

Journal

Journal NameNirma University Journal of Engineering and Technology

Title of PaperCopy Move Forgery Detection Using SIFT Features – An Analysis

PublisherNirma University

Volume Number4

Page Number11-14

Published YearJanuary 2015

ISSN/ISBN No2231-2870

Indexed INUGC List

Abstract

Emphasis on the need for authentication of image content has increased since images have been inferred to have some cognitive effects on human brain coupled along with the pervasiveness of images. General form of malicious image manipulations is Copy Move Forgery (CMF) in which a region is cloned from source location and pasted onto the same image at a target location. Techniques often used to hide or increase presence of an object in the image. This need to establish detection of image originality and authentication without using any prior details of the image has increased by many folds. In this paper, we present a list of comparisons on the detection of image forgeries mostly pertaining to CMF using SIFT method. An effort has been made to produce suffused paper by quoting most of the recent practices by providing an in-depth analysis of range of different techniques for forgery localization.

A novel multiclass classification based approach for playback attack detection in speaker verification systems

Journal

Journal NameJournal of Ambient Intelligence and Humanized Computing

Title of PaperA novel multiclass classification based approach for playback attack detection in speaker verification systems

PublisherSpringer Berlin Heidelberg

Volume Number14

Page Number16737-16748

Published YearDecember 2023

ISSN/ISBN No1868-5145

Indexed INScopus

XGB-RFE: An XGBoost Approach for Improved Playback Spoofing Detection in Automatic Speaker Verification Systems Using Recursive Feature Elimination

Conference

Title of PaperXGB-RFE: An XGBoost Approach for Improved Playback Spoofing Detection in Automatic Speaker Verification Systems Using Recursive Feature Elimination

Proceeding Name IEEE 11th Region 10 Humanitarian Technology Conference (R10-HTC)

PublisherIEEE

Author NameHarshil Sanghvi, Sapan H Mankad

Year , VenueOctober 2023 , Marwadi University, Rajkot

Page Number177-182

Voice Based Pathology Detection from Respiratory Sounds using Optimized Classifiers

Journal

Journal NameInternational Journal of Computing and Digital Systems

Title of PaperVoice Based Pathology Detection from Respiratory Sounds using Optimized Classifiers

PublisherUniversity of Bahrain

Volume Number13

Page Number327-339

Published YearJanuary 2023

ISSN/ISBN No2210-142X

Indexed INScopus

Detecting emotions from human speech: role of gender information

Conference

Title of PaperDetecting emotions from human speech: role of gender information

Proceeding NameIEEE Xplore

PublisherIEEE

OrganizationIEEE Tensymp 2022

Year , VenueJuly 2022 , IIT Bombay

Page Number1-6

ISSN/ISBN No2642-6102

Indexed INScopus

On the performance of empirical mode decomposition-based replay spoofing detection in speaker verification systems

Journal

Journal NameProgress in Artificial Intelligence

Title of PaperOn the performance of empirical mode decomposition-based replay spoofing detection in speaker verification systems

PublisherSpringer

Volume Number9

Page Number325-339

Published YearDecember 2020

ISSN/ISBN No2192-6360

Indexed INScopus, Web of Science

Voice liveness detection under feature fusion and cross-environment scenario

Journal

Journal NameMultimedia Tools and Applications

Title of PaperVoice liveness detection under feature fusion and cross-environment scenario

PublisherSpringer

Published YearJuly 2020

ISSN/ISBN No1573-7721

Indexed INScopus

Development of a Novel Database in Gujarati Language for Spoken Digits Classification

Book Chapter

Book NameCommunications in Computer and Information Science

PublisherSpringer, Singapore

Page Number208-219

Chapter TitleDevelopment of a Novel Database in Gujarati Language for Spoken Digits Classification

Published YearMay 2020

ISSN/ISBN No978-981-15-4828-4

Indexed INScopus

Investigating Feature Reduction Strategies for Replay Antispoofing in Voice Biometrics

Book Chapter

Book NameLecture Notes in Computer Science

PublisherSpringer, Cham

Page Number400-408

Chapter TitleInvestigating Feature Reduction Strategies for Replay Antispoofing in Voice Biometrics

Published YearDecember 2019

ISSN/ISBN No978-3-030-34872-4

Indexed INScopus

On the Performance of Cepstral Features for Voice-Based Gender Recognition

Book Chapter

Book NameInformation and Communication Technology for Intelligent Systems

PublisherSpringer, Singapore

Page Number327-333

Chapter TitleOn the Performance of Cepstral Features for Voice-Based Gender Recognition

Published YearJanuary 2019

ISSN/ISBN No978-981-13-1747-7

Indexed INScopus, UGC List

Detection of Mimicry Attacks on Speaker Verification System for Cartoon Characters’ Dataset

Book Chapter

Book NameInformation and Communication Technology for Intelligent Systems

PublisherSpringer, Singapore

Page Number319-326

Chapter TitleDetection of Mimicry Attacks on Speaker Verification System for Cartoon Characters’ Dataset

Published YearJanuary 2019

ISSN/ISBN No978-981-13-1747-7

Indexed INScopus, UGC List

Towards Development of Smart and Reliable Voice Based Personal Assistants

Conference

Title of PaperTowards Development of Smart and Reliable Voice Based Personal Assistants

Proceeding NameTENCON 2018-2018 IEEE Region 10 Conference

PublisherIEEE

Author NameSapan H Mankad, Viramya Shah, Sanjay Garg

Year , VenueOctober 2018 , Jeju, South Korea

Page Number2473-2478

Emotion Recognition from Sensory and Bio-Signals: A Survey

Book Chapter

Book NameAdvances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Page Number345-355

Chapter TitleEmotion Recognition from Sensory and Bio-Signals: A Survey

Published YearOctober 2018

ISSN/ISBN No978-981-13-1610-4

Indexed INScopus, UGC List

Investigating the Effect of Varying Window Sizes in Speaker Diarization for Meetings Domain

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer, Cham

Page Number361-369

Chapter TitleInvestigating the Effect of Varying Window Sizes in Speaker Diarization for Meetings Domain

Published YearAugust 2017

ISSN/ISBN No978-3-319-63645-0

Indexed INScopus, UGC List

Emerging Role of Crowdsourcing in MOOCs: A Review

Journal

Journal NameInternational Journal of Control Theory and Applications

Title of PaperEmerging Role of Crowdsourcing in MOOCs: A Review

PublisherInternational Science Press

Volume Number9

Page Number273-280

Published YearNovember 2016

ISSN/ISBN No09745572

Indexed INScopus

Automatic Weight Calculation Based Associative Classifier

Journal

Journal NameInternational Journal of Artificial Intelligence and Knowledge Discovery

Title of PaperAutomatic Weight Calculation Based Associative Classifier

PublisherRG Education Society

Volume Number6

Page Number1-5

Published YearOctober 2016

ISSN/ISBN No2231-0312

Indexed INOthers

Predicting learning behaviour of students: Strategies for making the course journey interesting

Conference

Title of PaperPredicting learning behaviour of students: Strategies for making the course journey interesting

Proceeding NameIntelligent Systems and Control (ISCO), 2016 10th International Conference on

PublisherIEEE

Year , VenueJuly 2016 , Karpagam Engineering College, Coimbatore

Page Number1-6

A new approach to address Subset Sum problem

Conference

Title of PaperA new approach to address Subset Sum problem

Proceeding NameConfluence The Next Generation Information Technology Summit (Confluence), 2014 5th International Conference -

PublisherIEEE

Year , VenueSeptember 2014 , Amity University, Noida

Page Number953-956

Indexed INOthers

Application of Software Defined Radio for Noise Reduction Using Empirical Mode Decomposition

Book Chapter

Book NameAdvances in Intelligent and Soft Computing

PublisherSpringer, Berlin, Heidelberg

Author NameDavid C. Wyld, Jan Zizka, Dhinaharan Nagamalai

Page Number113-121

Chapter TitleApplication of Software Defined Radio for Noise Reduction Using Empirical Mode Decomposition

Published YearMay 2012

ISSN/ISBN No978-3-642-30157-5

Indexed INScopus

Smart Inbox: A comparison based approach to classify the incoming mails

Journal

Journal NameInternational Journal of Artificial Intelligence and Knowledge Discovery

Title of PaperSmart Inbox: A comparison based approach to classify the incoming mails

PublisherRG Education Society

Volume Number1

Page Number29-32

Published YearJanuary 2011

ISSN/ISBN No2231-0312

Indexed INOthers

A Review of Non Invasive Blood Pressure Monitoring using Artificial Intelligence based Approaches

Conference

Title of PaperA Review of Non Invasive Blood Pressure Monitoring using Artificial Intelligence based Approaches

Proceeding Name2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC)

PublisherIEEE

Author NameVimal Sheoran, Gaurang Raval, Sharada Valiveti, Saurin Parikh

Organization(ICAAIC)

Year , VenueMay 2022 , Online

Page Number6

ISSN/ISBN No978-1-6654-9711-4

Indexed INScopus

Abstract

The problem of non-invasive blood pressure monitoring has been tackled by researchers for quite some time now and it still remains an open problem with ever developing solutions trying to satisfy measurement standards and experimentally successful solutions trying to find their way into the commercial market. The problem continues to be solved in 2022 and as more and more viable solutions are being proposed via different techniques, different experimental setups and different instrumentation, it is important to have a brief retrospect of the work that has already been done in this dynamic field. The study here compiles some of the most recent and the most effective work that has been done in the field of non-invasive blood pressure monitoring and categorises it into two broad fields, Pulse Transit Time based approaches and Artificial Intelligence based approaches. The study aims to be a starting point for people who are picking up this problem for the first time or wish to look at alternative approaches.

A Survey on Reading Habit of Library Users during COVID-19 Lockdown

Journal

Journal NameLibrary Philosophy and Practice

Title of PaperA Survey on Reading Habit of Library Users during COVID-19 Lockdown

PublisherLibrary Philosophy and Practice

Volume Number1A

Page Number6

Published YearSeptember 2020

ISSN/ISBN No15220222

Indexed INScopus

Abstract

E-Libraries has become more relevant in present situation of COVID-19 pandemic as it has caused an international lockdown in the world and India. Causing majority of the citizens to stay at home. The survey was conducted to study the reading habits of various library users (volunteers) during this situation. Besides the reading habit, the survey also collected the data for the various activities carried out by users at home. Main finding of the survey is that the users had taken keen interest to switch over to reading eBooks and 70% of student users and 53% of faculty users are reading more e-content especially books/magazines/research papers. Besides the extensive reading habit, the survey also discloses the greater involvement of users for learning/leisure/hobby activities at home. Student users have also reported spending more quality life with family members at home. Above all, the survey disclosed the reading of books as the main activity of the users during lockdown. This finding will inspire the organizations for establishing scalable and secure elibrary Infrastructure and for focusing on acquiring more eBooks for the eLibrary and provide better services to their users during situations like that of COVID-19.

Feature Weighted Linguistics Classifier for Predicting Learning Difficulty Using Eye Tracking

Journal

Journal NameACM Transactions on Applied Perception

Title of PaperFeature Weighted Linguistics Classifier for Predicting Learning Difficulty Using Eye Tracking

PublisherACM

Volume Number17-2

Page Number25

Published YearMay 2020

ISSN/ISBN No1544-3558

Indexed INScopus, Web of Science, EBSCO

Abstract

This article presents a new approach to predict learning difficulty in applications such as e-learning using eye movement and pupil response. We have developed 12 eye response features based on psycholinguistics, contextual information processing, anticipatory behavior analysis, recurrence fixation analysis, and pupillary response. A key aspect of the proposed approach is the temporal analysis of the feature response to the same concept. Results show that variations in eye response to the same concept over time are indicative of learning difficulty. A Feature Weighted Linguistics Classifier (FWLC) was developed to predict learning difficulty in real time. The proposed approach predicts learning difficulty with an accuracy of 90%.

Predicting Learning Difficulty based on Gaze and Pupil Response

Conference

Title of PaperPredicting Learning Difficulty based on Gaze and Pupil Response

Proceeding NameUMAP 2018 - Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization

PublisherACM 26th Conference on User Modeling, Adaptation and Personalization

OrganizationACM-UMAP

Year , VenueJuly 2018 , Singapore

Page Number5

ISSN/ISBN No978-145035784-5

Indexed INScopus

Eye Gaze Feature Classification for Predicting Levels of Learning

Conference

Title of PaperEye Gaze Feature Classification for Predicting Levels of Learning

Proceeding NameCEUR Workshop Proceedings, 8th International Workshop on Personalization Approaches in Learning Environments, PALE 2018

PublisherInternational Conference on Artificial intelligence in Education - PALE 2018, London, UK

OrganizationAIED- PALE

Year , VenueJune 2018 , London, USA

Page Number6

ISSN/ISBN No16130073

Indexed INScopus

High Bit-Depth Medical Image Compression with HEVC

Journal

Journal NameIEEE Journal of Biomedical and Health Informatics

Title of PaperHigh Bit-Depth Medical Image Compression with HEVC

PublisherIEEE Journal of Biomedical and Health Informatics

Volume Number22

Page Number9

Published YearMarch 2018

ISSN/ISBN No2168-2208

Indexed INScopus, PubMed, Web of Science

Predicting Information Context Processing from Eye Movements

Conference

Title of PaperPredicting Information Context Processing from Eye Movements

Proceeding Nameproceeding of the 19th European Conference on Eye Movements 2017

PublisherJournal of Eye Movement Research

OrganizationECEM

Year , VenueAugust 2017 , Germany, Europe

ISSN/ISBN No1995-8692

Indexed INOthers

Real-Time Learning Level Assessment using Eye Tracking

Conference

Title of PaperReal-Time Learning Level Assessment using Eye Tracking

Proceeding NameWorkshop proceeding on Computational and Mathematical models in Vision (MODVIS, a Satellite event of VSS 2017)

PublisherWorkshop proceeding on Computational and Mathematical models in Vision (MODVIS, a Satellite event of VSS 2017)

OrganizationMODVIS, a satellite event of VSS

Year , VenueMay 2017 , Tampa, Florida, USA

Indexed INOthers

Content Dependent Intra Mode Selection for Medical Image Compression using HEVC

Conference

Title of PaperContent Dependent Intra Mode Selection for Medical Image Compression using HEVC

Proceeding NameICCE

PublisherIEEE

OrganizationCES

Year , VenueJanuary 2016 , Las Vegas, USA

Page Number4

ISSN/ISBN No978-1-4673-8364-6

Indexed INScopus

Evaluation of HEVC compression for high bit depth medical images

Conference

Title of PaperEvaluation of HEVC compression for high bit depth medical images

Proceeding Name2016 IEEE International Conference on Consumer Electronics (ICCE)

PublisherIEEE

OrganizationICCE

Year , VenueJanuary 2016 , Las Vegas, USA

Page Number4

ISSN/ISBN No978-1-4673-8364-6

Indexed INScopus

Efficient algorithm for Auto Correction using n-gram indexing

Journal

Journal NameInternational Journal of Computer & Communication Technology

Title of PaperEfficient algorithm for Auto Correction using n-gram indexing

PublisherInternational Journal of Computer & Communication Technology

Volume Number3

Page Number5

Published YearJanuary 2014

ISSN/ISBN No 0975 - 7449

Indexed INOthers

A Geo-Location based Mobile Service that Dynamically Locates and Notifies the Nearest Blood Donors for Blood Donation during Medical Emergencies

Journal

Journal NameInternational Journal of Computer Applications (IJCA)

Title of PaperA Geo-Location based Mobile Service that Dynamically Locates and Notifies the Nearest Blood Donors for Blood Donation during Medical Emergencies

PublisherInternational Journal of Computer Applications (IJCA)

Volume Number88

Page Number6

Published YearJanuary 2014

ISSN/ISBN No0975-8887

Indexed INOthers

Analysis of Network Performance by Configuring Static ARP Based Network

Conference

Title of PaperAnalysis of Network Performance by Configuring Static ARP Based Network

Proceeding NameNational Seminar on Recent Advances on Information Technology (RAIT-2009)

PublisherNational Seminar on Recent Advances on Information Technology (RAIT-2009)

OrganizationNational Seminar on Recent Advances on Information Technology (RAIT-2009)

Year , VenueJanuary 2009 , Indian School of Mines,

Indexed INOthers

Regenerating vital facial keypoints for impostor identification from disguised images using CNN

Journal

Journal NameExpert Systems with Applications

Title of PaperRegenerating vital facial keypoints for impostor identification from disguised images using CNN

PublisherElsevier

Volume Number219

Page Number11

Published YearJune 2023

ISSN/ISBN No0957-4174

Indexed INScopus, Web of Science

Abstract

Technical advancements in the digital era have eased up the time required to complete complex tasks by a decisive rate. These advancements introduce several threats. Hence, there is a compelling need to provide security for systems against these threats. Identity and data thefts are the major threats which require immediate, effective and responsive solutions. Face recognition systems have evolved over the last few years, providing a suitable solution for authenticating an individual. However, the system running on facial recognition can be interfered by disguise. This paper discusses the approaches used in detecting a disguise and analysing the captured face among the other non-disguised faces in the dataset. The parameters used for detection and analysis are the keypoints of the face. These keypoints may be blocked, hidden or disoriented due to the presence of props on the face. The proposed approach aims to avoid this interference by creating an estimate of the face based on fewer available keypoints. The estimated face so created, is then matched with the available set of faces to determine the probabilistic chance of the matched person’s presence even though a disguise had been detected. Thus the solution provides a clear distinction if the image obtained proves to be of an impostor or an intruder with obfuscation with a said probability. The Disguised Faces in the Wild (DFW) dataset has been used.

An efficient bio-inspired routing scheme for tactical ad hoc networks

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperAn efficient bio-inspired routing scheme for tactical ad hoc networks

PublisherSCPE

Volume Number24

Page Number45-55

Published YearApril 2023

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science, EBSCO

Abstract

Ad hoc networks are temporary networks, created mainly for applications that are infrastructure-less. Such networks and network nodes demand special characteristics like mobile nodes having dynamic topology, wireless medium, heterogeneous deployment environment, and reactive or proactive routing depending on the nature of the network which includes network parameters such as node placement, mobility model, number of participants in the network, patterns of mobility, etc. Due to these characteristics and the mobility of network nodes, the process of routing is quite challenging in the ad hoc environment, especially when the node mobility is high. Bio-inspired routing can be an effective solution to meet all the design requirements and deal with the issues of tactical ad hoc networks. Different types of nature-inspired routing mechanisms are possible to use for tactical networks. This paper proposes the design of a novel Ant Colony Optimization-based routing strategy for ad hoc networks. Ant-based algorithms are dynamic and have adaptive behavior. Hence, they are competent for routing in ad hoc networks. Our proposed routing scheme is evaluated based on the network’s performance by varying different parameters. The performance of our proposed ACO-based routing approach is also compared to some existing ad hoc routing mechanisms. Different metrics in different deployment scenarios that can affect the efficiency of our proposed protocol are taken into consideration to evaluate the performance.

Profiling Cyber Crimes from News Portals Using Web Scraping

Conference

Title of PaperProfiling Cyber Crimes from News Portals Using Web Scraping

Proceeding Name Futuristic Trends in Networks and Computing Technologies

PublisherLecture Notes in Electrical Engineering, Springer

Author NameJoel Christian, Sharada Valiveti, Swati Jain

OrganizationNirma University

Year , VenueNovember 2022 , Nirma University

Page Number1007-1016

ISSN/ISBN No978-981-19-5037-7

Indexed INScopus, Web of Science

Abstract

In the past few years and especially during the pandemic period everything is going online. Everyone is connected through the Internet. With this rapid surge, cyber crimes are also skyrocketing. The government has made efforts to cope with situation but that is not enough. India faced a loss of more than Rs. 1.25 trillion ($16 billion USD) due to cyber crimes. Online news are a reliable source of information which are always up to date and freely available. In this paper, we conduct a survey of web scraping related previous works. Web scraping is a method to gather information from websites. With this knowledge we have proposed a system of web scraping where we gather cyber crime related news articles. From this data we can classify the crimes into their respective categories according to their regions and time period. This can help law enforcement and also create awareness amongst common people.

Blockchain based E-Voting: Opportunities and Challenges

Conference

Title of PaperBlockchain based E-Voting: Opportunities and Challenges

Proceeding Name7th International Conference on Communication and Electronic Systems ICCES-2022

PublisherIEEE

Author NamePimal Khanpara, Shivam Patel, Sharada Valiveti

Year , VenueJune 2022 , Coimbatore, India

Page Number855-861

Indexed INScopus

A Review of Non Invasive Blood Pressure Monitoring using Artificial Intelligence based Approaches

Conference

Title of PaperA Review of Non Invasive Blood Pressure Monitoring using Artificial Intelligence based Approaches

Proceeding NameProceedings - International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2022

PublisherInstitute of Electrical and Electronics Engineers Inc.

Author NameVimal Sheoran, Gaurang Raval, Sharada Valiveti, Saurin Parikh

Year , VenueMay 2022 , Salem,

Page Number101-106

ISSN/ISBN No978-166549710-7

Indexed INScopus

Anomaly-Based Intrusion Detection Systems for Mobile Ad Hoc Networks: A Practical Comprehension

Journal

Journal NameInternational Journal of Systems and Software Security and Protection

Title of PaperAnomaly-Based Intrusion Detection Systems for Mobile Ad Hoc Networks: A Practical Comprehension

PublisherIGI Global

Volume Number12

Page Number22

Published YearJuly 2021

ISSN/ISBN No 2640-4265

Indexed INOthers

Abstract

Ad hoc networks are used in heterogeneous environments like tactical military applications, where no centrally coordinated infrastructure is available. The network is required to perform self-configuration, dynamic topology management, and ensure the self-sustainability of the network. Security is hence of paramount importance. Anomaly-based intrusion detection system (IDS) is a distributed activity carried out by all nodes of the network in a cooperative manner along with other related network activities like routing, etc. Machine learning and its advances have found a promising place in anomaly detection. This paper describes the journey of defining the most suitable routing protocol for implementing IDS for tactical applications, along with the selection of the related suitable data set. The paper also reviews the latest machine learning techniques, implementation capabilities, and limitations.

Survey on Security Provisions in Named Data Networking

Journal

Journal NameInternational Journal of Applied Research on Information Technology and Computing

Title of PaperSurvey on Security Provisions in Named Data Networking

PublisherIndian Journals

Volume Number10

Page Number1-7

Published YearApril 2019

ISSN/ISBN No0975-8089

Indexed INIndian citation Index

Abstract

Named Data Networking (NDN) is considered to be a new proposed Internet architecture which is fundamentally different from host-centric communications in Internet. Here, instead of sending data packet to specific locations, NDN retrieves data by name. This methodology addresses the IP’s (Internet Protocol) communication issues as well as the digital distribution and management issues. This content has to be authenticated and signed by the originator of the content. This security model is core to NDN from functioning perspective. Internet raises multiple-challenge issues related to end to end communication. On the other hand, a NDN differs fundamentally in the host-to-host communication design of today’s internet. Hence, NDN gives rise to several research challenges. In NDN, focus is on digital signature and authentication. So, the public key using which the data is signed is to be made available to the intended stake holders. Hence, public key management issue is critical to NDN. The certificate format and related systems and protocols for supporting certificate distribution and revocation are intrinsic to the NDN architecture. In this paper, exhaustive survey of various security aspects that deal with provisioning of digital signature mechanisms for NDN are presented.

Multi-Objective Optimization Based Clustering in Wireless Sensor Networks Using Harmony Search Algorithm

Journal

Journal NameJournal on Communication Engineering and Systems

Title of PaperMulti-Objective Optimization Based Clustering in Wireless Sensor Networks Using Harmony Search Algorithm

Publisheri-Manager Publication

Volume Number7

Page Number1-12

Published YearOctober 2018

ISSN/ISBN No 2277-5242

Indexed INPubMed, Indian citation Index, EBSCO

Abstract

While planning and designing the operation of the wireless sensor network, major focus is always on balancing the energy consumption, lifetime of the node, and data aggregation. This may be achieved through suitable clustering technique, which helps in minimizing the distance between cluster head nodes and associated cluster members. Some of the algorithms like, LEACH, GCA (Genetic Clustering Algorithm), ERP (Evolutionary Routing Protocol), EAERP (Energy Aware Evolutionary Routing Protocol), HSA (Harmony Search Algorithm) work on similar lines. Due to variety of constraints inherently present in WSN, the objective function of clustering technique is of multi-objective nature. One of the objectives may be of minimization type whereas other may be of maximization type. Due to conflicting goals of objective functions it might be difficult to find a unique and optimal solution. This paper examines multiple solutions and compares performance of these candidate solutions for their applicability in the clustering process of WSN. Pareto optimality concept has been incorporated in the proposed work for multi-objective problem of clustering in WSN. Multiple objectives based approach with customized stopping criteria in the proposed work results into near optimal solutions with reduced simulation time requirements and improved network performance in terms of energy usage, data delivery from the sensor nodes to the base station.

Open Issues in Named Data Networking–A Survey

Conference

Title of PaperOpen Issues in Named Data Networking–A Survey

Proceeding NameInternational Conference on Information and Communication Technology for Intelligent Systems

PublisherSpringer

Year , VenueJuly 2018 , Ahmedabad

Indexed INScopus

Natural Language Interface for Multilingual Database

Conference

Title of PaperNatural Language Interface for Multilingual Database

Proceeding NameInternational Conference on Information and Communication Technology for Intelligent Systems

PublisherSpringer

Year , VenueJuly 2017 , Ahmedabad

Indexed INScopus

Optimization of clustering process in WSN with meta-heuristic techniques-A survey

Conference

Title of PaperOptimization of clustering process in WSN with meta-heuristic techniques-A survey

Proceeding NameRecent Advances in Information Technology (RAIT)

PublisherIEEE

Published YearJuly 2016

Indexed INScopus

Optimization of clustering process for WSN with hybrid harmony search and K-means algorithm

Conference

Title of PaperOptimization of clustering process for WSN with hybrid harmony search and K-means algorithm

Proceeding NameRecent Trends in Information Technology (ICRTIT)

PublisherIEEE

Published YearApril 2016

Indexed INScopus

Parallel generation of RSA keys—A review

Conference

Title of PaperParallel generation of RSA keys—A review

Proceeding NameCloud Computing, Data Science & Engineering-Confluence, 2017

PublisherIEEE

Year , VenueMarch 2016 , Delhi

Indexed INScopus

Analyzing The Performance of Bandwidth Starvation Attack in Lan

Journal

Journal NameInternational Journal of Advanced Research in Engineering & Technology (IJARET)

Title of PaperAnalyzing The Performance of Bandwidth Starvation Attack in Lan

Page Number145-153

Published YearFebruary 2014

Performance Evaluation Of Byzantine Flood Rushing Attack In Ad Hoc Network

Journal

Journal NameInternational Journal of Electronics and Communication Engineering & Technology (IJECET)

Title of PaperPerformance Evaluation Of Byzantine Flood Rushing Attack In Ad Hoc Network

Published YearFebruary 2014

ISSN/ISBN No0976-6464

Routing in Ad Hoc Network Using Ant Colony Optimization

Book Chapter

Book NameInternational Conference on Future Generation Communication and Networking FGCN 2010

PublisherCommunications in Computer and Information Science, vol 120. Springer, Berlin, Heidelberg

Page Number393-404

Chapter TitleRouting in Ad Hoc Network Using Ant Colony Optimization

Published YearDecember 2010

ISSN/ISBN No978-3-642-17604-3

Indexed INScopus

Trust Based Routing in Ad Hoc Network

Book Chapter

Book NameInternational Conference on Future Generation Communication and Networking FGCN 2010

PublisherCommunications in Computer and Information Science, vol 120. Springer, Berlin, Heidelberg

Page Number381-392

Chapter TitleTrust Based Routing in Ad Hoc Network

Published YearDecember 2010

ISSN/ISBN No978-3-642-17604-3

Indexed INScopus

Non-Repudiation in Ad Hoc Networks

Book Chapter

Book NameInternational Conference on Future Generation Communication and Networking

Publisher Communications in Computer and Information Science, Springer

Page Number405-415

Chapter TitleNon-Repudiation in Ad Hoc Networks

Published YearDecember 2010

ISSN/ISBN No978-3-642-17604-3

Indexed INScopus

Comparative Study of Distributed Intrusion Detection in ad hoc networks

Journal

Journal NameInternational Journal of Computer Applications

Title of PaperComparative Study of Distributed Intrusion Detection in ad hoc networks

PublisherInternational Journal of Computer Applications

Volume Number8

Page Number11-16

Published YearOctober 2010

ISSN/ISBN No0975 - 8887

Indexed INEBSCO

Abstract

In recent years ad hoc networks are widely used because of mobility and open architecture nature. But new technology always comes with its own set of problems. Security of ad hoc network is an area of widespread research in recent years. Some unique characteristics of ad hoc network itself are an immense dilemma in the way of security.

Parkinson’s Disease Detection Using Machine Learning

Conference

Title of PaperParkinson’s Disease Detection Using Machine Learning

PublisherSpringer

Author Name Shivani Desai

OrganizationICISS 2022

Published YearFebruary 2022

Indexed INScopus

Insights of Deep Learning Applications

Conference

Title of PaperInsights of Deep Learning Applications

PublisherIEEE Explore

Author Name Shivani Desai

OrganizationICECA-2021

Published YearDecember 2021

Indexed INScopus

Email autocomplete function using RNN encoder-decoder sequence to sequence model

Conference

Title of PaperEmail autocomplete function using RNN encoder-decoder sequence to sequence model

PublisherIEEE Explore

Author NameShivani desai

OrganizationICECA-2021

Published YearDecember 2021

Indexed INScopus

Deep learning-based scheme to diagnose Parkinson's disease

Journal

Journal NameExpert Systems

Title of Paper Deep learning-based scheme to diagnose Parkinson's disease

Publisherwiley

Published YearMay 2021

Indexed INScopus

Intrusion Detection System - Deep Learning Perspective

Conference

Title of PaperIntrusion Detection System - Deep Learning Perspective

Proceeding NameIEEE Explore

PublisherIEEE Explore

Author NameShivani Desai ; Bhavyang Dave ; Tarjni Vyas ; Anuja R. Nair

OrganizationJCT College of Engineering and Tchnology

Published YearMarch 2021

Indexed INScopus

Fog Data Processing and Analytics for Health Care-Based IoT Applications

Book Chapter

Book NameFog Data Analytics for IoT Applications

PublisherSpringer

Author NameTarjni Vyas , Shivani Desai, and Anand Ruparelia

Chapter TitleFog Data Processing and Analytics for Health Care-Based IoT Applications

Published YearAugust 2020

The Fog Computing Paradigm: A Rising Need of IoT World

Conference

Title of PaperThe Fog Computing Paradigm: A Rising Need of IoT World

Proceeding NameProceedings of the 2nd International Conference on Data Engineering and Communication Technology

PublisherSpringer

OrganizationICDECT 2017

Page Number387-393

Published YearOctober 2018

ISSN/ISBN No978-981-13-1609-8

Indexed INScopus

Traffic Signal Synchronization Using Computer Vision and Wireless Sensor Networks

Conference

Title of PaperTraffic Signal Synchronization Using Computer Vision and Wireless Sensor Networks

Proceeding NameArtificial Intelligence and Evolutionary Computations in Engineering Systems

PublisherSpringer

OrganizationICAIECES 2015

Page Number 743-751

Published YearFebruary 2016

ISSN/ISBN No978-81-322-2654-3

Indexed INScopus

Blockchain-Driven Real-Time Incentive Approach for Energy Management System

Journal

Journal NameMathematics

Title of PaperBlockchain-Driven Real-Time Incentive Approach for Energy Management System

PublisherMDPI

Volume Number11

Page Number928

Published YearFebruary 2023

ISSN/ISBN No22277390

Indexed INScopus, Web of Science

Data Encryption Approach Using Hybrid Cryptography and Steganography with Combination of Block Ciphers

Conference

Title of Paper Data Encryption Approach Using Hybrid Cryptography and Steganography with Combination of Block Ciphers

Proceeding NameCommunications in Computer and Information Science

PublisherSpringer Nature Switzerland

Author NameSmita Agrawal

Organization1st International Conference on Advancements in Smart Computing and Information Security, ASCIS 2022

Year , VenueJanuary 2023 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number59-69

ISSN/ISBN No18650929

Indexed INScopus

Blockchain and Reverse Auction-based EVs Energy Trading Approach for Optimal Pricing

Conference

Title of PaperBlockchain and Reverse Auction-based EVs Energy Trading Approach for Optimal Pricing

Proceeding NameProceedings of the 13th International Conference on Cloud Computing, Data Science and Engineering, Confluence 2023

PublisherIEEE

Author NameSmita Agrawal

Organization Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Year , VenueJanuary 2023 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number412 - 417

ISSN/ISBN No978-166546263-1

Indexed INScopus

A Review on Standardizing Electric Vehicles Community Charging Service Operator Infrastructure

Journal

Journal NameApplied Sciences (Switzerland)

Title of PaperA Review on Standardizing Electric Vehicles Community Charging Service Operator Infrastructure

PublisherMDPI

Volume Number12

Page Number12096

Published YearNovember 2022

ISSN/ISBN No20763417

Indexed INScopus

Blockchain and Deep Learning-Based Fault Detection Framework for Electric Vehicles

Journal

Journal NameMathematics

Title of PaperBlockchain and Deep Learning-Based Fault Detection Framework for Electric Vehicles

PublisherMDPI

Volume Number10

Page Number3626

Published YearOctober 2022

ISSN/ISBN No22277390

Indexed INScopus

Blockchain and IoT-Driven Optimized Consensus Mechanism for Electric Vehicle Scheduling at Charging Stations

Journal

Journal NameSustainability (Switzerland)

Title of PaperBlockchain and IoT-Driven Optimized Consensus Mechanism for Electric Vehicle Scheduling at Charging Stations

PublisherMDPI

Volume Number14

Page Number12800

Published YearOctober 2022

ISSN/ISBN No20711050

Indexed INScopus

Blockchain and Double Auction-Based Trustful EVs Energy Trading Scheme for Optimum Pricing

Journal

Journal NameMathematics

Title of PaperBlockchain and Double Auction-Based Trustful EVs Energy Trading Scheme for Optimum Pricing

PublisherMDPI

Volume Number10

Page Number2748

Published YearAugust 2022

ISSN/ISBN No22277390

Indexed INScopus

A Taxonomy on Smart Healthcare Technologies: Security Framework, Case Study, and Future Directions

Journal

Journal NameJournal of Sensors

Title of PaperA Taxonomy on Smart Healthcare Technologies: Security Framework, Case Study, and Future Directions

PublisherHindawi

Volume Number2022

Page Number-

Published YearJuly 2022

ISSN/ISBN No1687725X

Indexed INScopus

A Secure DBA Management System: A Comprehensive Study

Conference

Title of PaperA Secure DBA Management System: A Comprehensive Study

Proceeding NameLecture Notes in Networks and Systems

PublisherSpringer Nature Singapore

Author NameSmita Agrawal

Organization3rd International Conference on Computing, Communications, and Cyber-Security, IC4S 2021

Year , VenueJuly 2022 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number883 - 893

ISSN/ISBN No23673370

Indexed INOthers

Concurrency Control in Distributed Database Systems: An In-Depth Analysis

Conference

Title of PaperConcurrency Control in Distributed Database Systems: An In-Depth Analysis

Proceeding NameLecture Notes in Networks and Systems

PublisherSpringer Nature Singapore

Author NameSmita Agrawal

OrganizationComputer Science and Engineering Department, Nirma University, Ahmedabad, India

Year , VenueJuly 2022 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number223 - 234

ISSN/ISBN No23673370

Indexed INScopus

Blockchain-based secure and trusted data sharing scheme for autonomous vehicle underlying 5G

Journal

Journal NameJournal of Information Security and Applications

Title of PaperBlockchain-based secure and trusted data sharing scheme for autonomous vehicle underlying 5G

PublisherElsevier

Volume Number67

Page Number103179

Published YearJune 2022

ISSN/ISBN No22142134

Indexed INScopus

PADaaV: Blockchain-Based Parking Price Prediction Scheme for Sustainable Traffic Management

Journal

Journal NameIEEE Access

Title of PaperPADaaV: Blockchain-Based Parking Price Prediction Scheme for Sustainable Traffic Management

PublisherIEEE

Volume Number10

Page Number50125-50136

Published YearMay 2022

ISSN/ISBN No21693536

Indexed INScopus

Blockchain and Zero-Sum Game-based Dynamic Pricing Scheme for Electric Vehicle Charging

Conference

Title of PaperBlockchain and Zero-Sum Game-based Dynamic Pricing Scheme for Electric Vehicle Charging

Proceeding NameINFOCOM WKSHPS 2022 - IEEE Conference on Computer Communications Workshops

PublisherIEEE

Author NameSmita Agrawal

Organization2022 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2022

Year , VenueMay 2022 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number1-6

ISSN/ISBN No978-166540926-1

Indexed INScopus

Blockchain and Stackleberg Game-based Fair and Trusted Data Pricing Scheme for Ride Sharing

Conference

Title of PaperBlockchain and Stackleberg Game-based Fair and Trusted Data Pricing Scheme for Ride Sharing

Proceeding Name2022 IEEE International Conference on Communications Workshops, ICC Workshops 2022

PublisherIEEE

Author NameSmita Agrawal

Organization Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Year , VenueMay 2022 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number854-859

ISSN/ISBN No978-166542671-8

Indexed INScopus

Neuromorphic Computing: Review of Architecture, Issues, Applications and Research Opportunities

Conference

Title of PaperNeuromorphic Computing: Review of Architecture, Issues, Applications and Research Opportunities

Proceeding NameLecture Notes in Electrical Engineering

PublisherSpringer Singapore

Author NameSmita Agrawal

Organization4th International Conference on Recent Innovations in Computing, ICRIC 2021

Year , VenueApril 2022 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number371 - 383

ISSN/ISBN No18761100

Indexed INScopus

A Comprehensive Study of “etcd”—An Open-Source Distributed Key-Value Store with Relevant Distributed Databases

Conference

Title of PaperA Comprehensive Study of “etcd”—An Open-Source Distributed Key-Value Store with Relevant Distributed Databases

Proceeding NameLecture Notes in Electrical Engineering

PublisherSpringer Nature Singapore

Author NameSmita Agrawal

Organization2nd International Conference on Emerging Technologies for Computing, Communications, and Smart Cities, ETCCS 2021

Year , VenueApril 2022 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number481-489

ISSN/ISBN No18761100

Indexed INScopus

Blockchain and federated learning-based security solutions for telesurgery system: a comprehensive review

Journal

Journal NameTurkish Journal of Electrical Engineering and Computer Sciences

Title of PaperBlockchain and federated learning-based security solutions for telesurgery system: a comprehensive review

PublisherTurkish Journal of Electrical Engineering and Computer Sciences

Volume Number30

Page Number2446-2488

Published YearJanuary 2022

ISSN/ISBN No13000632

Indexed INScopus

Enhanced Secure ATM authentication using NFC Technology and Iris Verification

Journal

Journal NameScalable Computing

Title of PaperEnhanced Secure ATM authentication using NFC Technology and Iris Verification

PublisherSCPE- Institute e-Austria Timisoara

Volume Number22(2)

Page Number273–282

Published YearOctober 2021

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science

Abstract

In today’s world technology has advanced to such an extent that it is interchangeable with connection and convenience. ATM was one of the major breakthroughs, and over the time it has provided better convenience in fulfilling one’s banking needs. Although, there are certain predicaments that such ATM transactions are susceptible too. The conventional PIN based authentication that is presently accustomed in all ATM apparatus is liable to shoulder surfing, hassle in remembering the multiple PIN and the rest. The physical card brings along setbacks in particular, wearing out of the magnetic strip attributable to frequent usage, losing or getting it stolen. Aside from these there are other unlawful activities that are carried upon. The objective of this paper is to present a solution to the above stated problems. In contrast to standard architecture, the proposed solution incorporates NFC enabled smartphones as a substitute for physical card and iris based authentication for PIN.

AI Approaches for Breast Cancer Diagnosis: A Comprehensive Study

Conference

Title of Paper AI Approaches for Breast Cancer Diagnosis: A Comprehensive Study

Proceeding NameAdvances in Intelligent Systems and Computing,

PublisherSpringer, Singapore

Author NamePatel H.J., Oza P., Agrawal S.

Page Number-

Published YearAugust 2021

ISSN/ISBN No978-981-16-3071-2

Indexed INScopus, EBSCO, Others

Abstract

According to the report of the World Health Organization (WHO), the most common and dangerous disease among women is known to be breast cancer. Breast cancer is a life-threatening disease and may cause death of women. Early detection of breast cancer can decrease mortality rate and improve survival rate in women. Various artificial intelligence (AI) approaches have been used by the research community to build computer-aided diagnosis (CAD) systems for early detection of breast cancer. This study presents various breast imaging modalities used for the cancer diagnosis, related work in this domain, various pre-processing techniques to improve the quality of breast images and applications of machine learning (ML) for breast imaging. The study also presents various deep learning (DL) approaches to build a system for automated breast cancer diagnosis. Various pre-trained deep learning models are also presented in the study. Due to an imbalanced and inconsistent dataset, AI models may not perform well. We have also discussed various techniques to improve the performance of the model. Prediction, segmentation, and classification deep neural network models along with the various imaging modalities are presented which are beneficial for the diagnosis process of breast cancer.

SAG Cluster: An unsupervised graph clustering based on collaborative similarity for community detection in complex networks

Journal

Journal NamePhysica A: Statistical Mechanics and its Applications

Title of PaperSAG Cluster: An unsupervised graph clustering based on collaborative similarity for community detection in complex networks

PublisherElsevier

Volume Number563

Page Number1-16

Published YearFebruary 2021

ISSN/ISBN No0378-4371

Indexed INScopus, PubMed, Web of Science

Abstract

Many real-world social networks such as brain graph, protein structure, food web, transportation system, World Wide Web, online social networks exist in the form of a complex network. In such complex networks, pattern identification or community detection requires extra effort in which identifying community is a significant problem in various research areas. Most of the clustering methods on graphs predominantly emphasize on the topological structure without considering connectivity between vertices and not bearing in mind the vertex properties/attributes or similarity-based on indirectly connected vertices. A novel clustering algorithm SAG-Cluster with K-medoids framework presented for detecting communities using a collaborative similarity measure which considers attribute importance in case the pair of disconnected nodes. A novel path strategy using classic Basel problem for the indirectly connected node as well as balanced attribute similarity and distance function is proposed. On two real data sets, experimental results show the effectiveness of SAG-Cluster with the comparison of other relevant methods.

Diabetes Prediction Using Machine Learning

Conference

Title of PaperDiabetes Prediction Using Machine Learning

Proceeding NameLecture Notes in Networks and Systems

PublisherSpringer Singapore

Author NameSmita Agrawal

Organization2nd International Conference on Computing, Communications, and Cyber-Security, IC4S 2020

Year , VenueJanuary 2021 , Institute of Technology, Nirma University, Department of Computer Science and Engineering, Ahmedabad, India

Page Number703 - 715

ISSN/ISBN No23673370

Indexed INScopus

Data Ingestion and Analysis Framework for Geoscience Data

Book Chapter

Book NameLecture Notes in Electrical Engineering

PublisherSpringer, Singapore

Page Number809-820

Chapter TitleData Ingestion and Analysis Framework for Geoscience Data

Published YearJanuary 2021

ISSN/ISBN No978-981-15-8296-7

Indexed INScopus

Abstract

Big earth data analytics is an emerging field since environmental sciences are probably going to profit by its different systems supporting the handling of the enormous measure of earth observation data, gained and produced through perceptions. It additionally benefits by giving enormous stockpiling and registering capacities. Be that as it may, big earth data analytics requires explicitly planned instruments to show specificities as far as significance of the geospatial data, intricacy of handling, and wide heterogeneity of information models and arrangements [1]. Data ingestion and analysis framework for geoscience data is the study and implementation of extracting data on the system and processing it for change detection and to increase the interoperability with the help of analytical frameworks which aims at facilitating the understanding of the data in a systematic manner. In this paper, we address the challenges and opportunities in the climate data through the climate data toolbox for MATLAB [2] and how it can be beneficial to resolve various climate-change-related analytical difficulties.

Predictive maintenance and monitoring of industrial machine using machine learning

Journal

Journal NameScalable Computing

Title of PaperPredictive maintenance and monitoring of industrial machine using machine learning

PublisherWest University of Timisoara

Volume Number20(4)

Page Number663-668

Published YearDecember 2019

ISSN/ISBN No18951767

Indexed INScopus, Web of Science, EBSCO

Abstract

Machine learning is one of the break-through technologies of the modern digital world. It's applications are found in various research domain such as medicine, image processing, production and manufacturing, aviation and autonomics and many more. To efficiently run a machine, it's maintenance and its monitoring automation system play key role. The major problem we are targetting is to overcome the lack of an automation system which can give accuracy rate of the production machine at a given instance of time. Also the important energy meter parameters required to make power report in automation system for addressing the production issues, at given interval of time, were also not recorded. Thus in this paper, we describe how machine learning techniques is used for prediction of accuracy of running production machine. To address this issues, we have used supervised machine learning technique of Binary decision tree using CART method and for power report, while the data is fetched using RS232 to RS485 convertor via Modbus communication protocol. Using CART we have predicted the machine accuracy at a given time with specific energy meter readings as its input features. This paper discusses the problem definition identified, data analysis of energy meter data and it's fetching and at the end ML techniques applied to predict accuracy of running production machine. In the end we prepare various power reports of the different machines from the fetched parameters as well as produce a graphical warning of deteriorate performance of the machine at a given instance of the time. © 2019 SCPE.

IoT-based home automation with smart fan and AC using NodeMCU

Book Chapter

Book NameLecture Notes in Electrical Engineering

PublisherSpringer

Page Number197-207

Chapter Title IoT-based home automation with smart fan and AC using NodeMCU

Published YearNovember 2019

ISSN/ISBN NoISSN: 18761100 ISBN: 978-303029406-9

Indexed INScopus, PubMed, EBSCO

Clustering Algorithm for Community Detection in Complex Network: a Comprehensive Review

Journal

Journal NameRecent Patents on Computer Science

Title of PaperClustering Algorithm for Community Detection in Complex Network: a Comprehensive Review

PublisherBentham Science

Volume Number19

Published YearJune 2019

ISSN/ISBN NoISSN (Print): 2666-2558 ISSN (Online): 2666-2566

Indexed INScopus, EBSCO, Others

CSG cluster: A collaborative similarity based graph clustering for community detection in complex networks

Journal

Journal NameInternational Journal of Engineering and Advanced Technology

Title of PaperCSG cluster: A collaborative similarity based graph clustering for community detection in complex networks

PublisherBlue Eyes Intelligence Engineering and Sciences Publication

Volume Number8(5)

Page Number1682-1687

Published YearJune 2019

ISSN/ISBN No22498958

Indexed INScopus, Indian citation Index

Abstract

Many real-world social networks exist in the form of the complex network, which includes very large scale structured or unstructured data. The large scale networks like brain graph, protein structure, food web, transportation system, WorldWide Web, online social network are sparsely connected globally and densely connected locally. For detecting densely connected clusters from complex networks, graph clustering methods are useful. Graph clustering performs through partition a graph based on edge cut, vertex cut, edge betweeness, vertex similarities, topological structure of graph. Most of the graph clustering methods predominantly emphasis on topological structure of graph and not bearing in mind the vertex properties/attributes or similarity based on indirectly connected vertices. In this paper, we propose a CSGCluster, a novel collaborative similarity based graph clustering methodfor community detection ina complex network. In this, we introduce concepts, Approachable Unitto find similarities for directly connected vertices and introduced shortest path strategy for indirectly connected vertices and based on that a graph clustering method, CSG-Cluster is presented. For this, a new collaborative similarity approach is adopted to compute vertex similarities. In the CSG-Cluster method, weform a group of vertices based on distance measures based on calculated similarity with the help of K-Medoids framework. Performs experiment on two real datasets with other relevant methods in whichresults shows the effectiveness of CSG-Cluster. This idea is suitable for graph database to apply collaborative similarity during query processing.

Homomorphic Cryptography and Its Applications in Various Domains

Journal

Journal NameLecture Notes in Networks and Systems

Title of PaperHomomorphic Cryptography and Its Applications in Various Domains

PublisherSpringer Nature Singapore Pte Ltd.

Volume Number55

Page Number269-278

Published YearNovember 2018

ISSN/ISBN No2367-3370

Indexed INScopus

Abstract

Homomorphic encryption (HE) is an encryption technique where operations are performed on ciphertext. This encryption method can be used in varieties of applications by using public key algorithms. For transferring data from one place to another, there are various encryption algorithms for storage of data and securing the operations, but they do not preserve privacy. HE is useful in various applications in which HE performs the different operations on encrypted data and provides results after calculations performed directly on the plaintext. Nowadays, security of information and calculations to deal with the data of big business has expanded massively. In any case, a basic issue emerges when there is a necessity of registering on such encrypted information where protection is built up. This paper represents homomorphic cryptosystems for preserving security, properties, and categories of homomorphic encryption. In addition to this, privacy-preserving applications of homomorphic cryptosystems in the field of cloud computing, private information retrieval, and data aggregation in wireless sensor network are also presented. © 2019, Springer Nature Singapore Pte Ltd.

SUTRON: IoT-based Industrial/Home Security and Automation System to Compete the Smarter World

Journal

Journal NameInternational Journal of Applied Research on Information Technology and Computing

Title of PaperSUTRON: IoT-based Industrial/Home Security and Automation System to Compete the Smarter World

PublisherIndian Journals

Volume Number8

Page Number193-198

Published YearAugust 2017

ISSN/ISBN NoPrint ISSN : 0975-8070. Online ISSN : 0975-8089

Indexed INIndian citation Index, EBSCO, UGC List

Abstract

Print ISSN : 0975-8070. Online ISSN : 0975-8089.

Web Crawler: Review of Different Types of Web Crawler, Its Issues, Applications and Research Opportunities

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of PaperWeb Crawler: Review of Different Types of Web Crawler, Its Issues, Applications and Research Opportunities

PublisherInternational Journal of Advanced Research in Computer Science

Volume Number8 , issue-3

Page Number1199-1202

Published YearMarch 2017

ISSN/ISBN No0976-5697

Indexed INEBSCO, Others

Abstract

Today's search engines are equipped with dedicated agents known as “web crawlers” keen to crawling large web contents online which are analyzed and indexed and make the content available to users. Crawlers act together with thousands of web servers over periods expanding from weeks to several years. These crawlers visits several thousands of pages every second, includes a high-performance fault manager, are platform independent or dependent and are able to get used to a wide range of configurations without including additional hardware. This paper is focused on prerequisites of crawler, process of crawling and different types of crawlers. This paper give review about some potential issues related to crawler, applications and research area of web crawler.

A STUDY ON GRAPH STORAGE DATABASE OF NOSQL

Journal

Journal NameInternational Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)

Title of PaperA STUDY ON GRAPH STORAGE DATABASE OF NOSQL

PublisherInternational Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)

Volume Number5

Page Number33-39

Published YearFebruary 2016

ISSN/ISBN No2019-1015

Indexed INOthers

Abstract

Big Data is used to store huge volume of both structured and unstructured data which is so large and is hard to process using current / traditional database tools and software technologies. The goal of Big Data Storage Management is to ensure a high level of data quality and availability for business intellect and big data analytics applications. Graph database which is not most popular NoSQL database compare to relational database yet but it is a most powerful NoSQL database which can handle large volume of data in very efficient way. It is very difficult to manage large volume of data using traditional technology. Data retrieval time may be more as per database size gets increase. As solution of that NoSQL databases are available. This paper describe what is big data storage management, dimensions of big data, types of data, what is structured and unstructured data, what is NoSQL database, types of NoSQL database, basic structure of graph database, advantages, disadvantages and application area and comparison of various graph database

BIG DATA ANALYTICS: CHALLENGES AND APPLICATIONS FOR TEXT, AUDIO, VIDEO, AND SOCIAL MEDIA DATA

Journal

Journal NameInternational Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)

Title of PaperBIG DATA ANALYTICS: CHALLENGES AND APPLICATIONS FOR TEXT, AUDIO, VIDEO, AND SOCIAL MEDIA DATA

PublisherInternational Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)

Volume Number5

Page Number41-51

Published YearFebruary 2016

ISSN/ISBN No2019-1015

Indexed INEBSCO, Others

Abstract

All types of machine automated systems are generating large amount of data in different forms like statistical, text, audio, video, sensor, and bio-metric data that emerges the term Big Data. In this paper we are discussing issues, challenges, and application of these types of Big Data with the consideration of big data dimensions. Here we are discussing social media data analytics, content based analytics, text data analytics, audio, and video data analytics their issues and expected application areas. It will motivate researchers to address these issues of storage, management, and retrieval of data known as Big Data. As well as the usages of Big Data analytics in India is also highlighted.

SURVEY ON MONGODB: AN OPEN-SOURCE DOCUMENT DATABASE

Journal

Journal NameInternational Journal of Advanced Research in Engineering and Technology

Title of PaperSURVEY ON MONGODB: AN OPEN-SOURCE DOCUMENT DATABASE

PublisherIAEME Publication

Volume Number6

Page Number1-11

Published YearDecember 2015

ISSN/ISBN NoPrint: 0976-6480 and Inline: 0976-6499

Indexed INOthers

Abstract

MongoDB is open source cross platform database. It is classified as NoSQL (Not Only SQL). It is written in C++ and it follows document oriented data model. It is database model which provides dynamic schema. It uses features like Map/Reduce, Auto-sharding and MongoDump etc. Using these features MongoDB provides high performance, where Map/Reduce is efficient data arrangement, Auto-sharding is storing data on across the different machines, Backup facilities and many more. It has collections as table and each collection can store different kinds of data. It stores data in JSON like structure. Unlike the RDBMS databases it can store unstructured data as well. It can process and handle large amount of data more efficiently than RDBMS. It is ACID system like RDBMS databases. MongoDB mainly used in such application which produces and uses vast amount of data. Like blogs or sites which produces or stores unstructured data. It can be used to in applications which stores structured and semi-structured data as well

Age Invariant Face Recognition: A Survey on the Recent Developments, Challenges and Potential Future Directions

Journal

Journal NameInternational Journal of Engineering Trends and Technology

Title of PaperAge Invariant Face Recognition: A Survey on the Recent Developments, Challenges and Potential Future Directions

Volume NumberVolume: 5

Published YearAugust 2023

ISSN/ISBN No ISSN No. :2231-5381

Indexed INScopus

Age invariant face recognition using discriminative tensor subspace learning with fuzzy based classification

Journal

Journal NameExpert Systems

Title of PaperAge invariant face recognition using discriminative tensor subspace learning with fuzzy based classification

Publisherwilley

Volume NumberVolume: 40 Issue - 7

Published YearMarch 2023

ISSN/ISBN NoISSN:1468-0394

Indexed INScopus

Unsupervised learning models of invariant features in images: Recent developments in multistage architecture approach for object detection

Journal

Journal NameInternational Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)

Title of PaperUnsupervised learning models of invariant features in images: Recent developments in multistage architecture approach for object detection

PublisherInternational Journal on Soft Computing, Artificial Intelligence and Applications (IJSCAI)

Volume Number5

Page Number63-70

Published YearFebruary 2016

ISSN/ISBN No2319-1015

Indexed INEBSCO, Others

Face Detection And Tracking: A Comparative Study Of Two Algorithms

Journal

Journal NameInternational Journal Of Computer Science And Communication

Title of PaperFace Detection And Tracking: A Comparative Study Of Two Algorithms

PublisherIJCSE

Volume Number7

Page Number76-82

Published YearSeptember 2015

ISSN/ISBN No0973-7391

Indexed INUGC List

An Optimized and Efficient Multi Parametric Scheduling Approach for Multi-Core Systems

Journal

Journal NameInternational Journal of Computer Theory and Engineering

Title of PaperAn Optimized and Efficient Multi Parametric Scheduling Approach for Multi-Core Systems

PublisherInternational Journal of Computer Theory and Engineering (IJCTE)

Volume Number5

Page Number391-395

Published YearJune 2013

ISSN/ISBN No1793-820

Indexed INEBSCO, Others

Transfer Learning-based Emotion Detection System in Cultivating Workplace Harmony

Conference

Title of PaperTransfer Learning-based Emotion Detection System in Cultivating Workplace Harmony

Proceeding Name2024 20th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP)

PublisherIEEE

Author NamePremal P. Shah; Nilesh Kumar Jadav; Vatsalkumar Makwana; Harshal Trivedi; Jitendra Bhatia; Sudeep Tanwar; Hossein Shahinzadeh

OrganizationIEEE

Year , VenueMarch 2024 , Babol, Iran, Islamic Republic of

Page Number1-6

ISSN/ISBN No2640-5768

Indexed INScopus

Abstract

The technological advancements made the organizations achieve more business profits and attain new horizons that significantly impact on employee stress and mental-well well-being. Moreover, due to the advent of Artificial intelligence (AI), which offers automotive tasks and efficiency gains, the employee get fear of losing their jobs. Due to this, the employee suffers from excessive stress and mental health issues. Therefore, emotion detection is imperative in such a stressful workplace environment. Inspired by this, we proposed a transfer learning-based emotion detection system to improve the workplace environment. For that, a facial emotion dataset is utilized, which comprises grayscale images of employee faces having emotions such as fear, neutral, anger, sadness, happiness, surprise, and disgust. Then, we used transfer learning-based pre-trained models with the intention of reducing the computational overhead of AI training. We employed ResNet, Inception, MobileNet, and EfficientNet which offer an effective accuracy while detecting the emotions of the employee. This strategic use of pre-existing models not only optimizes efficiency but also enhances the overall effectiveness of our facial emotion analysis system, ensuring a robust and accurate representation of diverse emotional states in employees. From the result analysis, we found that the ResNet outperforms other existing pre-trained models in terms of training accuracy (95.23%), training loss (0.41), and training time (2803 sec).

Fuzzy and Spiking Neural Network-based Secure Data Exchange Framework for Autonomous Vehicle

Conference

Title of PaperFuzzy and Spiking Neural Network-based Secure Data Exchange Framework for Autonomous Vehicle

Proceeding Name2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence)

PublisherIEEE

Author NameNishi Patel; Dhyan Patel; Nilesh Kumar Jadav; Sudeep Tanwar; Deepak Garg

OrganizationIEEE

Year , VenueMarch 2024 , Noida, India

Page Number1-6

ISSN/ISBN No2766-4228

Indexed INScopus

Abstract

Autonomous vehicles (AVs) represent a revolutionary step in intelligent transportation (ITS), which uses artificial intelligence (AI) models to navigate without human intervention. However, the reliance on sensor networks for operational functionality introduces significant vulnerabilities as inadequate training of these sensors can lead to sub-optimal path selection or, more critically, accidents. The main security issue addressed in this study is the lack of strong security mechanisms for the operation of sensors in AVs, which makes them vulnerable to counter-revolutionary actions. These attacks can degrade performance and compromise the security of ITS. Thus, we propose a novel intrusion detection system integrated with fuzzy logic and AI, which is designed to validate and sanitize the communication between the sensors to improve the performance of AVs. For that, a sensor communication dataset is utilized comprised of malicious and non-malicious data. Furthermore, a spiking neural network (SNN) is employed to get trained on the dataset for efficient binary classification tasks. Our implementation of the SNN model has demonstrated a remarkable accuracy of 97.76% in identifying non-malicious data. The performance of our framework is further validated by comprehensive evaluations using indicators such as recall, accuracy, precision, and F1 score.

SEAM: Deep Learning-based Secure Message Exchange Framework For Autonomous EVs

Conference

Title of PaperSEAM: Deep Learning-based Secure Message Exchange Framework For Autonomous EVs

Proceeding Name2023 IEEE Globecom Conference (Globecom)

PublisherIEEE

Author NameFenil Ramoliya; Riya Kakkar; Rajesh Gupta; Sudeep Tanwar; Smita Agrawal

OrganizationIEEE

Year , VenueMarch 2024 , Kuala Lumpur, Malaysia

Page Number1-6

ISSN/ISBN No979-8-3503-7021-8

Indexed INScopus

Abstract

The proliferation of digitization in the automotive industry has witnessed the drastic transition from fossil-fuel vehicles to autonomous Electric Vehicles (EVs) to enable colossal data communication in an Industrial Internet of Things (IIoT) environment. However, the malicious attacker can deter message exchange between autonomous EVs with various security attacks such as ransomware, cyber-trojan, and injection. Thus, to mitigate the aforementioned security issues, we proposed a deep learning-based secure message exchange framework, i.e., SEAM to safeguard the data communication between autonomous EVs in an IIoT environment. The proposed framework leverages the Long Short-Term Memory (LSTM) model to classify message requests as malicious or benign, enabling seamless and secure communication between EVs. The message classification performed by the LSTM helps autonomous EVs decide the message's authenticity, reducing road fatalities. The model training includes various state-of-the-art deep learning models such as Gated Recurrent Unit (GRU), Recurrent Neural Network (RNN) and LSTM. Finally, the performance of the SEAM is evaluated considering various metrics such as F-score, precision, recall, loss curve, accuracy curve, and confusion matrix for the best performing LSTM model in which Adam yields the best performance over other optimizers.

Cyber Security and Digital Forensics (Proceedings of the International Conference, ReDCySec 2023)

Book

PublisherSpringer

Published YearMarch 2024

ISSN/ISBN No978-981-99-9810-4

Indexed INScopus, Web of Science

Abstract

The book contains peer-reviewed papers from the International Conference on Recent Developments in Cyber Security organized by the Center for Cyber Security and Cryptology at Sharda University in June 2023. This volume focuses on privacy and secrecy of information, cryptography, applications and analysis, cyber threat intelligence and mitigation, cyber-physical systems, cyber threat intelligence, quantum cryptography and blockchain technologies and their application, etc. This book is a unique collection of chapters from different areas with a common theme and will be immensely useful to academic researchers and practitioners in the industry.

Multi-agent-based decentralized residential energy management using Deep Reinforcement Learning

Journal

Journal NameJournal of Building Engineering

Title of PaperMulti-agent-based decentralized residential energy management using Deep Reinforcement Learning

PublisherElsevier

Volume Number87

Page Number109031

Published YearMarch 2024

ISSN/ISBN No2352-7102

Indexed INScopus, Web of Science

Abstract

In smart grid, energy consumption has grown exponentially in residential houses, which necessitates the adoption of demand response management. To alleviate and handle the energy management in residential houses, an efficient residential energy management (REM) system can be employed to regulate the energy consumption of appliances for several energy loads such as non-shiftable, shiftable, and controllable loads. Many researchers have focused on the REM using machine learning and deep learning techniques which is not able to provide secure and optimal energy management procedure. Thus, in this paper, a multi-agent-based decentralized REM, i.e., MD-REM approach is proposed using Deep Reinforcement Learning (DRL) with the utilization of blockchain. Furthermore, The combinatorial model DQN, i.e., Q-learning and deep neural network (DNN) is employed, to gain the optimal price based on the reduced energy consumption by appliances associated with different energy loads utilizing the Markov Decision Process (MDP). Here, multiple agents are designed to handle different energy loads and consumption is controlled by the DQN agent, then reduced consumption data is securely shared among all stakeholders using blockchain-based smart contract. The performance evaluation of the proposed MD-REM approach seems to be efficient in terms of reduced energy consumption, optimal energy price, reward, and total profit analysis. Moreover, blockchain-based result is evaluated for the proposed MD-REM approach considering the performance metrics such as transaction efficiency, Interplanetary File System (IPFS) bandwidth utilization, and data storage cost comparison.

FedOnion: FL and Onion Routing-Driven Secure Data Exchange Framework for 5G-IIoT Applications

Conference

Title of PaperFedOnion: FL and Onion Routing-Driven Secure Data Exchange Framework for 5G-IIoT Applications

Proceeding Name2023 IEEE Global Communications Conference

PublisherIEEE

Author NameNilesh Kumar Jadav; Rajesh Gupta; Pronaya Bhattacharya; Sudeep Tanwar

OrganizationIEEE

Year , VenueFebruary 2024 , KualaLumpur, Malayasia

Page Number1-6

ISSN/ISBN No979-8-3503-1090-0

Indexed INScopus

Abstract

The emergence of massive automation has transformed Industrial Internet-of-Things (IIoT) to become adaptive, self-healing, and autonomous. In IloT, the increased volume of data traffic has raised questions about the privacy and security of shared sensor data, resource management, the accuracy of trained models, and the authenticity of network traffic in operation. Thus, conventional security paradigms and centralized learning models are outdated to support the IloT operational space. Modern solutions like federated learning (FL) and onion routing (OR) are integrated into IloT to secure and optimize link communication and improve the computational requirements of central model training. Thus, the paper integrates FL and OR in IloT, and presents a framework FedOnion, where federated classifiers are proposed at intermediate OR circuits, which preserves anonymity and privacy of data sharing among nodes in IloT. In this frame-work, an FL-assisted network traffic classification approach is presented for malicious or non-malicious data requests forwarded to the OR network. Malicious requests are discarded at the next onion router, and it prevents the shared key from getting compromised, as the hash is computed at each hop to signify that data is not tampered with. FL-classifiers divide the overall dataset into small segments, which alleviates the computational burden on OR links and improves the detection rate of malicious data requests. The proposed framework's effectiveness is demonstrated on real-world IloT datasets, based on security and computational parameters. The obtained results indicate the practical viability of the scheme for critical industrial setups which paves the way towards a robust and secured industrial future. The proposed framework is assessed using different performance parameters, such as FL MSE (10−9 at 300 epochs), onion circuit compromisation rate (16%), and 5G modulation scheme.

Whale Optimization-Based Access Control Scheme in D2D Communication Underlaying Cellular Networks

Journal

Journal NameIEEE Transactions on Network and Service Management

Title of PaperWhale Optimization-Based Access Control Scheme in D2D Communication Underlaying Cellular Networks

PublisherIEEE

Volume NumberEarly Access

Page Number1-12

Published YearFebruary 2024

ISSN/ISBN No1932-4537

Indexed INScopus, Web of Science

Abstract

Integration of device-to-device (D2D) communication has gained significant attention within cellular networks as a means to enhance their capacity, coverage, and performance. Despite these advantages, D2D communication encounters various challenges, such as high interference, resource allocation, energy efficiency, and security. In this paper, we investigate the problem associated with resource allocation in D2D communication underlying cellular networks. The existing resource allocation schemes (e.g., game theory and graph theory) do not offer an access control mechanism, due to which the existing schemes are computationally intensive and do not converge to offer a global optimum solution. Toward this goal, we proposed a whale optimization algorithm(WOA)-based access control scheme to enhance the performance of the resource allocation scheme in D2D communication. In WOA, we created a signal-to-interference-plus-noise ratio (SINR)-based objective function that iteratively discovers the best D2D users, allowing them to participate in the resource allocation process. Moreover, for resource allocation, we adopted the Munkres algorithm, which allows only optimized D2D users (from WOA) to reuse the resources of cellular users (CUs). In the proposed work, WOA acts as an access control scheme that optimally finds the best D2D users and only allows them to reuse cellular resources in the Munkres resource assignment problem. Simulation results show that the proposed scheme significantly improves the system’s throughput compared to other existing algorithms. Moreover, other evaluation parameters, such as convergence rate, fairness, WOA update positions, and execution time, show the outperformance of the proposed scheme.

ML-Based Energy Consumption and Distribution Framework Analysis for EVs and Charging Stations in Smart Grid Environment

Journal

Journal NameIEEE Access

Title of PaperML-Based Energy Consumption and Distribution Framework Analysis for EVs and Charging Stations in Smart Grid Environment

PublisherIEEE

Volume Number12

Page Number23319 - 23337

Published YearFebruary 2024

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Electric vehicles (EVs) have become a prominent alternative to fossil fuel vehicles in the modern transportation industry due to their competitive benefits of carbon neutrality and environment friendliness. The tremendous adoption of EVs leads to a significant increase in demand for charging infrastructure. But, the scarcity of charging stations (CSs) concerns efficient and reliable EV charging. Existing studies discussed EV energy consumption prediction schemes at the CS without analyzing the affecting parameters such as energy demand, weather, day, etc. In this regard, we have proposed an energy consumption and distribution framework for EVs in a smart grid environment for efficient EV charging after analyzing the affecting parameters such as location, weekday, weekend, and user. Moreover, we have considered EV dataset to perform a detailed and deep analysis of energy consumption patterns based on the aforementioned parameters such as CS (Station ID) within the location (Location ID), weekday, weekend, and user (UserID). The main aim is to understand the smart grid-based electricity distribution to the CS by analyzing energy consumption patterns for reliable EV charging. We have done different analysis on different parameters and present their graphical representations.

GRU-based digital twin framework for data allocation and storage in IoT-enabled smart home networks

Journal

Journal NameFuture Generation Computer Systems

Title of PaperGRU-based digital twin framework for data allocation and storage in IoT-enabled smart home networks

PublisherElsevier

Volume Number153

Page Number391-402

Published YearDecember 2023

ISSN/ISBN No1872-7115

Indexed INScopus, Web of Science

Abstract

In recent years, the Internet of Things (IoT) devices utilization with Information Communication Technology (ICT) has grown exponentially in various Smart City applications, including Smart Homes, Smart Enterprises, and others. The fusion of IoT, ICT, and Smart Home delivers interactive solutions to reduce costs and resource consumption, enhance performance, and engage people's needs more virtually and proactively. A smart home has numerous advantages with the integration of emerging advanced technologies. Big data, centralization, data and resource allocation, security, and privacy issues persist as challenges in IoT-enabled Smart Home Networks. To address these challenges, in this paper, we propose a GRU-based Digital Twin Framework for Data Allocation in IoT-enabled Smart Home Networks. Data and resource allocation of smart home applications are completed at the virtual twin layer using Gated Recurrent Unit (GRU)-based Digital Twin Networks. Low-priority data is stored and processed at the Macro-based Stations (MBSs), and high-priority data is transferred to the upper (Security) layer for authentication and validation. Blockchain-based distributed networks are utilized for Smart Home Data authentication at the security layer with a Proof of Authentication (PoAh) Consensus Algorithm; Data is stored at the cloud layer after validation. The validation results of the proposed framework demonstrate superior performance as the quantitative analysis with accuracy 0.9412, Root Mean Square Error (RMSE) 0.0588 for IoT-enable Smart Home compared to existing works as LSTM-based Digital Twin network and provide a secure environment in IoT-enabled Smart Home.

Federated Learning for Internet of Medical Things Concepts, Paradigms, and Solutions

Book

PublisherTaylor's and Francis Group

Published YearJune 2023

ISSN/ISBN No9781032300764

Indexed INScopus, Web of Science

Abstract

This book intends to present emerging Federated Learning (FL)-based architectures, frameworks, and models in Internet of Medical Things (IoMT) applications. It intends to build on the basics of the healthcare industry, the current data sharing requirements, and security and privacy issues in medical data sharing. Once IoMT is presented, the book shifts towards the proposal of privacy-preservation in IoMT, and explains how FL presents a viable solution to these challenges. The claims are supported through lucid illustrations, tables, and examples that present effective and secured FL schemes, simulations, and practical discussion on use-case scenarios in a simple manner. The book intends to create opportunities for healthcare communities to build effective FL solutions around the presented themes, and to support work in related areas that will benefit from reading the book. It also intends to present breakthroughs and foster innovation in FL-based research, specifically in the IoMT domain. The emphasis of this book is on understanding the contributions of IoMT to healthcare analytics, and its aim is to provide insights including evolution, research directions, challenges, and the way to empower healthcare services through federated learning. The book also intends to cover the ethical and social issues around the recent advancements in the field of decentralized Artificial Intelligence. The book is mainly intended for undergraduates, post-graduates, researchers, and healthcare professionals who wish to learn FL-based solutions right from scratch, and build practical FL solutions in different IoMT verticals.

An Improved Dense CNN Architecture for Deepfake Image Detection

Journal

Journal NameIEEE Access

Title of PaperAn Improved Dense CNN Architecture for Deepfake Image Detection

PublisherIEEE

Volume Number11

Page Number22081 - 22095

Published YearMarch 2023

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Recent advancements in computer vision processing need potent tools to create realistic deepfakes. A generative adversarial network (GAN) can fake the captured media streams, such as images, audio, and video, and make them visually fit other environments. So, the dissemination of fake media streams creates havoc in social communities and can destroy the reputation of a person or a community. Moreover, it manipulates public sentiments and opinions toward the person or community. Recent studies have suggested using the convolutional neural network (CNN) as an effective tool to detect deepfakes in the network. But, most techniques cannot capture the inter-frame dissimilarities of the collected media streams. Motivated by this, this paper presents a novel and improved deep-CNN (D-CNN) architecture for deepfake detection with reasonable accuracy and high generalizability. Images from multiple sources are captured to train the model, improving overall generalizability capabilities. The images are re-scaled and fed to the D-CNN model. A binary-cross entropy and Adam optimizer are utilized to improve the learning rate of the D-CNN model. We have considered seven different datasets from the reconstruction challenge with 5000 deepfake images and 10000 real images. The proposed model yields an accuracy of 98.33% in AttGAN, [Facial Attribute Editing by Only Changing What You Want (AttGAN)] 99.33% in GDWCT,[Group-wise deep whitening-and-coloring transformation (GDWCT)] 95.33% in StyleGAN, 94.67% in StyleGAN2, and 99.17% in StarGAN [A GAN capable of learning mappings among multiple domains (StarGAN)] real and deepfake images, that indicates its viability in experimental setups.

EmReSys: AI-based Efficient Employee Ranking and Recommender System for Organizations

Conference

Title of PaperEmReSys: AI-based Efficient Employee Ranking and Recommender System for Organizations

Proceeding Name2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

PublisherIEEE

Author NameDhairya Jadav; Dev Patel; Somya Thacker; Anuja Nair; Rajesh Gupta; Nilesh Kumar Jadav; Sudeep Tanwar

Year , VenueFebruary 2023 , Sharda University, Grater Noida, UP

Page Number1-6

ISSN/ISBN No978-1-6654-6200-6

Indexed INScopus, Web of Science

Abstract

According to Jorge Paulo Lemann, “the greatest asset of a company is its people.” An organization consists of many areas where technologies supporting decision-making, i.e., artificial intelligence, can assist organizations in organization aspects, business strategies, and people management. The objective of decision-making technologies is not based on subjective factors but on objective data analysis. One such application area is to provide incentives to employees without any human interaction or intervention. It is an organization’s job to find good employees and recognize their efforts by offering incentives. However, handpicking potentially outstanding employees in a workplace where biases have penetrated gets perplexing. To overcome this barrier, EmReSys, an employee recommendation System for large-scale organizations, is developed, which does not require any human interaction to recognize personnel potential. It uses Machine Learning (ML) techniques to recommend the employee for promotion, increment, etc. The EmReSys system is installed at the edge network to perform ML tasks efficiently and the communication is established via the 5G network. The suggested method automates the procedure using a Support Vector Machine (SVM), an ML technique with a 98.9% accuracy.

GeFL: Gradient Encryption-Aided Privacy Preserved Federated Learning for Autonomous Vehicles

Journal

Journal NameIEEE Access

Title of PaperGeFL: Gradient Encryption-Aided Privacy Preserved Federated Learning for Autonomous Vehicles

PublisherIEEE

Volume Number11

Page Number1825 - 1839

Published YearJanuary 2023

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Autonomous vehicles (AVs) are getting popular because of their usage in a wide range of applications like delivery systems, self-driving taxis, and ambulances. AVs utilize the power of machine learning (ML) and deep learning (DL) algorithms to improve their self-driving learning experiences. The sudden surge in the number of AVs raises the need for distributed learning ecosystem to optimize their self-driving experiences at a rapid pace. Toward this goal, federated learning (FL) benefits, which can create a distributed learning environment for AVs. But, the traditional FL transfers the raw input data directly to a server, which leads to privacy concerns among the end-users. The concept of blockchain helps us to protect privacy, but it requires additional computational infrastructure. The extra infrastructure increases the operational cost for the company handling and maintaining the AVs. Motivated by this, in this paper, the authors introduced the concept of gradient encryption in FL, which preserves the users’ privacy without the additional computation requirements. The computational power present in the edge devices helps to fine-tune the local model and encrypt the input data to preserve privacy without any drop in performance. For performance evaluation, the authors have built a German traffic sign recognition system using a convolutional neural network (CNN) algorithm-based classification system and GeFL. The simulation process is carried out over a wide range of input parameters to analyze the performance at scale. Simulation results of GeFL outperform the conventional FL-based algorithms in terms of accuracy, i.e., 2% higher. Also, the amount of data transferred among the devices in the network is nearly three times less in GeFL compared to the traditional FL.

Blockchain and Federated Learning-based Security Solutions for Telesurgery System: A Comprehensive Review

Journal

Journal NameTurkish Journal of Electrical Engineering & Computer Sciences

Title of PaperBlockchain and Federated Learning-based Security Solutions for Telesurgery System: A Comprehensive Review

PublisherTUBITAK

Volume Number30

Page Number1-43

Published YearNovember 2022

ISSN/ISBN No1300-0632

Indexed INScopus, Web of Science

Abstract

The advent of telemedicine with its remote surgical procedures has effectively transformed the working of healthcare professionals. The evolution of telemedicine facilitates the remote monitoring of patients that lead to the advent of telesurgery systems, i.e. one of the most critical applications in telemedicine systems. Apart from gaining popularity, the telesurgery system may encounter security and trust issues of patients’ data while communicating with the surgeon for their remote treatment. Motivated by this, we have presented a comprehensive survey on secure telesurgery systems comprising healthcare, surgical robots, traditional telesurgery systems, and the role of artificial intelligence to deal with the numerous security attacks associated with the patients’ health data. Furthermore, we propose a blockchain and federated learning-based secure telesurgery system to secure the communication between patient and surgeon. The results of the proposed system are better than those of the traditional system in terms of improved latency, low data storage cost, and enhanced data offloading. Finally, we explore the research challenges and issues associated with the telesurgery system.

BaRCODe: A Blockchain-based Framework for Remote COVID Detection for Healthcare 5.0

Conference

Title of PaperBaRCODe: A Blockchain-based Framework for Remote COVID Detection for Healthcare 5.0

Proceeding NameIEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

PublisherIEEE

Author NameDhairya Jadav; Dev Patel; Rajesh Gupta; Nilesh Kumar Jadav; Sudeep Tanwar

OrganizationIEEE ComSac

Year , VenueJuly 2022 , Seoul, Korea

Page Number782-787

ISSN/ISBN No2694-2941

Indexed INScopus

Abstract

The emergence of wearable technology for assessing health data has revolutionized the health sector. Consequently, medical practitioners can now virtually examine the patient's health and provide immediate medications. However, when the security of this equipment is considered, there is a grave hazard. The data is delivered across an open channel, i.e., the internet, from the patient's device to the doctor, and it may be tampered with by intruders. Insurance firms keep a record of their patient's health and subsequently offer appropriate treatments. In case of data tampering, the insurer will consider the conduct fraudulent. As a result, ensuring the system's integrity and granting access only to authorized stakeholders becomes critical. Blockchain has surpassed conventional technologies in terms of guaranteeing security for information held. Motivated by these, this paper has developed a novel approach that uses blockchain technology to transmit a patient's health information to a medical expert. Machine Learning (ML) techniques, K-Nearest Neighbours (KNN), and Logistic Regression (LR) is used to categorize Coronavirus Disease (COVID) positive users and malevolent wearable devices, respectively. The performance of the proposed model is evaluated considering parameters such as accuracy, precision, recall, and F1 score. The proposed model achieves an accuracy of 98.15% for COVID positive detection and 96.78% for malevolent user detection.

Blockchain Applications for Healthcare Informatics: Beyond 5G

Book

PublisherElsevier

Published YearJune 2022

ISSN/ISBN No9780323906159

Indexed INScopus

Abstract

Blockchain Applications for Healthcare Informatics: Beyond 5G offers a comprehensive survey of 5G-enabled technology in healthcare applications. This book investigates the latest research in blockchain technologies and seeks to answer some of the practical and methodological questions surrounding privacy and security in healthcare. It explores the most promising aspects of 5G for healthcare industries, including how hospitals and healthcare systems can do better. Chapters investigate the detailed framework needed to maintain security and privacy in 5G healthcare services using blockchain technologies, along with case studies that look at various performance evaluation metrics, such as privacy preservation, scalability and healthcare legislation.

Interference Mitigation and Secrecy-ensured D2D Resource Allocation Scheme using Game Theory

Conference

Title of PaperInterference Mitigation and Secrecy-ensured D2D Resource Allocation Scheme using Game Theory

Proceeding NameIEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

PublisherIEEE

Author NameRajesh Gupta; Sudeep Tanwar

OrganizationIEEE

Year , VenueMay 2022 , New York, NY, USA

Page Number1-6

ISSN/ISBN No978-1-6654-0926-1

Indexed INScopus, Others

Abstract

This paper proposes a cognitive radio (CR)-based secure resource allocation scheme for device-to-device (D2D) communication networks. It aims to minimize the interference effect with a proper pairing of strong and weak D2D users by sensing the available spectrum of cellular users (CUs). It maximizes the total sum rate of D2D users with great service and quality of experience. Further, to improve the secrecy capacity of the proposed scheme, we formulate a coalition game. It has a preference order (decides upon the channel conditions) and based on that it moves D2D users from one coalition to another. This landed D2D users in the superlative coalition with conducive channel conditions. We then evaluate the proposed scheme considering parameters such as total sum rate, sum secrecy capacity, and average secrecy capacity. The graphs show that the proposed scheme outperforms the traditional without CR, first-order algorithm (FOA), and nearest first approaches.

DuBloQ: Blockchain and Q-Learning Based Drug Discovery in Healthcare 4.0

Conference

Title of PaperDuBloQ: Blockchain and Q-Learning Based Drug Discovery in Healthcare 4.0

Proceeding Name2022 International Wireless Communications and Mobile Computing (IWCMC)

PublisherIEEE

Author NameUrvashi Ramdasani; Gunjan Vinzuda; Sudeep Tanwar; Rajesh Gupta; Mohsen Guizani

OrganizationIEEE

Year , VenueMay 2022 , Dubrovnik, Croatia

Page Number284-289

ISSN/ISBN No2376-6506

Indexed INScopus, Others

Abstract

Drug Discovery is a process by which new potential drugs are discovered and clinically trialed for commercial medicinal purposes. It has several stages of development, where each stage requires a prescribed time for its completion. The stages of drug development are discovery and development, pre-clinical research, clinical development, Food and Drug Administration (FDA) review, and post-market monitoring. The first three stages themselves take nearly 6.5 years. These stages take a huge time in cases where there is an urgent need for a drug. For example, during the COVID-19 pandemic, there was an urgent need for a vaccine. Many research institutes worked 24×7 to develop a vaccine, but it still took a considerable time to get to a bare minimum vaccine. To tackle this problem, we propose DuBloQ, a novel methodology for drug discovery using Q-Learning. Our Q-Learning model consists of a generator and a predictor model. The generator generates a set of Simplified Molecular Input Line Entry System (SMILES) strings and the Predictor predicts its logp values. Based on the logp values, the reward for the generator is provided to improve its performance. We integrate this model with a blockchain User Interface (UI) that ensures security and privacy. We achieved an accuracy of 76.1% for the generator model.

Deep Learning and Blockchain-based Framework to Detect Malware in Autonomous Vehicles

Conference

Title of PaperDeep Learning and Blockchain-based Framework to Detect Malware in Autonomous Vehicles

Proceeding Name 2022 International Wireless Communications and Mobile Computing (IWCMC)

PublisherIEEE

Author NameDev Patel; Dhairya Jadav; Rajesh Gupta; Nilesh Kumar Jadav; Sudeep Tanwar; Bassem O

OrganizationIEEE

Year , VenueMay 2022 , Dubrovnik, Croatia

Page Number278-283

ISSN/ISBN No2376-6506

Indexed INScopus, Others

Abstract

The advancement in technology has brought to life the concept of Autonomous vehicles (AV). The primary goal of AV is to reduce driving stress and provide comfort to the occupants. Since AVs can drive themselves, it poses a question of passenger security. Furthermore, AVs are connected to an open network like a public Internet to communicate to the outer world, raising security and privacy concerns. Skillful attackers can effortlessly infiltrate the vehicle by injecting malware which can disrupt the regular operation of the entire AV system. A Deep Learning (DL) and Blockchain framework is proposed for AV to resolve the aforementioned security challenges. The network traffic is continuously monitored, and the malware binaries are converted to grey-scale images, which are then classified by Convolutional Neural Network (CNN) employed in the DL model. The CNN architecture, ResNet50V2, has been tested and proves to be efficient in detecting malware with an accuracy of 97.56%.

Deep learning and Blockchain-based Essential and Parkinson Tremor Classification Scheme

Conference

Title of PaperDeep learning and Blockchain-based Essential and Parkinson Tremor Classification Scheme

Proceeding Name: IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

PublisherIEEE

Author NameJigna J Hathaliya; Hetav Modi; Rajesh Gupta; Sudeep Tanwar

OrganizationIEEE

Year , VenueMay 2022 , New York, NY, USA

Page Number1-6

ISSN/ISBN No978-1-6654-0926-1

Indexed INScopus

Abstract

Essential tremor (ET) and Parkinson’s tremor (PST) are neurological movement disorders in which ET emerges with body part activation, while PST is recorded in the relaxed position of the patient. The medical symptoms of ET and PST are equivalent, including gait, anxiety, and muscular stiffness. In both disorders, doctors diagnose patients related to clinical evaluations during such hospital visits, leading to misdiagnosis. Machine Learning (ML) is being used to classify the ET and PST using human-based feature extraction to address this issue. Motivated by this, we applied Deep Learning (DL) to overcome the ML issue via automating feature extraction through the model itself. In this paper, we have used the integration of Gated recurrent unit (GRU) and Long short term memory (LSTM) algorithms to predict tremor severity. Initially, accelerometer sensors are used to record tremors in all three axial dimensions for each subject. Further, this data is pre-processed using the standard scalar function and scaled in-unit variance. Furthermore, this data first passed through the GRU model, and later it fed into the LSTM model to improve the model’s performance. Moreover, we employed the blockchain (BC) network to validate the performance of the trained model. we have used a smart contract to validate the identity of the researcher. The proposed model outperforms with 80.4% training accuracy and 74.1% testing accuracy. The total communication and computation cost of the proposed scheme is 448 bits and 0.056 ms. The integration of BC and DL makes a system more reliable, transparent, and accurate.

Blockchain and Zero-Sum Game-based Dynamic Pricing Scheme for Electric Vehicle Charging

Conference

Title of PaperBlockchain and Zero-Sum Game-based Dynamic Pricing Scheme for Electric Vehicle Charging

Proceeding NameIEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

PublisherIEEE

Author NameRiya Kakkar; Smita Agrawal; Rajesh Gupta; Sudeep Tanwar

OrganizationIEEE

Year , VenueMay 2022 , New York, NY, USA

Page Number1-6

ISSN/ISBN No978-1-6654-0926-1

Indexed INScopus

Abstract

This paper proposes a zero-sum game theory and blockchain-based secure and decentralized dynamic pricing scheme for electric vehicle charging. It aims to secure data sharing between electric vehicles and charging stations. We integrate the sixth-generation (6G) communication network to enable data transactions between electric vehicles and charging stations with low latency and high reliability. We employ a zerosum game theory approach to maximize the payoff of electric vehicles and charging stations. The performance of the proposed system with 6G is evaluated by comparing it with 5G and 4G traditional networks. The performance evaluation of the proposed system has been analyzed with various parameters latency, profit for electric vehicles, profit for charging station, and optimal payoff of the system. The results show that the proposed system is highly secure and reliable than traditional systems.

Blockchain and Stackleberg Game-based Fair and Trusted Data Pricing Scheme for Ride Sharing

Conference

Title of PaperBlockchain and Stackleberg Game-based Fair and Trusted Data Pricing Scheme for Ride Sharing

Proceeding Name2022 IEEE International Conference on Communications Workshops (ICC Workshops)

PublisherIEEE

Author NameRiya Kakkar; Nilesh Kumar Jadav; Rajesh Gupta; Smita Agrawal; Sudeep Tanwar

OrganizationIEEE

Year , VenueMay 2022 , Seoul, Korea,

Page Number854-859

ISSN/ISBN No2694-2941

Indexed INScopus

Abstract

This paper proposes a blockchain-based secure and optimal data pricing scheme for ride-sharing. It mainly focuses on securing the data transactions between vehicle owners and customers. It utilizes a communication network, i.e., 6G, to facilitate the low latency and high data rate transmissions between vehicle owner and customer. We applied a reverse Stackelberg game theory approach to yield the optimal payoff for vehicle owners and customers. The performance results of the proposed system over a 6G communication network is estimated by differentiating it with conventional networks such as 4G and 5G. The performance is evaluated considering the parameters latency, scalability, and the optimal payoff for the system. The performance results conclude that the proposed system is secure, reliable, and yields the optimal payoff for vehicle owners and customers.

Blockchain and Edge Intelligence-based Secure and Trusted V2V Framework Underlying 6G Networks

Conference

Title of PaperBlockchain and Edge Intelligence-based Secure and Trusted V2V Framework Underlying 6G Networks

Proceeding NameIEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

PublisherIEEE

Author NameNilesh Kumar Jadav; Rajesh Gupta; Sudeep Tanwar

OrganizationIEEE

Year , VenueMay 2022 , New York, NY, USA

Page Number1-6

ISSN/ISBN No978-1-6654-0926-1

Indexed INScopus

Abstract

There is a significant rise in vehicle-to-vehicle (V2V) communication for intelligent transportation systems such as reducing road accidents, traffic congestion, and optimal route planning. The main objective of the V2V communication is to provide real-time monitoring data from vehicles sensors to other vehicles. However, the attackers can exploit this communication by forging the controller area network (CAN) protocol and injecting malicious traffic. In this context, the vehicles mislead by false update messages and alerts. To overcome this issue, this paper presents the artificial intelligence (AI) and blockchain-based proposed architecture on a 6G network. The proposed architecture is examined with a car hacking dataset, wherein the sensors of vehicles are communicating with each other for data sharing. For that, we have adopted an AI algorithm, i.e., random forest (RF), to classify normal and malicious data traffic. Further, edge nodes are considered to reduce the computation of AI algorithms and faster accessibility of vehicular data. Furthermore, incorporating inter planetary file system (IPFS) and a 6G network makes the proposed architecture cost-effective and scalable. Finally, the architecture is evaluated against performance metrics such as accuracy, latency, and scalability. The results demonstrate that the RF surpasses the other algorithms in terms of accuracy and achieves 97% accuracy.

A Survey on Resource Allocation Schemes in Device-to-Device Communication

Conference

Title of PaperA Survey on Resource Allocation Schemes in Device-to-Device Communication

Proceeding Name2022 12th International Conference on Cloud Computing, Data Science & Engineering (Confluence)

PublisherIEEE

Year , VenueMarch 2022 , Noida, India

ISSN/ISBN No978-1-6654-3701-1

Indexed INScopus

A Taxonomy of Fake News Classification Techniques: Survey and Implementation Aspects

Journal

Journal NameIEEE Access

Title of PaperA Taxonomy of Fake News Classification Techniques: Survey and Implementation Aspects

Page Number30367 - 30394

Published YearMarch 2022

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

AI-Empowered Recommender System for Renewable Energy Harvesting in Smart Grid System

Journal

Journal NameIEEE Access

Title of PaperAI-Empowered Recommender System for Renewable Energy Harvesting in Smart Grid System

PublisherIEEE

Page Number24316 - 24326

Published YearFebruary 2022

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

A Comprehensive Review of the Technological Solutions to Analyse the Effects of Pandemic Outbreak on Human Lives

Journal

Journal NameMedicina, MDPI

Title of PaperA Comprehensive Review of the Technological Solutions to Analyse the Effects of Pandemic Outbreak on Human Lives

Published YearFebruary 2022

Indexed INScopus, Web of Science

A survey on energy-efficient resource allocation schemes in device-to-device communication

Journal

Journal NameInternational Journal of Communication Systems

Title of PaperA survey on energy-efficient resource allocation schemes in device-to-device communication

Published YearFebruary 2022

Indexed INScopus, Web of Science

BFLEdge: Blockchain based federated edge learning scheme in V2X underlying 6G communications

Conference

Title of PaperBFLEdge: Blockchain based federated edge learning scheme in V2X underlying 6G communications

Proceeding Name 2022 12th International Conference on Cloud Computing, Data Science & Engineering (Confluence)

PublisherIEEE

Author NameVishwa AmitKumar Patel; Pronaya Bhattacharya; Sudeep Tanwar; Nilesh Kumar Jadav; Rajesh Gupta

OrganizationIEEE

Year , VenueJanuary 2022 , Noida, India

Page Number1-6

ISSN/ISBN No978-1-6654-3701-1

Indexed INScopus

Abstract

Sixth generation (6G) vehicle-to-anything (V2X) networks support intelligent edge computing that leverages data sensing, computation, and offloading among vehicular nodes (VN) with ultra-low latency. Data is heterogeneous with high complex interactions among V2X users and pass via open channels that induce privacy and security concerns. Thus, federated learning (FL) protects user privacy and fine-tunes the learning models at resource-constrained edge nodes to address security and computational concerns at the edge. However, to ensure reliability and trust, we propose a block-chain (BC) and FL-based edge scheme, BFLEdge. It also improves the overall learning rate of the FL model. The proposed scheme consists of three phases, where the first phase uses local machine learning (LML) to model the VN data and store it into the local BC network. The LML block updates are verified in the second phase through a proposed distributed consensus mechanism. Lastly, through 6G communication services, the channel dynamics are modelled as a Markov chain process to reduce end-to-end delay of local BC propagation updates at the edge that improves the V2X system throughput. Simulation and analytical results are proposed based on channel loss, block mining rate, edge latency, and FL-learning rate. The obtained results indicate the viability of the proposed framework against conventional state-of-the-art approaches.

Cyber Security: Issues and Current Trends

Book

PublisherSpringerLink

Published YearJanuary 2022

ISSN/ISBN No978-981-16-6597-4

Indexed INScopus

Optimal Resource Allocation for Quality-of-Service in D2D Communication Underlying Imperfect CSI

Conference

Title of PaperOptimal Resource Allocation for Quality-of-Service in D2D Communication Underlying Imperfect CSI

Proceeding Name2021 IEEE 6th International Conference on Computing, Communication and Automation (ICCCA)

PublisherIEEE

Year , VenueJanuary 2022 , Arad, Romania

ISSN/ISBN No2642-7354

Indexed INScopus

Deep Learning-based Parkinson disease Classification using PET Scan Imaging Data

Conference

Title of PaperDeep Learning-based Parkinson disease Classification using PET Scan Imaging Data

Proceeding Name2021 IEEE 6th International Conference on Computing, Communication and Automation (ICCCA)

PublisherIEEE

Year , VenueJanuary 2022 , Arad, Romania

ISSN/ISBN No2642-7354

Indexed INScopus

A Smart contract-based secure data sharing scheme in Healthcare 5.0

Conference

Title of PaperA Smart contract-based secure data sharing scheme in Healthcare 5.0

Proceeding Name 2021 IEEE Globecom Workshops (GC Wkshps)

PublisherIEEE

Year , VenueJanuary 2022 , Madrid, Spain

ISSN/ISBN No978-1-6654-2390-8

Indexed INScopus

Students' Assessment for Quantitative Measurement of Course Learning Outcomes in Online Class of Power Plant Instrumentation

Conference

Title of PaperStudents' Assessment for Quantitative Measurement of Course Learning Outcomes in Online Class of Power Plant Instrumentation

Proceeding Name2022 International Conference for Advancement in Technology (ICONAT)

PublisherIEEE

Year , VenueJanuary 2022 , Goa, India

ISSN/ISBN No978-1-6654-2577-3

Indexed INScopus

Adversarial learning techniques for security and privacy preservation: A comprehensive review

Journal

Journal NameSecurity and Privacy, Wiley

Title of PaperAdversarial learning techniques for security and privacy preservation: A comprehensive review

PublisherWiley Online Library

Published YearJanuary 2022

Federated Learning for Air Quality Index Prediction using UAV Swarm Networks

Conference

Title of PaperFederated Learning for Air Quality Index Prediction using UAV Swarm Networks

Proceeding Name2021 IEEE Global Communications Conference (GLOBECOM)

PublisherIEEE

Author NamePrateek Chhikara; Rajkumar Tekchandani; Neeraj Kumar; Sudeep Tanwar; Joel J. P. C. Rodrigues

OrganizationIEEE

Year , VenueDecember 2021 , Madrid, Spain

Page Number1-6

ISSN/ISBN No978-1-7281-8104-2

Indexed INScopus, Others

Abstract

People need to breathe, and so do other living beings, including plants and animals. It is impossible to overlook the impact of air pollution on nature, human well-being, and concerned countries' economies. Monitoring of air pollution and future predictions of air quality have lately displayed a vital concern. There is a need to predict the air quality index with high accuracy; on a real-time basis to prevent people from health issues caused by air pollution. With the help of Unmanned Aerial Vehicle's onboard sensors, we can collect air quality data easily. The paper proposes a distributed and decentralized Federated Learning approach within a UAV swarm. The accumulated data by the sensors are used as an input to the Long Short Term Memory (LSTM) model. Each UAV used its locally gathered data to train a model before transmitting the local model to the central base station. The central base station creates a master model by combining all the UAV's local model weights of the participating UAVs in the FL process and transmits it to all UAV s in the subsequent cycles. The effectiveness of the proposed model is evaluated with other machine learning models using various evaluation metrics using test data from the capital city of India, i.e., Delhi

Coalition of 6G and Blockchain in AR/VR Space: Challenges and Future Directions

Journal

Journal NameIEEE Access

Title of PaperCoalition of 6G and Blockchain in AR/VR Space: Challenges and Future Directions

Volume Number9

Published YearDecember 2021

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

SaTYa: Trusted Bi-LSTM-Based Fake News Classification Scheme for Smart Community

Journal

Journal NameIEEE Transactions on Computational Social Systems

Title of PaperSaTYa: Trusted Bi-LSTM-Based Fake News Classification Scheme for Smart Community

PublisherIEEE

Published YearDecember 2021

ISSN/ISBN No2329-924X

Indexed INScopus, Web of Science

Machine Learning in Signal Processing: Applications, Challenges, and the Road Ahead

Book

PublisherTaylor & Francis

Published YearDecember 2021

ISSN/ISBN No9780367618902

Indexed INScopus

GaRuDa: A Blockchain-Based Delivery Scheme Using Drones for Healthcare 5.0 Applications

Journal

Journal NameIEEE Internet of Things Magazine

Title of PaperGaRuDa: A Blockchain-Based Delivery Scheme Using Drones for Healthcare 5.0 Applications

PublisherIEEE

Page Number60 - 66

Published YearDecember 2021

ISSN/ISBN No2576-3199

Indexed INScopus, Web of Science

Amalgamation of Blockchain and AI to Classify Malicious Behavior of Autonomous Vehicles

Conference

Title of PaperAmalgamation of Blockchain and AI to Classify Malicious Behavior of Autonomous Vehicles

Proceeding Name2021 International Conference on Computer, Information and Telecommunication Systems (CITS)

PublisherIEEE

Year , VenueNovember 2021 , Istanbul, Turkey

ISSN/ISBN No978-1-6654-4913-7

Indexed INScopus

Blockchain and Multiple Linear Regression-based Energy Trading Scheme for Electric Vehicles

Conference

Title of PaperBlockchain and Multiple Linear Regression-based Energy Trading Scheme for Electric Vehicles

Proceeding Name 2021 International Conference on Computer, Information and Telecommunication Systems (CITS)

PublisherIEEE

Year , VenueNovember 2021 , Istanbul, Turkey

ISSN/ISBN No978-1-6654-4913-7

Indexed INScopus

Deep learning-based malicious smart contract detection scheme for internet of things environment

Journal

Journal NameComputers & Electrical Engineering

Title of PaperDeep learning-based malicious smart contract detection scheme for internet of things environment

PublisherElseiver

Volume Number97

Published YearNovember 2021

ISSN/ISBN No0045-7906

Indexed INScopus, Web of Science

XAI-AV: Explainable Artificial Intelligence for Trust Management in Autonomous Vehicles

Conference

Title of PaperXAI-AV: Explainable Artificial Intelligence for Trust Management in Autonomous Vehicles

Proceeding Name 2021 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)

PublisherIEEE

Year , VenueOctober 2021 , Beijing, China

ISSN/ISBN No978-1-6654-3208-5

Indexed INScopus

Blockchain-based Data Dissemination Scheme for 5G-enabled Softwarized UAV Networks

Journal

Journal Name IEEE Transactions on Green Communications and Networking

Title of PaperBlockchain-based Data Dissemination Scheme for 5G-enabled Softwarized UAV Networks

PublisherIEEE

Volume Number5

Page Number1712 - 1721

Published YearSeptember 2021

ISSN/ISBN No2473-2400

Indexed INScopus, Web of Science

Multiagent-based secure energy management for multimedia grid communication using Q-learning

Journal

Journal NameMultimedia Tools and Applications

Title of PaperMultiagent-based secure energy management for multimedia grid communication using Q-learning

PublisherSpringerLink

Published YearSeptember 2021

ISSN/ISBN No1573-7721

Indexed INScopus, Web of Science

BCovX: Blockchain-based COVID Diagnosis Scheme using Chest X-Ray for Isolated Location

Conference

Title of PaperBCovX: Blockchain-based COVID Diagnosis Scheme using Chest X-Ray for Isolated Location

Proceeding Name ICC 2021 - IEEE International Conference on Communications

PublisherIEEE

Year , VenueAugust 2021 , Montreal, QC, Canada

ISSN/ISBN No1938-1883

Indexed INScopus

A Machine Learning Approach to Classify Network Traffic

Conference

Title of PaperA Machine Learning Approach to Classify Network Traffic

Proceeding Name2021 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)

PublisherIEEE

Year , VenueAugust 2021 , Pitesti, Romania

ISSN/ISBN No978-1-6654-2534-6

Indexed INScopus

Interference Mitigation and Secrecy Ensured for NOMA-Based D2D Communications Under Imperfect CSI

Conference

Title of PaperInterference Mitigation and Secrecy Ensured for NOMA-Based D2D Communications Under Imperfect CSI

Proceeding Name ICC 2021 - IEEE International Conference on Communications

PublisherIEEE

Year , VenueAugust 2021 , Montreal, QC, Canada

ISSN/ISBN No1938-1883

Indexed INScopus

FaitH: Trusted Chain Network for Non-Cooperative D2D Communication Underlying HetNet

Conference

Title of PaperFaitH: Trusted Chain Network for Non-Cooperative D2D Communication Underlying HetNet

Proceeding Name2021 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)

PublisherIEEE

Year , VenueAugust 2021 , Pitesti, Romania

ISSN/ISBN No978-1-6654-2534-6

Indexed INScopus

MedBlock: An AI-enabled and Blockchain-driven Medical Healthcare System for COVID-19

Conference

Title of PaperMedBlock: An AI-enabled and Blockchain-driven Medical Healthcare System for COVID-19

Proceeding NameICC 2021 - IEEE International Conference on Communications

PublisherIEEE

Year , VenueAugust 2021 , Montreal, QC, Canada

ISSN/ISBN No1938-1883

Indexed INScopus

PoRF: Proof-of-Reputation-based Consensus Scheme for Fair Transaction Ordering

Conference

Title of PaperPoRF: Proof-of-Reputation-based Consensus Scheme for Fair Transaction Ordering

Proceeding Name2021 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)

PublisherIEEE

Year , VenueAugust 2021 , Pitesti, Romania

ISSN/ISBN No978-1-6654-2534-6

Indexed INScopus

Res6Edge: An Edge-AI Enabled Resource Sharing Scheme for C-V2X Communications towards 6G

Conference

Title of PaperRes6Edge: An Edge-AI Enabled Resource Sharing Scheme for C-V2X Communications towards 6G

Proceeding Name2021 International Wireless Communications and Mobile Computing (IWCMC)

PublisherIEEE

Year , VenueAugust 2021 , Harbin City, China

ISSN/ISBN No2376-6506

Indexed INScopus

B-IoMV: Blockchain-based onion routing protocol for D2D communication in an IoMV environment beyond 5G

Journal

Journal NameElsevier Vehicular Communications

Title of PaperB-IoMV: Blockchain-based onion routing protocol for D2D communication in an IoMV environment beyond 5G

PublisherElseiver

Volume Number33

Published YearAugust 2021

ISSN/ISBN No2214-2096

Indexed INScopus, Web of Science

VaCoChain: Blockchain-based 5G-assisted UAV Vaccine distribution scheme for future pandemics

Journal

Journal Name IEEE Journal of Biomedical and Health Informatics

Title of PaperVaCoChain: Blockchain-based 5G-assisted UAV Vaccine distribution scheme for future pandemics

PublisherIEEE

Published YearAugust 2021

ISSN/ISBN No2168-2208

Indexed INScopus, Web of Science

Blockchain for 5G Healthcare Applications: Security and privacy solutions

Book

PublisherIET

Published YearAugust 2021

ISSN/ISBN No978-1-83953-325-9

Indexed INScopus

PRS-P2P: A Prosumer Recommender System for Secure P2P Energy Trading using Q-Learning Towards 6G

Conference

Title of PaperPRS-P2P: A Prosumer Recommender System for Secure P2P Energy Trading using Q-Learning Towards 6G

Proceeding Name 2021 IEEE International Conference on Communications Workshops (ICC Workshops)

PublisherIEEE

Year , VenueJuly 2021 , Montreal, QC, Canada

ISSN/ISBN No2694-2941

Indexed INScopus

EVBlocks: A Blockchain-Based Secure Energy Trading Scheme for Electric Vehicles underlying 5G-V2X Ecosystems

Journal

Journal NameWireless Personal Communications

Title of PaperEVBlocks: A Blockchain-Based Secure Energy Trading Scheme for Electric Vehicles underlying 5G-V2X Ecosystems

Published YearJuly 2021

ISSN/ISBN No1572-834X

Indexed INScopus, Web of Science

Fusion of AI techniques to tackle COVID-19 pandemic: models, incidence rates, and future trends

Journal

Journal NameMultimedia Systems

Title of PaperFusion of AI techniques to tackle COVID-19 pandemic: models, incidence rates, and future trends

PublisherSpringerLink

Published YearJuly 2021

ISSN/ISBN No1432-1882

Indexed INScopus, Web of Science

Secrecy-ensured NOMA-based cooperative D2D-aided fog computing under imperfect CSI

Journal

Journal NameJournal of Information Security and Applications

Title of PaperSecrecy-ensured NOMA-based cooperative D2D-aided fog computing under imperfect CSI

PublisherElseiver

Volume Number59

Published YearJune 2021

ISSN/ISBN No2214-2126

Indexed INScopus, Web of Science

Energy Consumption Minimization Scheme for NOMA-Based Mobile Edge Computation Networks Underlaying UAV

Journal

Journal NameIEEE Systems Journal

Title of PaperEnergy Consumption Minimization Scheme for NOMA-Based Mobile Edge Computation Networks Underlaying UAV

PublisherIEEE

Volume Number15

Page Number5724 - 5733

Published YearMay 2021

ISSN/ISBN No1937-9234

Indexed INScopus, Web of Science

Emergence of Cyber Physical System and IoT in Smart Automation and Robotics: Computer Engineering in Automation

Book

PublisherSpringerLink

Published YearMay 2021

ISSN/ISBN No978-3-030-66224-0

Indexed INScopus

A taxonomy of energy optimization techniques for smart cities: Architecture and future directions

Journal

Journal NameExpert Systems

Title of PaperA taxonomy of energy optimization techniques for smart cities: Architecture and future directions

PublisherWiley Online Library

Published YearApril 2021

ISSN/ISBN No1468-0394

Indexed INScopus, Web of Science

Machine learning-based traffic scheduling techniques for intelligent transportation system: Opportunities and challenges

Journal

Journal NameInternational Journal of Communication Systems

Title of PaperMachine learning-based traffic scheduling techniques for intelligent transportation system: Opportunities and challenges

PublisherWiley Online Library

Published YearApril 2021

ISSN/ISBN No1099-1131

Indexed INScopus, Web of Science

6G-enabled Edge Intelligence for Ultra -Reliable Low Latency Applications: Vision and Mission

Journal

Journal NameComputer Standards & Interfaces

Title of Paper6G-enabled Edge Intelligence for Ultra -Reliable Low Latency Applications: Vision and Mission

PublisherElseiver

Volume Number77

Published YearFebruary 2021

ISSN/ISBN No0920-5489

Indexed INScopus, Web of Science

Blockchain for 5G-Enabled IoT: The new wave for Industrial Automation

Book

PublisherSpringerLink

Published YearJanuary 2021

ISSN/ISBN No978-3-030-67490-8

Indexed INScopus

Fog Computing for Healthcare 4.0 Environments : Technical, Societal, and Future Implications (622 pages)

Book

PublisherSpringerLink

Published YearJanuary 2021

ISSN/ISBN No978-3-030-46199-7

Indexed INScopus

Abstract

This book provides an analysis of the role of fog computing, cloud computing, and Internet of Things in providing uninterrupted context-aware services as they relate to Healthcare 4.0. The book considers a three-layer patient-driven healthcare architecture for real-time data collection, processing, and transmission. It gives insight to the readers for the applicability of fog devices and gateways in Healthcare 4.0 environments for current and future applications. It also considers aspects required to manage the complexity of fog computing for Healthcare 4.0 and also develops a comprehensive taxonomy.

Fog Data Analytics for IoT Applications : Next Generation Process Model with State of the Art Technologies (497 pages)

Book

PublisherSpringerLink

Published YearJanuary 2020

ISSN/ISBN No978-981-15-6046-0

Indexed INScopus

Abstract

This book discusses the unique nature and complexity of fog data analytics (FDA) and develops a comprehensive taxonomy abstracted into a process model. The exponential increase in sensors and smart gadgets (collectively referred as smart devices or Internet of things (IoT) devices) has generated significant amount of heterogeneous and multimodal data, known as big data. To deal with this big data, we require efficient and effective solutions, such as data mining, data analytics and reduction to be deployed at the edge of fog devices on a cloud. Current research and development efforts generally focus on big data analytics and overlook the difficulty of facilitating fog data analytics (FDA). This book presents a model that addresses various research challenges, such as accessibility, scalability, fog nodes communication, nodal collaboration, heterogeneity, reliability, and quality of service (QoS) requirements, and includes case studies demonstrating its implementation. Focusing on FDA in IoT and requirements related to Industry 4.0, it also covers all aspects required to manage the complexity of FDA for IoT applications and also develops a comprehensive taxonomy.

Security and Privacy of Electronics Healthcare Records

Book

PublisherIET Publications (450 Pages)

Published YearJune 2019

ISSN/ISBN No978-1-78561-898-7

Indexed INScopus

Abstract

Gathering international contributions, this book is the first “how-to” guide addressing privacy and security for Electronics Health Records (EHRs): Who can access EHR information? How can users and healthcare staff view EHR information and make sure it is correct? How is the information protected from loss, theft and hacking? What should users and healthcare staff do if they think the information has been compromised? The team of authors present a detailed framework for security and privacy in EHRs, as well as comparative case studies for privacy preservation, scalability, and healthcare legislation.

SWIPT-NOMA Based Framework for Heterogeneous Network with Imperfect Channel State Information

Conference

Title of PaperSWIPT-NOMA Based Framework for Heterogeneous Network with Imperfect Channel State Information

Proceeding Name15th International Wireless Communications Mobile Computing Conference (IEEE IWCMC-2019), Tangier, Morocco,

Year , VenueJune 2019 , (IEEE IWCMC-2019), Tangier, Morocco,

Page Number1-6

Indexed INScopus

A proposed Buffer based Load balanced Optical Switch with AO-NACK scheme in modern Optical DataCentres

Book Chapter

Book NameSpringer International Conference on Emerging Trends in Information Technology (ICETIT-2019)

PublisherSpringer International Conference on Emerging Trends in Information Technology (ICETIT-2019)

Chapter TitleA proposed Buffer based Load balanced Optical Switch with AO-NACK scheme in modern Optical DataCentres

Published YearJune 2019

Indexed INScopus

Multimedia Big Data Computing for IoT Applications: Concepts, Paradigms and Solutions

Book

PublisherSpringer Nature Singapore Pte Ltd., Singapore

Published YearMay 2019

ISSN/ISBN No978-981-13-8759-3

Indexed INScopus

Abstract

This book considers all aspects of managing the complexity of Multimedia Big Data Computing (MMBD) for IoT applications and develops a comprehensive taxonomy. It also discusses a process model that addresses a number of research challenges associated with MMBD, such as scalability, accessibility, reliability, heterogeneity, and Quality of Service (QoS) requirements, presenting case studies to demonstrate its application. Further, the book examines the layered architecture of MMBD computing and compares the life cycle of both big data and MMBD. Written by leading experts, it also includes numerous solved examples, technical descriptions, scenarios, procedures, and algorithms.

Standardising the use of Duplex Channels in 5G-WiFi Networking for Ambient Assisted Living

Conference

Title of PaperStandardising the use of Duplex Channels in 5G-WiFi Networking for Ambient Assisted Living

Proceeding NameIEEE Conference on Communications (IEEE ICC- 2019), Shanghai, China

PublisherIEEE

OrganizationIEEE Conference on Communications (IEEE ICC- 2019), Shanghai, China

Year , VenueMay 2019 , IEEE Conference on Communications (IEEE ICC- 2019), Shanghai, China

Page Number1-6

Indexed INScopus

Can Tactile Internet be a Solution for Low Latency Heart Disorientation Measure: An Analysis

Conference

Title of PaperCan Tactile Internet be a Solution for Low Latency Heart Disorientation Measure: An Analysis

Proceeding NameIEEE Conference on Communications (IEEE ICC-2019), Shanghai, China,

PublisherIEEE

Organization (IEEE ICC-2019), Shanghai, China,

Year , VenueMay 2019 , IEEE Conference on Communications (IEEE ICC-2019), Shanghai, China,

Page Number1-6

Indexed INScopus

Probabilistic Markov Model-based Health Routine Recommender System for Sleep Apnea Patients

Conference

Title of PaperProbabilistic Markov Model-based Health Routine Recommender System for Sleep Apnea Patients

Proceeding NameIEEE Conference on Communications (IEEE ICC-2019), Shanghai, China

OrganizationIEEE Conference on Communications (IEEE ICC-2019), Shanghai, China

Year , VenueMay 2019 , Shanghai, China

Page Number1-6

Indexed INScopus

Chapter 9 Specific Cloud Service Models

Book Chapter

Book NameInstant Guide to Cloud Computing, A. Nayyar (ed.), BPB Publications

Publisher BPB Publications

Page Number299-342

Chapter TitleChapter 9 Specific Cloud Service Models

Published YearApril 2019

ISSN/ISBN No978-93-88176-66-8

Indexed INScopus

Chapter 3: Software Errors

Book Chapter

Book NameA. Nayyar (ed.) Software Testing, BPB Publications,

PublisherA. Nayyar (ed.) Software Testing, BPB Publications,

Chapter TitleChapter 3: Software Errors

Published YearApril 2019

Indexed INScopus

Tactile Internet for Autonomous Vehicles: Latency and Reliability Analysis

Journal

Journal NameIEEE Wireless Communication Magazine

Title of PaperTactile Internet for Autonomous Vehicles: Latency and Reliability Analysis

Published YearApril 2019

Indexed INScopus, Web of Science

Securing Electronics Healthcare Records in Healthcare 4.0: A Biometric-based Approach

Journal

Journal NameComputers & Electrical Engineering,

Title of PaperSecuring Electronics Healthcare Records in Healthcare 4.0: A Biometric-based Approach

Published YearApril 2019

Indexed INScopus, Web of Science

DIYA: Tactile Internet Driven Delay Assessment NOMA-based Scheme for D2D Communication

Journal

Journal NameIEEE Transaction on Industrial Informatics

Title of PaperDIYA: Tactile Internet Driven Delay Assessment NOMA-based Scheme for D2D Communication

Page Number1-12

Published YearApril 2019

Indexed INScopus, Web of Science

Chapter 9: Specific Cloud Service Models

Book Chapter

Book NameInstant Guide to Cloud Computing, BPB Publications, 2018

Publisher BPB Publications, 2018

Chapter TitleChapter 9: Specific Cloud Service Models

Published YearApril 2019

ISSN/ISBN No978-93-88176-66-8

Indexed INScopus

Energy Conservation for IoT Devices: Concepts, Paradigms and Solutions

Book

PublisherSpringer Nature Singapore Pte Ltd., Singapore

Published YearMarch 2019

ISSN/ISBN No978-981-13-7399-2

Indexed INScopus

Mobile Edge Computing enabled Blockchain FrameworkA survey

Book Chapter

Book NameSpringer 2nd International Conference on Recent Innovations in Computing (ICRIC-2019)

PublisherSpringer 2nd International Conference on Recent Innovations in Computing (ICRIC-2019)

Page Number1-14

Chapter TitleMobile Edge Computing enabled Blockchain FrameworkA survey

Published YearMarch 2019

Indexed INScopus

Dynamic Distance based Lifetime Enhancement Scheme for HWSN

Book Chapter

Book NameSpringer 2nd International Conference on Recent Innovations in Computing (ICRIC-2019),

PublisherSpringer 2nd International Conference on Recent Innovations in Computing (ICRIC-2019),

Page Number1-16

Chapter TitleDynamic Distance based Lifetime Enhancement Scheme for HWSN

Published YearMarch 2019

Indexed INScopus

Sensor’s Energy and Performance Enhancement using LIBP in Contiki with Cooja

Book Chapter

Book NameSpringer 2nd International Conference on Innovative Computing and Communication (ICICC-2019), 21st − 22nd March, 2019 at VSB - Technical University Of Ostrava, Czech Republic

PublisherSpringer

Author Namesudeep tanwar

Chapter TitleSensor’s Energy and Performance Enhancement using LIBP in Contiki with Cooja

Published YearMarch 2019

Indexed INScopus

Tactile Internet for Industry 4.0 in 5G Era: A Comprehensive Review

Journal

Journal NameInternational Journal of Communication System

Title of PaperTactile Internet for Industry 4.0 in 5G Era: A Comprehensive Review

Published YearMarch 2019

Indexed INScopus, Web of Science

“Software Defined Vehicular Networks: A Comprehensive Review

Journal

Journal NameInternational Journal of Communication System

Title of Paper“Software Defined Vehicular Networks: A Comprehensive Review

Page Number1-26

Published YearMarch 2019

Indexed INScopus, Web of Science

Cross Layer NOMA Interference Mitigation for Femtocell users in 5G

Journal

Journal NameIEEE Transaction Vehicular Technology,

Title of PaperCross Layer NOMA Interference Mitigation for Femtocell users in 5G

Page Number1-12

Published YearFebruary 2019

Indexed INScopus, Web of Science

BHEEM: A Blockchain-based Framework for Securing Electronic Health Records

Conference

Title of PaperBHEEM: A Blockchain-based Framework for Securing Electronic Health Records

Proceeding NameIEEE GLOBECOM Conference, Abu Dhabi, UAE

PublisherIEEE GLOBECOM Conference, Abu Dhabi, UAE

Year , VenueFebruary 2019 , Abu Dhabi, UAE

Indexed INScopus

Abstract

BHEEM: A Blockchain-based Framework for Securing Electronic Health Records

Human Arthritis Analysis in Fog Computing Environment using Bayesian Network Classifier and Thread Protocol

Journal

Journal NameIEEE Consumer Electronics Magazine (In press; Impact Factor: 1.434 (SCI))

Title of PaperHuman Arthritis Analysis in Fog Computing Environment using Bayesian Network Classifier and Thread Protocol

Published YearJanuary

ISSN/ISBN No2162-2248

Indexed INScopus, Web of Science

Abstract

he scope covers the following areas that are related to “consumer electronics” and other topics considered of interest to consumer electronics: video technology, audio technology, white goods, home care products, mobile communications, gaming, air care products, home medical devices, fitness devices, home automation and networking devices, consumer solar technology, home theater, digital imaging,

Fog Data Analytics: A Taxonomy and Process Model

Journal

Journal NameJournal of Network and Computer Applications

Title of PaperFog Data Analytics: A Taxonomy and Process Model

Volume Number128

Page Number90-104, 2019

Published YearJanuary 2019

Indexed INScopus, Web of Science

Fog Computing for Smart Grid Systems in 5G Environment: Challenges and Solutions

Journal

Journal NameIEEE Wireless Communication Magazine

Title of PaperFog Computing for Smart Grid Systems in 5G Environment: Challenges and Solutions

PublisherIEEE

Page Number1-7

Published YearJanuary 2019

Indexed INScopus, Web of Science

TILAA: Tactile Internet-based Ambient Assistant Living In Fog Environment

Journal

Journal NameFuture Generation Computer Systems

Title of PaperTILAA: Tactile Internet-based Ambient Assistant Living In Fog Environment

Volume Number98

Page Number635-649

Published YearJanuary 2019

Indexed INScopus, Web of Science

Evaluation of Pattern based Customized Approach for Stock Market Trend Prediction with Big Data and Machine Learning Techniques

Journal

Journal NameInternational Journal of Business Analytics, IGI Global

Title of PaperEvaluation of Pattern based Customized Approach for Stock Market Trend Prediction with Big Data and Machine Learning Techniques

Page Number1-13

Published YearJanuary 2019

Indexed INScopus

Resolving Conflicts in Requirement Engineering Through Agile Software Development: A Comparative Case Study”

Book Chapter

Book NameInternational Conference on Innovative Computing and Communications. Lecture Notes in Networks and Systems

PublisherSpringer, Singapore

Page Number349-357

Chapter TitleResolving Conflicts in Requirement Engineering Through Agile Software Development: A Comparative Case Study”

Published YearJanuary 2019

Indexed INScopus

Chapter 10: Resource Allocation in Cloud Computing

Book Chapter

Book NameInstant Guide to Cloud Computing, A. Nayyar (ed.), BPB Publications

PublisherBPB Publications

Page Number343-376

Chapter TitleChapter 10: Resource Allocation in Cloud Computing

Published YearJanuary 2019

ISSN/ISBN No978-93-88176-66-8

Indexed INScopus

Online Signature-based Biometrics Recognition

Book Chapter

Book NameBiometric-Based Physical and Cybersecurity Systems,, Springer Nature Switzerland AG 2019

PublisherBiometric-Based Physical and Cybersecurity Systems,, Springer Nature Switzerland AG 2019

Page Number255-285

Chapter Title Online Signature-based Biometrics Recognition

Published YearJanuary 2019

Indexed INScopus

Boosted Neural Network Ensemble Classification for Lung Cancer Disease Diagnosis”

Journal

Journal NameApplied Soft Computing

Title of PaperBoosted Neural Network Ensemble Classification for Lung Cancer Disease Diagnosis”

Published YearJanuary 2019

Indexed INScopus, Web of Science

Fog Data Analytics: A Taxonomy and Process Model

Journal

Journal NameJournal of Network and Computer Applications

Title of PaperFog Data Analytics: A Taxonomy and Process Model

Published YearJanuary 2019

ISSN/ISBN No1084-8045

Indexed INScopus, Web of Science

Hybrid Energy System for Upgrading the Rural Environment

Conference

Title of PaperHybrid Energy System for Upgrading the Rural Environment

Proceeding NameIEEE GLOBECOM Conference, Abu Dhabi, UAE

PublisherIEEE GLOBECOM Conference, Abu Dhabi, UAE

Year , VenueJanuary 2019 , Abu Dhabi, UAE

Indexed INScopus

Base Station Oriented Multi-Route Diversity Protocol for Wireless Sensor Networks

Conference

Title of PaperBase Station Oriented Multi-Route Diversity Protocol for Wireless Sensor Networks

Proceeding NameIEEE GLOBECOM Conference, Abu Dhabi, UAE

PublisherIEEE GLOBECOM Conference, Abu Dhabi, UAE

Year , VenueJanuary 2019 , Abu Dhabi, UAE

Indexed INScopus

Data Consumption-Aware Load Forecasting Scheme for Smart Grid Systems

Conference

Title of PaperData Consumption-Aware Load Forecasting Scheme for Smart Grid Systems

Proceeding NameIEEE GLOBECOM Conference, Abu Dhabi, UAE

PublisherIEEE GLOBECOM Conference, Abu Dhabi, UAE

Year , VenueJanuary 2019 , Abu Dhabi, UAE

Indexed INScopus

Tensor Decomposition of Biometric Data using Singular Value Decomposition

Conference

Title of PaperTensor Decomposition of Biometric Data using Singular Value Decomposition

Proceeding Name5th IEEE-PDGC-2018 (Indexing in SCOPUS)

Publisher5th IEEE-PDGC-2018

Published YearJanuary 2019

Indexed INScopus

Abstract

Tensor Decomposition of Biometric Data using Singular Value Decomposition.

Comparison and Evaluation of Real Time Reservation Technologies in the Intelligent Public Transport System

Conference

Title of PaperComparison and Evaluation of Real Time Reservation Technologies in the Intelligent Public Transport System

Proceeding NameFifth International Conference on Parallel, Distributed and Grid Computing (PDGC) (PDGC-2018), Jaypee University of Information Technology, Waknaghat, Solan, Himachal Pradesh, India

Page Number1-6

Published YearDecember 2018

Indexed INScopus

CR-NOMA based Interference Mitigation Scheme for 5G Femtocells users

Conference

Title of PaperCR-NOMA based Interference Mitigation Scheme for 5G Femtocells users

Proceeding NameIEEE Global Communications Conference (IEEE GLOBECOM- 2018), Abu Dhabi, UAE,

Year , VenueDecember 2018 , (IEEE GLOBECOM- 2018), Abu Dhabi, UAE,

Page Number1-6

Indexed INScopus

MRD: Sink-based Multi Route Diversity for Wireless Sensor Networks

Conference

Title of PaperMRD: Sink-based Multi Route Diversity for Wireless Sensor Networks

Proceeding NameIEEE Global Communications Conference (IEEE GLOBECOM-2018) Abu Dhabi, UAE

Page Number1-6

Published YearDecember 2018

Indexed INScopus

Hybrid Energy System for Upgrading the Rural Environment

Conference

Title of PaperHybrid Energy System for Upgrading the Rural Environment

Proceeding NameIEEE Global Communications Conference (IEEE GLOBECOM-2018), Abu Dhabi, UAE

PublisherIEEE Global Communications Conference (IEEE GLOBECOM-2018), Abu Dhabi, UAE

Page Number1-6

Published YearDecember 2018

Indexed INScopus

“Comparison and Evaluation of Real Time Reservation Technologies in the Intelligent Public Transport System

Book Chapter

Book NameFifth International Conference on Parallel, Distributed and Grid Computing (PDGC) (PDGC-2018),

Page Number1-6

Chapter Title“Comparison and Evaluation of Real Time Reservation Technologies in the Intelligent Public Transport System

Published YearDecember 2018

Indexed INScopus

Tensor Decomposition of Biometric Data using Singular Value Decomposition

Book Chapter

Book NameFifth International Conference on Parallel, Distributed and Grid Computing (PDGC) (PDGC-2018)

Page Number1-6

Chapter TitleTensor Decomposition of Biometric Data using Singular Value Decomposition

Published YearDecember 2018

Indexed INScopus

A Systematic Review on Scheduling Public Transport Using IoT as Tool

Book Chapter

Book NameSmart Innovations in Communication and Computational Sciences. Advances in Intelligent Systems and Computing

Publisher Springer, Singapore

Page Number 39-48

Chapter TitleA Systematic Review on Scheduling Public Transport Using IoT as Tool

Published YearDecember 2018

Indexed INScopus

Energy Harvesting-Based Two-Hop Clustering for Wireless Mesh Network

Book Chapter

Book NameAdvances in Intelligent Systems and Computing

PublisherSpringer, Singapore

Page Number463-476

Chapter TitleEnergy Harvesting-Based Two-Hop Clustering for Wireless Mesh Network

Published YearDecember 2018

Indexed INScopus

Combining User-based and Item-based Collaborative Filtering using Machine Learning

Book Chapter

Book NameIn: Satapathy S., Joshi A. (eds)3rd International Conference on Information and Communication Technology for Intelligent Systems (ICTIS-2018), April 06-07, 2018, Ahmedabad, vol 107. Springer, Singapore,

PublisherSpringer, Singapore

Page Number173-180

Chapter TitleCombining User-based and Item-based Collaborative Filtering using Machine Learning

Published YearDecember 2018

Indexed INScopus

Multimedia Big Data Computing and Internet of Things Applications: A Taxonomy and Process Model

Journal

Journal NameJournal of Network and Computer Applications

Title of PaperMultimedia Big Data Computing and Internet of Things Applications: A Taxonomy and Process Model

Volume Number124

Page Number 169-195

Published YearDecember 2018

ISSN/ISBN No1084-8045

Indexed INScopus, Web of Science

Abstract

With an exponential increase in the provisioning of multimedia devices over the Internet of Things (IoT), a significant amount of multimedia data (also referred to as multimedia big data – MMBD) is being generated. Current research and development activities focus on scalar sensor data based IoT or general MMBD and overlook the complexity of facilitating MMBD over IoT.

ADYTIA: Adaptive and Dynamic TCP Interface Architecture for Mobile Data Offloading in Heterogeneous Networks

Journal

Journal NameInternational Journal of Communication System

Title of PaperADYTIA: Adaptive and Dynamic TCP Interface Architecture for Mobile Data Offloading in Heterogeneous Networks

Volume Number32:2

Page Number1-20

Published YearNovember 2018

Indexed INScopus, Web of Science

Verification and Validation Techniques for Streaming Big Data Analytics in Internet of Things Environment

Journal

Journal NameIET Networks, 2019,

Title of PaperVerification and Validation Techniques for Streaming Big Data Analytics in Internet of Things Environment

Page Number1-8, DOI: 10.1049/ietnet.2018.518, 2019

Published YearNovember 2018

Indexed INScopus

Fog Computing for Healthcare 4.0 Environment: Opportunities and Challenges

Journal

Journal NameComputers & Electrical Engineering, Elsevier (SCI, IF: 1.747)

Title of PaperFog Computing for Healthcare 4.0 Environment: Opportunities and Challenges

PublisherElsevier

Volume Number72

Page Number1-13

Published YearNovember 2018

ISSN/ISBN No0045-7906

Indexed INScopus, Web of Science

Abstract

Internet of things provides interaction with billions of objects across the world using the Internet. In Internet of thing era, Healthcare Industry has grown-up from 1.0 to 4.0 generation. Healthcare 3.0 was hospital centric, where patients of long-lasting sickness suffered a lot due to multiple hospital visits for their routine checkups. This in turn, prolonged the treatment of such patients.

Resolving Conflicts in Requirement Engineering through Agile Software Development: A Comparative Case Study

Book Chapter

Book NameIn: Bhattacharyya S., Hassanien A., Gupta D., Khanna A., Pan I. (eds) International Conference on Innovative Computing and Communications. Lecture Notes in Networks and Systems, vol 55. Springer, Singapore

PublisherLecture Notes in Networks and Systems, Springer

Author Name Bhattacharyya, S., Hassanien

Page Number349-357

Chapter TitleResolving Conflicts in Requirement Engineering through Agile Software Development: A Comparative Case Study

Published YearNovember 2018

ISSN/ISBN No978-981-13-2324-9

Indexed INScopus

“A Systematic Review on Security Issues in VANET”, Security and P

Journal

Journal NameSecurity and Privacy Journal, Wiley

Title of Paper“A Systematic Review on Security Issues in VANET”, Security and P

PublisherWiley

Volume Number1:5

Page Number1-27

Published YearAugust 2018

Indexed INScopus, Web of Science

A Systematic Review on Scheduling Public Transport using IoT as Tool

Conference

Title of PaperA Systematic Review on Scheduling Public Transport using IoT as Tool

Proceeding NameSmart Innovations in Communication and Computational Sciences. Advances in Intelligent Systems and C

PublisherSpringer, Singapore,

Year , VenueJuly 2018 , Singapore,

Page Number39-48

ISSN/ISBN No978-981-10-8970-1

Indexed INScopus

Design of an Anonymity-Preserving Group Formation Based Authentication Protocol in Global Mobility Networks

Journal

Journal NameIEEE Access (SCI, Impact Factor: 3.557)

Title of PaperDesign of an Anonymity-Preserving Group Formation Based Authentication Protocol in Global Mobility Networks

PublisherIEEE Access

Volume Number6(1)

Page Number20673-20693

Published YearMay 2018

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

Global mobility networks (GLOMONETs) provide the ubiquitous services for mobile users while enabling global roaming. Each user belongs to a specific home network (HA) where he/she is registered. When a user is in the domain of a foreign agent (FA), the FA needs to provide service only after authenticating the user (with HA’s help). A remote user authentication scheme for GLOMONETs needs to validat

M-Tesla-Based Security Assessment in Wireless Sensor Network

Journal

Journal NameProcedia Computer Science, Elsevier. (Indexed in SCOPUS)

Title of PaperM-Tesla-Based Security Assessment in Wireless Sensor Network

PublisherElsevier

Volume Number132

Page Number1154-1162.

Published YearApril 2018

ISSN/ISBN No1877-0509

Indexed INScopus, Web of Science

LA-MHR: Learning Automata Based Multilevel Heterogeneous Routing for Opportunistic Shared Spectrum Access to Enhance Lifetime of WSN

Journal

Journal NameIEEE Access (SCI, Impact Factor: 3.557)

Title of PaperLA-MHR: Learning Automata Based Multilevel Heterogeneous Routing for Opportunistic Shared Spectrum Access to Enhance Lifetime of WSN

Publisher IEEE Systems Journal

Volume Number6

Page Number1-11

Published YearApril 2018

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

n wireless sensor networks (WSNs), optimal energy utilization is one of the most crucial issues which needs special attention. It has been observed from the existing literature that communication among sensor nodes (SNs) consumes more energy than computation. Therefore, an efficient mechanism needs to be designed for energy conservation during communication among different SNs. To address these ga

Chapter 10: Resource Allocation in Cloud Computing

Book Chapter

Book NameInstant Guide to Cloud Computing, BPB Publications, 2018

PublisherBPB Publications, 2018

Chapter TitleChapter 10: Resource Allocation in Cloud Computing

Published YearApril 2018

ISSN/ISBN No978-93-88176-66-8

Indexed INScopus

Software Defined Network-Based Vehicular Adhoc Networks for Intelligent Transportation System: Recent Advances and Future Challenges

Book Chapter

Book NameCommunications in Computer and Information Science

PublisherSpringer singapure

Page Number325-337

Chapter TitleSoftware Defined Network-Based Vehicular Adhoc Networks for Intelligent Transportation System: Recent Advances and Future Challenges

Published YearFebruary 2018

Indexed INScopus

Dimensionality Reduction using PCA and SVD in Big Data: A Comparative Case Study”

Book Chapter

Book NameSocial Informatics and Telecommunications Engineering, Springer International Publishing, presented at SVNIT, Surat, Gujarat

Page Number116-125

Chapter TitleDimensionality Reduction using PCA and SVD in Big Data: A Comparative Case Study”

Published YearJanuary 2018

ISSN/ISBN No978-3-319-73711-9

Indexed INScopus

Dimensionality Reduction using PCA and SVD in Big Data: A Comparative Case Study

Journal

Journal NameSpringer LN of the Institute for Computer Sciences, Social Informatics and Telecommunications Engine

Title of PaperDimensionality Reduction using PCA and SVD in Big Data: A Comparative Case Study

PublisherSpringer

Volume Number220

Page Number116-125

Published YearJanuary 2018

ISSN/ISBN No1867-8211

Indexed INScopus, Web of Science

Abstract

With the advancement in technology, data produced from different sources such as Internet, health care, financial companies, social media, etc. are increases continuously at a rapid rate. Potential growth of this data in terms of volume, variety and velocity coined a new emerging area of research, Big Data (BD). Continuous storage, processing, monitoring (if required), real time analysis are few

LA-MHR: Learning Automata Based Multi-level Heterogeneous Routing for Opportunistic Shared Spectrum Access to Enhance Lifetime of WSN

Journal

Journal NameIEEE Systems Journal, (SCI, Impact Factor: 4.337)

Title of PaperLA-MHR: Learning Automata Based Multi-level Heterogeneous Routing for Opportunistic Shared Spectrum Access to Enhance Lifetime of WSN

PublisherIEEE

Page Number2169-3536

Published YearJanuary 2018

ISSN/ISBN No1932-8184

Indexed INScopus, Web of Science

Abstract

Wireless Sensor Networks (WSNs) consist of many Sensor Nodes (SNs) which may be deployed at different geographical locations to perform multiple tasks such as monitoring, data aggregation, and data processing. During all these operations, energy of the SNs continuously depleted which results the creation of energy holes in some regions.

APD-JFAD: Accurate Prevention and Detection of Jelly Fish Attack in MANET

Journal

Journal NameIEEE Access- Accepted for Publication in next issue (SCI, Impact Factor: 3.557)

Title of PaperAPD-JFAD: Accurate Prevention and Detection of Jelly Fish Attack in MANET

PublisherIEEE Access

Published YearJanuary 2018

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Tree-based Ant Colony Optimization Algorithm for Effective Multicast Routing in Mobile Adhoc Network

Journal

Journal NameRecent Patents on Computer Science, accepted for publication (SCOPUS)

Title of PaperTree-based Ant Colony Optimization Algorithm for Effective Multicast Routing in Mobile Adhoc Network

Volume Number12

Published YearJanuary 2018

ISSN/ISBN No1874-4796

Indexed INScopus, Web of Science

ADYTIA: Adaptive and Dynamic TCP Interface Architecture for Heterogeneous Networks

Journal

Journal NameInternational Journal of Communication Systems, Wiley (SCI, Impact factor 1.717)

Title of PaperADYTIA: Adaptive and Dynamic TCP Interface Architecture for Heterogeneous Networks

PublisherJohn Wiley

Published YearJanuary 2018

ISSN/ISBN No1099-1131

Indexed INScopus, Web of Science

Ensuring Privacy and Security in E-Health Records

Conference

Title of PaperEnsuring Privacy and Security in E-Health Records

PublisherIEEE CITS-2018, Colmar, France

Year , VenueJanuary 2018 , IEEE CITS-2018, Colmar, France

ISSN/ISBN No978-1-5386-4599-4

Indexed INScopus

Blind Signatures Based Secured E-Healthcare System

Conference

Title of PaperBlind Signatures Based Secured E-Healthcare System

PublisherIEEE CITS-2018, Colmar, France

Year , VenueJanuary 2018 , IEEE CITS-2018, Colmar, France

ISSN/ISBN No978-1-5386-4599-4

Indexed INScopus

TCP-EXPO: Empirical Approach to Transport Layer Protocol for High-Speed Networks

Conference

Title of PaperTCP-EXPO: Empirical Approach to Transport Layer Protocol for High-Speed Networks

Proceeding NameIEEE ICC-2018, Kansas City, USA (Indexed in IEEE-Xplore, SCOPUS)

PublisherIEEE ICC-2018, Kansas City, USA (Indexed in IEEE-Xplore, SCOPUS)

Year , VenueJanuary 2018 , IEEE ICC-2018, Kansas City, USA

ISSN/ISBN No2474-9133

Indexed INScopus

A Range-based approach for Long-Term Forecast of Weather Using Probabilistic Markov Model

Conference

Title of PaperA Range-based approach for Long-Term Forecast of Weather Using Probabilistic Markov Model

PublisherIEEE ICC-2018, Kansas City, USA (Indexed in IEEE-Xplore, SCOPUS)

Year , VenueJanuary 2018 , IEEE ICC-2018, Kansas City, USA

ISSN/ISBN No2474-9133

Indexed INScopus

Software Defined Network-based Vehicular Adhoc Networks for Intelligent Transportation System: Recent Advances and Future Challenges

Conference

Title of PaperSoftware Defined Network-based Vehicular Adhoc Networks for Intelligent Transportation System: Recent Advances and Future Challenges

Proceeding NameSpringer International Conference FTNCT-2018. (CCIS Series, Indexing in SCOPUS

PublisherSpringer International Conference FTNCT-2018. (CCIS Series, Indexing in SCOPUS

Published YearJanuary 2018

Indexed INScopus

Performance Evaluation of SDN based Virtualization for Data Center Networks

Conference

Title of PaperPerformance Evaluation of SDN based Virtualization for Data Center Networks

Proceeding NameIEEE 3rd International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU 2018)

PublisherIEEE 3rd International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU 2018)

Published YearJanuary 2018

ISSN/ISBN No978-1-5090-6785-5

Indexed INScopus

Image Processing Based Analysis of Cracks on Vertical Walls

Conference

Title of PaperImage Processing Based Analysis of Cracks on Vertical Walls

Proceeding NameEEE 3rd International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU 2018)

PublisherEEE 3rd International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU 2018)

Published YearJanuary 2018

ISSN/ISBN No978-1-5090-6785-5

Indexed INScopus

Ethical, Legal, and Social Implications of Biometrics Technologies

Book Chapter

Book NameM. S. Obaidat et al. (eds.), Biometric-Based Physical and Cybersecurity Systems

PublisherSpringer Nature, 2018

Chapter TitleEthical, Legal, and Social Implications of Biometrics Technologies

Published YearJanuary 2018

ISSN/ISBN No978-3-319-98734-7

Indexed INScopus

Abstract

his book presents the latest developments in biometrics technologies and reports on new approaches, methods, findings, and technologies developed or being developed by the research community and the industry. The book focuses on introducing fundamental principles and concepts of key enabling technologies for biometric systems applied for both physical and cyber security.

Mobile Computing

Book

PublisherBhavya Publication, Delhi

Published YearMarch 2017

ISSN/ISBN No978-93-83992-25-6

Energy Optimization in Smart Grid using Tensor Decomposition

Journal

Journal NameInternational Journal of Computer Sciences and Engineering (Indexed in ICI, Google Scholar,UGC listed

Title of PaperEnergy Optimization in Smart Grid using Tensor Decomposition

Volume Number5:11

Page Number192-196

Published YearJanuary 2017

ISSN/ISBN No0974-5572

Indexed INScopus, Web of Science

Public Transport Tracking and its Issues

Journal

Journal NameInternational Journal of Computer Sciences and Engineering (Indexed in ICI, Google Scholar as well a

Title of PaperPublic Transport Tracking and its Issues

Volume Number5:11

Published YearJanuary 2017

ISSN/ISBN No2347-2693

Indexed INScopus, Web of Science

HDNcfm: Handwritten Digit Recognition System Using No Combination of Feature Maps

Journal

Journal NameInternational Journal of Advanced Research in Computer Science

Title of Paper HDNcfm: Handwritten Digit Recognition System Using No Combination of Feature Maps

Volume Number8

Published YearJanuary 2017

ISSN/ISBN No0976-5697

Indexed INScopus, Web of Science

PI-Cloud: A Sensor-Cloud oriented Measurement to Management System for Precise Irrigation based Agriculture

Conference

Title of PaperPI-Cloud: A Sensor-Cloud oriented Measurement to Management System for Precise Irrigation based Agriculture

Proceeding NameIEEE International Conference on Global Communication, GLOBECOM- 2017, Singapore

Year , VenueJanuary 2017 , GLOBECOM- 2017, Singapore

ISSN/ISBN No978-1-5090-5019-2

Indexed INScopus

Suitability of Big Data Analytics in Indian Banking Sector to Increase Revenue and Profitability

Conference

Title of PaperSuitability of Big Data Analytics in Indian Banking Sector to Increase Revenue and Profitability

Proceeding NameIEEE, ICACCA-2017, Tula Institute, Dehradhun, UA

Year , VenueJanuary 2017 , IEEE, ICACCA-2017, Tula Institute, Dehradhun, UA

ISSN/ISBN No978-1-5090-6403-8

Indexed INScopus

Fog based Enhanced Safety Management System for Miners

Conference

Title of PaperFog based Enhanced Safety Management System for Miners

Proceeding NameIEEE, ICACCA-2017, Tula Institute, Dehradhun, UA

Year , VenueJanuary 2017 , IEEE, ICACCA-2017, Tula Institute, Dehradhun, UA

ISSN/ISBN No978-1-5090-6403-8

Indexed INScopus

FAAL: Fog Computing based Patient Monitoring System for Ambient Assisted Living

Conference

Title of PaperFAAL: Fog Computing based Patient Monitoring System for Ambient Assisted Living

Proceeding NameIEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom-2017

PublisherIEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom-2017

Published YearJanuary 2017

ISSN/ISBN No978-1-5090-6704-6

Indexed INScopus

Home-based Exercise System for Patients Using IoT Enabled Smart Speaker

Conference

Title of PaperHome-based Exercise System for Patients Using IoT Enabled Smart Speaker

Proceeding NameIEEE 19th International Conference on e-Health Networking, Applications and Services, Healthcom-2017

Published YearJanuary 2017

ISSN/ISBN No978-1-5090-6704-6

Indexed INScopus

An Advanced Internet of Thing based Security Alert System for Smart Home

Conference

Title of PaperAn Advanced Internet of Thing based Security Alert System for Smart Home

PublisherInternational Conference on Computer, Information and Telecommunication Systems IEEE-CITS-2017, Dali

Year , VenueJanuary 2017 , IEEE-CITS-2017, Dali

ISSN/ISBN No978-1-5090-5957-7

Indexed INScopus

GATA: GPS-Arduino Based Tracking and Alarm System for Protection of Wildlife Animals

Conference

Title of PaperGATA: GPS-Arduino Based Tracking and Alarm System for Protection of Wildlife Animals

Proceeding Namenternational Conference on Computer, Information and Telecommunication Systems IEEE-CITS-2017, Dali

Publishernternational Conference on Computer, Information and Telecommunication Systems IEEE-CITS-2017, Dali

Year , VenueJanuary 2017 , IEEE-CITS-2017, Dali

ISSN/ISBN No978-1-5090-5957-7

Indexed INScopus

Big Data Analytics

Book

PublisherBhavya Publication, Delhi

Published YearJanuary 2017

ISSN/ISBN No978-93-83992-25-8

Routing in Heterogeneous Wireless Sensor Networks

Book

PublisherLap Lambert Academic Publishing, Germany

Published YearDecember 2016

ISSN/ISBN No978-3-330-02892-0

Abstract

Although many proposals exist in market addressing the Routing in HWSN issue, but node heterogeneity of SNs has not been exploited to its full potential. So there is a requirement of categorization of SNs based upon different performance evaluation metrics. Motivated by the above facts, in this book, we provide a complete categorization of various heterogeneous routing protocols for WSNs.

Analysis of Software Testing Techniques: Theory to Practical Approach

Journal

Journal NameIndian Journal of Science and Technology

Title of PaperAnalysis of Software Testing Techniques: Theory to Practical Approach

Volume Number9(32)

Page Number1-6

Published YearAugust 2016

ISSN/ISBN No0974-6846

Indexed INScopus, Web of Science, EBSCO

Abstract

n today’s scenario software testing is crucial aspect for any software company because the cost of maintenance is much more than development in software companies. We all make mistakes, some of them are not important, but some of them are harmful for software life cycle. So we should start testing the code/software that we are going to generate from initial stage because at later stage recovery

Min-Parent: An Effective Approach to Enhance Resource Utilization in Cloud Environment,

Conference

Title of PaperMin-Parent: An Effective Approach to Enhance Resource Utilization in Cloud Environment,

PublisherIEEE-ICACCA- 2016, Dehradhun, UA

Published YearJanuary 2016

ISSN/ISBN No978-1-5090-0673-1

Indexed INScopus

Cognitive Radio-based Clustering for Opportunistic Shared Spectrum Access to Enhance Lifetime of Wireless Sensor Network

Journal

Journal NamePervasive and Mobile Computing, Elsevier (SCI, Impact Factor: 2.974)

Title of PaperCognitive Radio-based Clustering for Opportunistic Shared Spectrum Access to Enhance Lifetime of Wireless Sensor Network

PublisherElsevier

Volume Number22

Page Number90-112

Published YearSeptember 2015

ISSN/ISBN No1574-1192

Indexed INScopus, Web of Science

Abstract

In recent times, Cognitive radio (CR)-based wireless sensor networks (WSNs) have been widely used for opportunistic access of the shared spectrum. In WSNs, deployment of sensor nodes (SN) may be random, or it may follow an optimized approach-based upon the application in which it is to be used. Energy efficient route selection for transferring data from a SN to the base station (BS) is the key iss

A Systematic Review of Heterogeneous Routing Protocols for Wireless Sensor Network

Journal

Journal NameJournal of Network and Computer Application, Elsevier, (SCI, Impact Factor: 3.99)

Title of PaperA Systematic Review of Heterogeneous Routing Protocols for Wireless Sensor Network

PublisherElsevier

Volume Number53

Page Number 39-56

Published YearJuly 2015

ISSN/ISBN No1084-8045

Indexed INScopus, Web of Science

Abstract

The latest developments in wireless communication are more focused on delivering sensitive information to its final destination under several constraints such as energy, latency, reliability, stability, and security. Through the latest developments in digital technology, wireless transceiver, and Micro-Electro-Mechanical Systems (MEMS), it is possible to integrate sensing and computing units along

Extended Multi-level Heterogeneous routing protocol for Wireless Sensor Networks

Journal

Journal NameTelecommunication System, Springer (SCI, Impact Factor: 1.527)

Title of PaperExtended Multi-level Heterogeneous routing protocol for Wireless Sensor Networks

PublisherSpringer

Volume Number59

Page Number43-62

Published YearMay 2015

ISSN/ISBN No1018-4864 (Print) 1572-9451 (Online)

Indexed INScopus, Web of Science

Abstract

IoT, Smart Grid and M2M are paradigms that are expected to dominate in 5G networks and, hence, the role of WSNs is of great importance. In WSNs, horizontal and vertical levels of node heterogeneity has been studied in the past for various operation such as data capturing, processing and communication at different levels of nodes in wireless sensor networks (WSNs). For saving energy consumption of

Learning Automata-Based Coverage Oriented Clustering in HWSNs

Conference

Title of PaperLearning Automata-Based Coverage Oriented Clustering in HWSNs

Proceeding NameIEEE-ICACCE-2015, Dehradhun, UA

Year , VenueJanuary 2015 , Dehradhun, UA

ISSN/ISBN No978-1-4799-1734-1

Indexed INScopus

Bayesian Coalition Game-Based Optimized Clustering in Wireless Sensor Networks

Conference

Title of PaperBayesian Coalition Game-Based Optimized Clustering in Wireless Sensor Networks

Proceeding NameIEEE International Conference on Communications (IEEE-ICC-2015), London, UK

Published YearJanuary 2015

ISSN/ISBN No978-1-4673-6432-4

Indexed INScopus

EEMHR: Energy-efficient multilevel heterogeneous routing protocol for wireless sensor networks

Journal

Journal NameInternational Journal of Communication System, Wiley (SCI, Impact Factor: 1.717)

Title of PaperEEMHR: Energy-efficient multilevel heterogeneous routing protocol for wireless sensor networks

PublisherWiley

Volume Number27(9)

Published YearMarch 2014

ISSN/ISBN No1099-1131

Indexed INScopus, Web of Science

Abstract

Wireless Sensor Networks (WSNs) are being used in wide areas of applications for data collection and processing. Energy management is one of the crucial issues that need special attention in WSNs. But most of the existing solutions for energy management are restricted in defining the number of levels for node heterogeneity for efficient energy management. Due to this restriction, a performance deg

Selective Cluster Based Energy Efficient routing protocol for homogeneous wireless sensor network

Journal

Journal NameWireless BANs for Pervasive Healthcare & Smart Environments, ZTE Communication

Title of PaperSelective Cluster Based Energy Efficient routing protocol for homogeneous wireless sensor network

Volume Number12(3)

Published YearJanuary 2014

Indexed INScopus, Web of Science

EHE-LEACH: Enhanced Heterogeneous LEACH Protocol for Lifetime Enhancement of WSNs,

Conference

Title of PaperEHE-LEACH: Enhanced Heterogeneous LEACH Protocol for Lifetime Enhancement of WSNs,

Proceeding NameIEEE-ICACCI-3013 Cited by 14 (IEEE Digital Library), 24 (Google Scholar)

Published YearJanuary 2013

ISSN/ISBN No978-1-4673-6217-7

Indexed INScopus

Software Testability Analysis using Cyclomatic Complexity

Conference

Title of PaperSoftware Testability Analysis using Cyclomatic Complexity

Proceeding NameNational conference on RTACM, Tiagrajar School of Management, Madurai (Tamilnadu)

Year , VenueJanuary 2009 , National conference on RTACM, Tiagrajar School of Management, Madurai (Tamilnadu)

Indexed INScopus

MPI Messaging Structure for Mobile Adhoc Network

Journal

Journal NameInternational Journal of Hybrid Computational Intelligence

Title of PaperMPI Messaging Structure for Mobile Adhoc Network

Volume Number1(2)

Page Number215-224

Published YearJanuary 2008

ISSN/ISBN No0975-3680

Indexed INScopus, Web of Science

Substantiation System Using Facial Recognition and Principal Component Analysis

Conference

Title of PaperSubstantiation System Using Facial Recognition and Principal Component Analysis

Proceeding NameInternational Conference on Computing, Communication and Learning

PublisherSpringer Nature Switzerland

Author NameRamesh R. Naik, Sanjay patel, Sunil Gautam, Rohit Pachlor, Umesh bodkhe

Page Number189-199

Published YearAugust 2023

Indexed INScopus

Abstract

In today’s networked society, the need to guarantee the security of data or physical assets is both increasingly important and more difficult to do. We periodically hear about criminal activity like credit card fraud, computer hacking, or security flaws in a corporate or governmental setting. Since they use an individual’s physiological and behavioral characteristics to determine and ascertain his identity rather than using passwords to authenticate users and grant them access to physical and virtual domains, biometric based techniques have become the most promising option for identifying people in recent years. Magnetic cards may become distorted and unreadable. PINs and passwords are tricky to remember and vulnerable to theft or guesswork. The biological makeup of a person, however, cannot be forgotten, stolen, falsified, or lost. Face recognition appears to have a variety of advantages over other biometric methods, some of which are described below: For fingerprints or hand geometry detection, the user must place his hand on a hand rest, and for iris or retina recognition, the user must remain steady in front of a camera. A user’s intentional action is required for almost all of these technologies. The objective is to develop a face recognition system that can automatically identify and verify faces based on images in a gallery or database. We’ll employ the PCA method, which recognises by employing Eigen faces, to recognise. We want to know how often each class is recognised in our research.

Defense and Evaluation Against Covert Channel-Based Attacks in Android Smartphones

Conference

Title of PaperDefense and Evaluation Against Covert Channel-Based Attacks in Android Smartphones

Proceeding NameInternational Conference on Data Management, Analytics & Innovation

Page Number685-696

Published YearJanuary 2023

Indexed INScopus

Abstract

The Android operating system (OS) currently occupies the majority of the global smartphone market. Even IoT specific applications have prevailing OS as Android into their end device or intermediary communication channels. These Android smartphones may store sensitive data such as texts, banking information, personal identification numbers (PIN), contact-based information, GPS/location-specific information, images, movies, IoT device operations, and so on. Furthermore, Android devices are popular among users due to their extensive capabilities and multiple connectivity options, making them a perfect target for attackers. To get their task done, attackers are shifting to methods that neatly disguise existing state-of-the-art equipment and targets. One such strategy is evasion, which is used to deceive security systems or conceal information flow in order to evade detection. On the alternative side, covert channels disguise the existence of exchange itself, making it unidentifiable to both users and cutting-edge technology. These covert channels, by employing evasive methods, become extremely undetectable and bypass security architecture, ensuring the secure maintenance or transmission of the user's confidentiality-based information. The research evaluates and analyses existing state-of-the-art technologies, as well as identifies potential defense mechanisms for mitigating and detecting such threats.

Wireless Sensor Networks With the Context of Knowledge-Based Management

Book Chapter

Book NameConstraint Decision-Making Systems in Engineering

PublisherIGI Global

Author NameSunil Gautam

Page Number18-40

Chapter TitleWireless Sensor Networks With the Context of Knowledge-Based Management

Published YearJanuary 2023

Indexed INScopus

Abstract

Wireless sensor networks (WSN) play in vital role in different research area technology, electronics, and telecommunication, but these wireless sensor networks have limited computational capability and memory. The basic functions of WSN are analysis, processing, storage, and mining of data. Due to the flexibility of WSN in solving problems of various fields, it has gained more popularity. WSNs have been successfully applied in a variety of applications. In these days, knowledge management systems are attracting research that emerge with wireless sensor networks to reduce drawback of sensors. This chapter presents the review literature of knowledge management and demonstrates creating, managing, sharing, and utilizing in organizations.

Intelligent Intrusion Detection System Using Deep Learning Technique

Conference

Title of PaperIntelligent Intrusion Detection System Using Deep Learning Technique

Proceeding NameComputing, Communication and Learning: First International Conference, CoCoLe 2022

PublisherSpringer Nature Switzerland

Author NameSunil Gautam

OrganizationNIT Warangal,

Year , VenueJanuary 2023 , NIT Warangal,

Page Number220-230

Indexed INScopus

Abstract

There is constant growth in the digitization of information across the world. However, this rapid growth has raised concerns over the security of the information. Today’s internet is made up of nearly half a million different networks. Network intrusions are very common these days which put user information at high risk. An intrusion detection system (IDS) is a software/system to analyze and monitor the data for the detection of intrusions in the host/network. An intrusion Detection System competent in detecting zero-day attacks and network anomalies is highly demanded. Researchers have used different methods to develop robust IDS. However, none of the methods is exceptionally well and meets every requirement of IDS. Machine learning/Deep learning (ML/DL) are among the widely used methods to develop IDS. This proposed technique uses a DL model, Recurrent Neural Network (RNN) with Gated Recurrent

Composition of Hybrid Deep Learning Model and Feature Optimization for Intrusion Detection System

Journal

Journal NameMDPI Sensors

Title of PaperComposition of Hybrid Deep Learning Model and Feature Optimization for Intrusion Detection System

PublisherMDPI

Volume Number23(2)

Page Number890

Published YearJanuary 2023

Indexed INScopus, Web of Science

Abstract

Recently, with the massive growth of IoT devices, the attack surfaces have also intensified. Thus, cybersecurity has become a critical component to protect organizational boundaries. In networks, Intrusion Detection Systems (IDSs) are employed to raise critical flags during network management. One aspect is malicious traffic identification, where zero-day attack detection is a critical problem of study. Current approaches are aligned towards deep learning (DL) methods for IDSs, but the success of the DL mechanism depends on the feature learning process, which is an open challenge. Thus, in this paper, the authors propose a technique which combines both CNN, and GRU, where different CNN–GRU combination sequences are presented to optimize the network parameters. In the simulation, the authors used the CICIDS-2017 benchmark dataset and used metrics such as precision, recall, False Positive Rate (FPR), True Positive Rate (TRP), and other aligned metrics. The results suggest a significant improvement, where many network attacks are detected with an accuracy of 98.73%, and an FPR rate of 0.075. We also performed a comparative analysis with other existing techniques, and the obtained results indicate the efficacy of the proposed IDS scheme in real cybersecurity setups.

A composite approach of intrusion detection systems: hybrid RNN and correlation-based feature optimization

Journal

Journal NameElectronics

Title of PaperA composite approach of intrusion detection systems: hybrid RNN and correlation-based feature optimization

PublisherMDPI

Volume Number11

Published YearOctober 2022

Indexed INScopus, Web of Science

Abstract

Detection of intrusions is a system that is competent in detecting cyber-attacks and network anomalies. A variety of strategies have been developed for IDS so far. However, there are factors that they lack in performance, creating scope for further research. The current trend shows that the Deep Learning (DL) technique has been proven better than traditional techniques for IDS. Throughout these studies, we presented a hybrid model that is a Deep Learning method called Bidirectional Recurrent Neural Network using Long Short-Term Memory and Gated Recurrent Unit. Through simulations on the public dataset CICIDS2017, we have shown the model’s effectiveness. It has been noted that the suggested model successfully predicted most of the network attacks with 99.13% classification accuracy. The proposed model outperformed the Naïve Bayes classifier in terms of prediction accuracy and False Positive rate. The suggested model managed to perform well with only 58% attributes of the dataset compared to other existing classifiers. Moreover, this study also demonstrates the performance of LSTM and GRU with RNN independently.

Data-Driven Android Malware Analysis Intelligence

Book Chapter

Book NameMethods, Implementation, and Application of Cyber Security Intelligence and Analytics

PublisherIGI Global

Author NameSunil Gautam

Page Number181-200

Chapter TitleData-Driven Android Malware Analysis Intelligence

Published YearOctober 2022

Indexed INScopus

Abstract

Android OS powers the majority of the market share. Malware acts as stimuli to the vulnerabilities in Android devices as it affects a huge amount of user data. Users' data is at high risk when it comes to attacks through varied types of malware. Also, mutations in malware have brought up newer variants in them. Malware families have been expanding, thereby making analysis and classification diverse. Mainly classified into static, dynamic, and alternative or hybrid analysis, the field of malware analysis is facing many repercussions. The development of malware is endless and hence calls for intelligent and self-learning approaches in this regard. However, more distinct techniques are in need and can be served by integrating intelligent and analytical capabilities. This chapter involves a fourfold approach with major contributions to review existing Android malware analysis techniques, intelligent techniques for Android.

A Composite Approach of Intrusion Detection Systems: Hybrid RNN and Correlation-Based Feature Optimization

Journal

Journal NameA Composite Approach of Intrusion Detection Systems: Hybrid RNN and Correlation-Based Feature Optimization

Title of PaperA Composite Approach of Intrusion Detection Systems: Hybrid RNN and Correlation-Based Feature Optimization

PublisherElectronics MDPI

Volume Number11

Page Number1-25

Published YearOctober 2022

Indexed INScopus, Web of Science

Big Data Applications in Transportation Systems Using the Internet of Things

Book Chapter

Book NameHandbook of Research for Big Data: Concepts and Techniques

PublisherCRC Press

Author NameSunil Gautam

Page Number91

Chapter TitleBig Data Applications in Transportation Systems Using the Internet of Things

Published YearFebruary 2022

Indexed INScopus

Abstract

The internet of things (IoT) is progressing towards the internet of everything (IoE). In the near future, all smart physical entities are likely to be connected so that they can communicate with each other. These communicating smart physical entities will generate huge data generated with high speed. The data generated by such devices may be called Big Data because it has a huge volume, is generated very fast, and has variety. The transmission and processing of such data is a gigantic task [1–4]. Analyzing such kind of data is gaining popularity among researchers for innovative application design and to design/identify future models of IoT. Many commercially viable IoT applications are being designed by researchers in the fields of Transport, Health care, Health tracking, Environment, Disaster management, Smart homes, Smart cities, Pharmaceutical products, Food sustainability, Energy, Military, etc.,[5–7].

A stealthy evasive information invasion using covert channel in mobile phones

Conference

Title of PaperA stealthy evasive information invasion using covert channel in mobile phones

Proceeding Name International Conference on Artificial Intelligence and Machine Vision (AIMV)

PublisherIEEE

Author NameSunil Gautam

Page Number1-5

Published YearSeptember 2021

Indexed INScopus

Abstract

The proliferation of mobile devices and widening technological advancements have led the world to potential repercussions of insecurities. This brings in the most intrinsic requirement of security in mobile devices that may have crucial information like contacts, messages or payment passwords. However, the rapid advancements and technological vulnerabilities have created a space for these threats to get in unnoticed from detection mechanisms like reverse engineering. Covert channels that either disrupt the information flow or thwart the flow in order to sidestep the detection mechanisms and leak sensitive information have been discovered in mobile devices also. The paper depicts an attack PCEII utilizing one of such covert channels and evasive mechanism to bypass the detection mechanisms like reverse engineering, data and control flow tracking a malware detection tools. The current research discusses the malicious approaches of such covert channels based evasive attacks, their operation, research gap and its solution in detail. Also, it open up an area for defense against covert channels to be incorporated in state-of-art tools.

Applications of Big Data and Internet of Things in Power System

Book Chapter

Book NameArchitectural Wireless Networks Solutions and Security Issues

PublisherSpringer, Singapore

Author NameSunil Gautam

Page Number209-225

Chapter TitleApplications of Big Data and Internet of Things in Power System

Published YearApril 2021

Indexed INScopus

Abstract

In recent years, Internet of things (IoT) technology is the fastest growing technology which connects physical device or sensors to Internet. IoT devices collect the information from object’s then store or transfer information over the Internet without help of any manual involvement and with the help of embedded technology. The big data play a vital role in IoT because it is a process of a huge amount of information on real-time basis. This chapter highlights the use of big data and IoT for the power systems. IoT can be used in various areas of power system such as metering, transformer monitoring, prediction of demand and planning for future consumption. The main objective of this chapter to make a clear understanding of the use of big data and IoT in the power system and how it will improve customer service and social welfare.

A Novel Multilevel Classifier Hybrid Model for Intrusion Detection Using Machine Learning

Book Chapter

Book NameNature-Inspired Computing for Smart Application Design

PublisherSpringer, Singapore

Author NameSunil Gautam

Page Number249-266

Chapter TitleA Novel Multilevel Classifier Hybrid Model for Intrusion Detection Using Machine Learning

Published YearMarch 2021

Indexed INScopus

Abstract

Due to widespread of Internet, the malicious activities are increasing that affect a single system as well as a network of systems (computer networks). Therefore, a system required for of an effective intrusion detection system (IDS) that can protect the user’s information, which is a great demanding task. In this research work, develop a novel multilevel classifier hybrid model of IDS using machine learning technique that combines together the misuse and anomaly detection approaches using the supervised and unsupervised learning approaches. This model contains two phases: In first phase, the random tree classifier classifies the dataset into known attacks using the misuse detection approach, and second phase classifies the novel attacks using the anomaly detection approach. It uses the instance-based learning method is used the k-nearest neighbor algorithm separately in phase 2. The proposed model provides a significant improvement of in predication accuracy, reduces false positive rate, and reduces the training time. Hence, it is confirmed that proposed model is a novel combination of classifiers that can be trained on a dataset in parallel, thus saves the training time and makes the system processing faster. Using simulation results, we describe that the developed model provides more significant results than the previous IDS models.

Application of Big Data and Machine Learning

Book Chapter

Book NameMachine Learning and Big Data: Concepts, Algorithms, Tools and Applications

PublisherJohn Wiley & Sons, Inc.

Author NameSunil Gautam

Page Number305-333

Chapter TitleApplication of Big Data and Machine Learning

Published YearJuly 2020

Indexed INScopus

Abstract

Today, Machine Learning (ML) is apart of our daily life. It has major advancements in its applications and research as well. ML is the study in which a machine is trained with past data and examples and uses algorithms to build the logic. Important ML applications are speech recognition, computer vision, bio-surveillance, robot or automation control, empirical science experiments, DNA classification, intrusion detection, astronomical data analysis, information security, transportation, etc. According to a recent survey, computer-generated insurance advice is helpful to customers. Using ML, determination of cover for a certain customer can be predicted. Choice of the mode of transportation can also be benefited from ML. ML predicts the mode of transportation for an individual to make their travel better. Travel modes may include private car, public transport (bus or train), or soft mode (walking or cycling). The very first step in applying ML is to define a problem. This step includes three important processes to be considered, namely, problem identification, the motivation behind problem solving, and the solution itself. This chapter presents the evolution of ML along with the purpose it serves. It also focuses on the ideas of concept learning along with the methods and algorithms therein.

Intrusion detection in RFID system using computational intelligence approach for underground mines

Journal

Journal NameInternational Journal of Communication Systems

Title of PaperIntrusion detection in RFID system using computational intelligence approach for underground mines

PublisherWilley

Volume Number31

Page Numbere3532

Published YearMay 2018

Indexed INScopus, Web of Science

Abstract

The radio frequency identification technology (RFID) is commonly used for object tracking and monitoring. In this paper, we discuss a model for intrusion detection system based on RFID to identify the abnormal behavior of underground mines' toxic gases. This model consists of various types of sensor nodes that are integrated with RFID tag, which are deployed in the underground mines by using Zigbee protocol. It consists of coordinators, routers, and sensor nodes, according to different capabilities and the probabilities of intrusive activities that occur in underground mines. It can detect the real-time abnormal behavior of the toxic gases viz. methane, carbon monoxide, carbon dioxide, hydrogen sulfide, and nitrogen dioxide gases, using artificial neural network middleware techniques. It increases the detection accuracy and reduces the false alarm rate, using multilayer perceptron, radial basis function network, and probabilistic and general regression neural network (PNN/GRNN) techniques. The simulations are performed on the toxic gas dataset, which has been generated in a real-time scenario by using different gas sensors. The real-time dataset contains intrusive and nonintrusive values of methane, carbon monoxide, carbon dioxide, hydrogen sulfide, and nitrogen dioxide gases. Experimentally, the PNN/GRNN provides higher detection accuracy as 90.153% for carbon monoxide, 86.713% for carbon dioxide, 93.752% for hydrogen sulfide, and 75.472% for nitrogen dioxide. The PNN/GRNN also provides low false alarm rate as 9.85% for carbon monoxide, 13.29% for carbon dioxide, 6.24% for hydrogen sulfide, and 24.53% for nitrogen dioxide compared with the multilayer perceptron and radial basis function networks.

Comparative analysis of classification techniques in network based intrusion detection systems

Conference

Title of PaperComparative analysis of classification techniques in network based intrusion detection systems

Proceeding NameProceedings of the First International Conference on Intelligent Computing and Communication

PublisherSpringer, Singapore

Author NameSunil Gautam

Page Number591-601

Published YearNovember 2016

Indexed INScopus

Abstract

An Intrusion Detection System (IDS) monitors the system events and examines the log files in order to detect the security problem. In this paper, we analyze the classification algorithms, especially Entropy based classification, Naïve classifier, and J48 using KDD-CUP’99 dataset to detect the different types of attacks. The KDD-Cup’99 dataset is a standard dataset for analysing these type of classification techniques. In KDD-CUP’99 dataset, each instance corresponds to either attack or normal connection. The KDD-Cup’99 dataset contains mainly four types of attack, namely, DOS, U2R, R2L, Probe and these four types of attacks also have subcategories attacks. In this paper, we carry out simulations on the KDD-Cup’99 dataset for all four types of attacks and their subcategories. The back, land, Neptune, pod, smurf, teardrop belong to DoS; the rootkit, Perl, load module, buffer-overflow belong to U2R; the FTP-write, spy, phf, guess-passwd, imap, warezclient, warezmaster, multihop belong to R2L, and the Ipsweep, nmap, portsweep, satan belong to the probe. The simulation results show that the entropy based classification algorithm gives high detection rate and accuracy for normal instances over the J48 and Naïve Bayes classifiers.

Computational neural network regression model for Host based Intrusion Detection System

Journal

Journal NamePerspectives in Science

Title of PaperComputational neural network regression model for Host based Intrusion Detection System

PublisherElsevier

Volume Number8

Page Number93-95

Published YearJanuary 2016

Indexed INScopus

Abstract

The current scenario of information gathering and storing in secure system is a challenging task due to increasing cyber-attacks. There exists computational neural network techniques designed for intrusion detection system, which provide security to single machine and entire network's machine. In this paper, we have used two types of computational neural network models, namely, Generalized Regression Neural Network (GRNN) model and Multilayer Perceptron Neural Network (MPNN) model for Host based Intrusion Detection System using log files that are generated by a single personal computer. The simulation results show correctly classified percentage of normal and abnormal (intrusion) class using confusion matrix. On the basis of results and discussion, we found that the Host based Intrusion Systems Model (HISM) significantly improved the detection accuracy while retaining minimum false alarm rate.

Host-Based Intrusion Detection Using Statistical Approaches

Conference

Title of PaperHost-Based Intrusion Detection Using Statistical Approaches

Proceeding NameProceedings of the 4th International Conference on Frontiers in Intelligent Computing: Theory and Applications (FICTA) 2015

PublisherSpringer, New Delhi

Author NameSunil Gautam

Page Number481-493

Published YearOctober 2015

Indexed INScopus

Abstract

An intrusion detection system (IDS) detects the malicious activities, running in the system that may be a single system or a networked system. Furthermore, the intrusion-based systems monitor the data in a system against the suspicious activities and also secure the entire network. Detection of malicious attacks with keeping acceptability of low false alarm rate is a challenging task in intrusion detection. In this paper, we analyze the three statistical approaches namely principal component analysis (PCA), linear discriminant analysis (LDA), and naive Bayes classifier (NBC), employed in host-based intrusion detection systems (HIDS) and we detect the accuracy rate using these approaches.

Anomaly detection system using entropy based technique

Conference

Title of PaperAnomaly detection system using entropy based technique

Proceeding Name1st International Conference on Next Generation Computing Technologies (NGCT)

Author NameIEEE

Page Number738-743

Published YearApril 2015

Indexed INScopus

Abstract

An Intrusion detection system (IDS) is a module of software and/or hardware that monitors the activities occurring in a computer system or network system. The IDSs use various algorithms for detecting malicious activities. One of them is feature selection algorithm that depends on dimensionality reduction of the datasets. In this paper, we propose a novel feature selection algorithm based on information gain (entropy). We use the Knowledge Discovery and Data Mining cup dataset'99 for detecting the attacks and to classify them in four categories as well. Our algorithm provides better detection rate than the existing Fast Feature Reduction in Intrusion Detection Datasets (FFRIDD) and Multi-Level Dimensionality Reduction Methods (MLDRM).

Multivariate linear regression model for host based intrusion detection

Conference

Title of PaperMultivariate linear regression model for host based intrusion detection

Proceeding NameComputational Intelligence in Data Mining

PublisherSpringer, New Delhi

Author NameSunil Gautam

Page Number361-371

Published YearJanuary 2015

Indexed INScopus

Abstract

Computer security is an important issue for an organization due to increasing cyber-attacks. There exist some intelligent techniques for designing intrusion detection systems which can protect the computer and network systems. In this paper, we discuss multivariate linear regression model (MLRM) to develop an anomaly detection system for outlier detection in hardware profiles. We perform experiments on performance logfiles taken from a personal computer. Simulation results show that our model discovers intrusion effectively and efficiently.

A pipelined architecture for acreage estimation using deep leaning and spectral image

Journal

Journal NameInternational Journal of Information Technology

Title of PaperA pipelined architecture for acreage estimation using deep leaning and spectral image

Volume Number15

Page Number4427-4435

Published YearDecember 2023

ISSN/ISBN No2511-2112

Indexed INScopus, Web of Science

Abstract

Deep learning is used to solve several image-related challenges due to its intrinsic feature learning property. They can learn spectral and spatial information from images obtained from special sensing devices. This information can be further used to compute acreage which is important while addressing bigger challenges like yield estimation. We propose CNN-based deep learning pipelined architecture for acreage estimation. We used spectral information to identify mixed classes spread across small or large areas and spatial information for acreage estimation. The designed architecture was tested over standard data. Small patches were used to train the model to reduce computation complexity. Standard statistical techniques were used to access the results. Additional Overall Pre-diction Accuracy (OPA) and Average Class-wise Prediction Accuracy(ACPA) were designed along with standard metrics for analysis. Acreage was calculated using spatial resolution. It was further observed that 80% of all classes had greater than 98% acreage estimation accuracy.

Predictive Maintenance System for Rotating Machinery Onboard Ships for Detecting Performance Degradation

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperPredictive Maintenance System for Rotating Machinery Onboard Ships for Detecting Performance Degradation

Volume Number24

Page Number1231-1240

Published YearNovember 2023

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science

Abstract

Maintenance of rotating machinery is crucial for extending the lifespan and increasing the reliability of equipment onboard ships. Presently, breakdown and preventive methodologies are used for the maintenance of equipment. Further, dataloggers collect critical machinery parameters, and parameter data is used for real-time parameter monitoring. The availability of such extensive monitoring data has also led to the adoption predictive maintenance methodologies in the industry, wherein machine learning-based analysis of recorded data is used to predict impending defects and prompt required maintenance. In this paper, we propose a predictive maintenance system that records data through a network of sensors installed over multiple electrical motor pump sets onboard the ship and uses statistical analysis to detect equipment degradation. Our system has been deployed onboard a ship to undertake real-time predictive maintenance of electrical motor pump sets used in firemain, AC plants, stabilizers, steering pumps and other auxiliary engine room machinery.

Earth Observation Data Analytics Using Machine and Deep Learning: Modern tools, applications and challenges

Book

PublisherIET

Published YearJune 2023

ISSN/ISBN No 978-1-83953-617-5

Indexed INScopus, Web of Science

Parameter optimization for surface mounter using a self-alignment prediction model

Journal

Journal NameSoldering & Surface Mount Technology

Title of Paper Parameter optimization for surface mounter using a self-alignment prediction model

PublisherEmerald Publishing Limited

Volume Number35

Page Number78-85

Published YearFebruary 2023

Indexed INScopus, Web of Science

A comprehensive analysis towards exploring the promises of AI-related approaches in autism research

Journal

Journal NameComputers in Biology and Medicine

Title of PaperA comprehensive analysis towards exploring the promises of AI-related approaches in autism research

PublisherElsevier

Page Number107801

Published YearJanuary 2023

ISSN/ISBN No 1879-0534 Copyright © 2024 Elsevier Ltd. All

Indexed INScopus, Web of Science, Indian citation Index

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that presents challenges in communication, social interaction, repetitive behaviour, and limited interests. Detecting ASD at an early stage is crucial for timely interventions and an improved quality of life. In recent times, Artificial Intelligence (AI) has been increasingly used in ASD research. The rise in ASD diagnoses is due to the growing number of ASD cases and the recognition of the importance of early detection, which leads to better symptom management. This study explores the potential of AI in identifying early indicators of autism, aligning with the United Nations Sustainable Development Goals (SDGs) of Good Health and Well-being (Goal 3) and Peace, Justice, and Strong Institutions (Goal 16). The paper aims to provide a comprehensive overview of the current state-of-the-art AI-based autism classification by reviewing recent publications from the last decade. It covers various modalities such as Eye gaze, Facial Expression, Motor skill, MRI/fMRI, and EEG, and multi-modal approaches primarily grouped into behavioural and biological markers. The paper presents a timeline spanning from the history of ASD to recent developments in the field of AI. Additionally, the paper provides a category-wise detailed analysis of the AI-based application in ASD with a diagrammatic summarization to convey a holistic summary of different modalities. It also reports on the successes and challenges of applying AI for ASD detection while providing publicly available datasets. The paper paves the way for future scope and directions, providing a complete and systematic overview for researchers in the field of ASD.

Machine Learning-Based Model for Effective Resource Provisioning in Cloud

Conference

Title of PaperMachine Learning-Based Model for Effective Resource Provisioning in Cloud

Proceeding NameFuturistic Trends in Networks and Computing Technologies: Select Proceedings of Fourth International Conference on FTNCT 2021

PublisherSpringer Nature-Nirma University

Author NamePayal Saluja, Swati Jain, Madhuri Bhavsar

OrganizationNirma University

Page Number935-950

Published YearNovember 2022

Indexed INScopus

Parameter optimization for surface mounter using a self-alignment prediction model

Journal

Journal NameSoldering & Surface Mount Technology

Title of PaperParameter optimization for surface mounter using a self-alignment prediction model

PublisherEmerald Publishing Limited

Volume Number35

Published YearJuly 2022

ISSN/ISBN No0954-0911

Indexed INScopus, Web of Science

Abstract

The purpose of this paper is to develop a machine learning model that predicts the component self-alignment offsets along the length and width of the component and in the angular direction. To find the best performing model, various algorithms like random forest regressor (RFR), support vector regressor (SVR), neural networks (NN), gradient boost (GB) and K-nearest neighbors (KNN) were performed and analyzed. The models were implemented using input features, which can be categorized as solder paste volume, paste-pad offset, component-pad offset, angular offset and orientation.

Deep sequence to sequence learning-based prediction of major disruptions in ADITYA tokamak

Journal

Journal NamePlasma Physics and Controlled Fusion

Title of PaperDeep sequence to sequence learning-based prediction of major disruptions in ADITYA tokamak

PublisherIOP Publishing

Volume Number63

Page Number11

Published YearSeptember 2021

Indexed INScopus, Web of Science

Abstract

Plasma Physics and Controlled Fusion PAPER Deep sequence to sequence learning-based prediction of major disruptions in ADITYA tokamak Aman Agarwal4,1, Aditya Mishra1, Priyanka Sharma1, Swati Jain1, Raju Daniel2,3, Sutapa Ranjan2, Ranjana Manchanda2, Joydeep Ghosh2,3, Rakesh Tanna2 and ADITYA Team2 Published 22 September 2021 • © 2021 IOP Publishing Ltd Plasma Physics and Controlled Fusion, Volume 63, Number 11 Citation Aman Agarwal et al 2021 Plasma Phys. Control. Fusion 63 115004 References 235 Total downloads 33 total citations on Dimensions.Article has an altmetric score of 1 Turn on MathJax Get permission to re-use this article Share this article Share this content via email Share on Facebook (opens new window) Share on Twitter (opens new window) Share on Mendeley (opens new window) Article information Abstract Major disruptions in tokamak plasmas need to be identified well before their occurrence and appropriately mitigated. Otherwise, it may dump the heat and electromagnetic load to the vessel and its surrounding plasma-facing components. A predictor system based on precursor diagnostics may help in forecasting the disruptive events in tokamak plasma and raise the alert beforehand to take necessary actions to prevent the major damages inside the vacuum vessel. This paper describes a predictor system built with a few selected diagnostic signals from the ADITYA tokamak and trained on a time-sequence long short-term memory network to predict the occurrence of disruption to 7–20 ms in advance with an accuracy of 89% on the testing set of 36 disruptive and 6 non-disruptive shots. This real-time network can infer to one time-step results under 170 µs on an Intel Xeon processor running python, suggesting minimal computation cost and best suited for the real-time plasma control applications.

A deep learning based approach for trajectory estimation using geographically clustered data

Journal

Journal NameSN Applied Sciences

Title of PaperA deep learning based approach for trajectory estimation using geographically clustered data

PublisherSpringer International Publishing

Volume Number3

Page Number1-17

Published YearJune 2021

Indexed INScopus

Abstract

This study presents a novel approach to predict a complete source to destination trajectory of a vehicle using a partial trajectory query. The proposed architecture is scalable to extremely large-scale data with respect to the dense road network. A deep learning model Long Short Term Memory (LSTM) has been used for analyzing the temporal data and predicting the complete trajectory. To handle a large amount of data, clustering of similar trajectory data is used that helps in reducing the search space. The clusters based on geographical locations and temporal values are used for training different LSTM models. The proposed approach is compared with the other published work on the parameters as Average distance error and one step prediction accuracy The one-step prediction accuracy is as good as 81% and Distance error are .33 Km. Our proposed approach termed Clustered LSTM is outperforming in both the parameters when compared with other reported results. The proposed solution is a clustering-based predictive model that effectively contributes to accurately handle the large scale data. The outcome of this study leads to improvise the navigation systems, route prediction, traffic management, and location-based recommendation systems.

Blockchain Based Framework for Document Authentication and Management of Daily Business Records

Book Chapter

Book NameBlockchain for 5G-Enabled IoT

PublisherSpringer-Cham

Author NamePrakrut Chauhan, Jai Prakash Verma, Swati Jain, Rohit Rai

Page Number497-517

Chapter TitleBlockchain Based Framework for Document Authentication and Management of Daily Business Records

Published YearJanuary 2021

ISSN/ISBN No978-3-030-67490-8

Indexed INScopus

Abstract

With the rise of digitization, documents are being created, modified, and shared digitally. Unlike hard copies, it is difficult to ascertain the authenticity of these digital documents. Thus, there is a need to authenticate and verify digital documents in an efficient manner. In this chapter, a decentralized application has been proposed, which uses a smart contract to facilitate the authentication and verification of documents by leveraging the blockchain technology. In contrast to the traditional way of storing the entire input digital document, this approach creates a unique fingerprint of every input document by using a cryptographic hash function. This fingerprint is stored on the blockchain network to verify the document in future. This blockchain based solution can be used by organizations to authenticate the documents that they generate and allow other entities to verify them.

Prediction of Mental Illness in Heart Disease Patients: Association of Comorbidities, Dietary Supplements, and Antibiotics as Risk Factors

Journal

Journal NameJournal of personalized medicine

Title of PaperPrediction of Mental Illness in Heart Disease Patients: Association of Comorbidities, Dietary Supplements, and Antibiotics as Risk Factors

PublisherMDPI

Volume Number10

Page Number214

Published YearNovember 2020

Indexed INScopus

Abstract

Comorbidities, dietary supplement use, and prescription drug use may negatively (or positively) affect mental health in cardiovascular patients. Although the significance of mental illnesses, such as depression, anxiety, and schizophrenia, on cardiovascular disease is well documented, mental illnesses resulting from heart disease are not well studied. In this paper, we introduce the risk factors of mental illnesses as an exploratory study and develop a prediction framework for mental illness that uses comorbidities, dietary supplements, and drug usage in heart disease patients. Particularly, the data used in this study consist of the records of 68,647 patients with heart disease, including the patient’s mental illness information and the patient’s intake of dietary supplements, antibiotics, and comorbidities. Patients in age groups <61, gender differences, and drug intakes, such as Azithromycin, Clarithromycin, Vitamin B6, and Coenzyme Q10, were associated with mental illness. For predictive modeling, we consider applying various state-of-the-art machine learning techniques with tuned parameters and finally obtain the following: Depression: 78.01% accuracy, 79.13% sensitivity, 72.65% specificity, and 86.26% Area Under the Curve (AUC). Anxiety: 82.93% accuracy, 82.86% sensitivity, 83.35% specificity, and 88.45% AUC. Schizophrenia: 87.59% accuracy, 87.70% sensitivity, 85.14% specificity, and 92.73% AUC. Disease: 86.63% accuracy, 95.50% sensitivity, 77.76% specificity, and 91.59% AUC. From the results, we conclude that using heart disease information, comorbidities, dietary supplement use, and antibiotics enables us to accurately predict …

Deep Neural Network based classification of tumorous and non-tumorous Medical Images

Book Chapter

Book NameSpringer Smart Innovation, Systems and Technologies

Chapter TitleDeep Neural Network based classification of tumorous and non-tumorous Medical Images

Published YearJanuary

Indexed INScopus

Deep Q-Learning for Navigation of Robotic Arm for Tokamak Inspection

Journal

Journal NameAlgorithms and Architectures for Parallel Processing

Title of PaperDeep Q-Learning for Navigation of Robotic Arm for Tokamak Inspection

PublisherSpringer

Volume Number11337

Page Number10

Published YearDecember 2018

ISSN/ISBN No978-3-030-05063-4

Indexed INOthers

Abstract

Computerized human-machine interfaces are used to control the manipulators and robots for inspection and maintenance activities in Tokamak. The activities embrace routine and critical activities such as tile inspection, dust cleaning, equipment handling and replacement tasks. Camera(s) is deployed on the robotic arm which moves inside the chamber to accomplish the inspection task. For navigating t

A Proposed Method for Disruption Classification in Tokamak Using Convolutional Neural Network

Book Chapter

Book NameTowards Extensible and Adaptable Methods in Computing

Chapter TitleA Proposed Method for Disruption Classification in Tokamak Using Convolutional Neural Network

Published YearJanuary 2018

Abstract

Thermonuclear fusion is one of the alternative sources of energy. Fusion reactors use a device called tokamak. Classification of favorable and non-favorable discharges in a tokamak is very important for plasma operation point of view. Non-favorable discharges are mainly disruptive in nature which causes certain losses of confinement that take place abruptly and affect the integrity of tokamak. Dur

Weighted Fusion of LBP and CCH Features for Effective Content Based Image Retrieval

Conference

Title of PaperWeighted Fusion of LBP and CCH Features for Effective Content Based Image Retrieval

Proceeding NameInternational Conference on Signal Processing and Communications (SPCOM'16), IISC, Bangalore

OrganizationIISC, Bangalore

Published YearJanuary 2018

Deep learning feature map for content based image retrieval system for remote sensing application

Journal

Journal NameInternational Journal of Image Mining

Title of PaperDeep learning feature map for content based image retrieval system for remote sensing application

PublisherInderscience

Volume Number2

Page Number11

Published YearSeptember 2016

Abstract

This paper proposes a model for content based image retrieval system (CBIR), in which handcrafted feature set is replaced with feature set learnt from deep learning, convolutional neural network (CNN) for image retrieval. Feature map obtained from CNN is of high dimension, which makes the matching process expensive in terms of time and computation. Hence to recapitulate information in smaller dime

Parallel Approach To Expedite Morphological Feature Extraction Of Remote Sensing Images for CBIR System

Conference

Title of PaperParallel Approach To Expedite Morphological Feature Extraction Of Remote Sensing Images for CBIR System

Proceeding Name35th IEEE International Geoscience and Remote Sensing Symposium, Quebec Canada

PublisherIEEE

OrganizationQuebec City, QC, Canada

Year , VenueNovember 2014 , Quebec City, QC, Canada

Page Number4

ISSN/ISBN No14716409

Abstract

In this paper, we have proposed a parallel approach to the morphological feature extraction process and demonstrated a good computational speedup. Remote sensing images have a typical property of incrementing constantly and each image being very large. Since the images are acquired constantly and hence added into the database regularly in good numbers, hence there is a need to make the feature ext

CNN-FEBAC: A framework for attention measurement of autistic individuals

Journal

Journal NameBiomedical Signal Processing and Control

Title of PaperCNN-FEBAC: A framework for attention measurement of autistic individuals

PublisherElsevier

Volume Number88

Page Number105018

Published YearJanuary 2014

ISSN/ISBN No1746-8108

Indexed INScopus, Web of Science

Abstract

Electroencephalogram (EEG) signals are a cost-effective and efficient method to measure and analyse neurological data and brain-related ailments. Autism Spectrum Disorder (ASD) is a globally prevalent neurological disorder that is of significant concern to the medical research community regarding its diagnosis and treatment. Artificial Intelligence (AI) algorithms utilized to study EEG signals of autistic patients have shown promising results to make progress in this domain. In this study, the authors have used the BCIAUT-P300 dataset for attention measurement and analysis of EEG signals of autistic patients. The dataset comprises the EEG signal data of ASD patients when they are exposed to external stimuli in a controlled environment. The authors propose a Convolutional Neural Network based Feature Extractor for BCI Attention Classification (CNN-FEBAC) framework to achieve the research objective of predicting the response of ASD patients by studying their EEG signal recordings. The CNN-FEBAC framework consists of a feature extractor architecture followed by a shallow classifier to predict the patient’s response to the stimuli. The proposed model was evaluated using performance metrics such as — confusion matrix, accuracy and F1 scores. The best accuracy achieved by the proposed model was 91%. The authors have explored and described the limitations of previously established methods and highlighted the performance improvements achieved with the proposed CNN-FEBAC framework. The authors further highlight the challenges encountered in the study and suggest the scope for improvement.

Computation Performance Gain in Key Feature Extraction for CBIR system for Remote Sensing Images

Conference

Title of PaperComputation Performance Gain in Key Feature Extraction for CBIR system for Remote Sensing Images

Proceeding NameEighth International Conference on Image and Signal Processing (ICISP 2014), Elsevier

Published YearJanuary 2014

ISSN/ISBN No9789351072522

Exploring a new direction in colour and texture based satellite image search and retrieval system

Conference

Title of PaperExploring a new direction in colour and texture based satellite image search and retrieval system

Proceeding Name2011 Nirma University International Conference on Engineering

PublisherIEEE

OrganizationNirma University

Year , VenueDecember 2012 , Nirma University, Ahmedabad, Gujarat, India

Page Number5

ISSN/ISBN No2375-1282

Abstract

Content based Image Retrieval systems (CBIR) have become a reliable tool for many image database applications. Today, the need for reliable, automated satellite image classification and browsing systems is more than ever before. Everyday there is a massive amount of remotely sensed data being collected and sent by terrestrial satellites for analysis. The use of automated tools for this analysis ha

Detection of Moving Object using Continuous Background Estimation Based on Probability of Pixel Intensity Occurrences

Journal

Journal NameInternational Journal of Computer Science and Telecommunications

Title of PaperDetection of Moving Object using Continuous Background Estimation Based on Probability of Pixel Intensity Occurrences

PublisherIJCST

Volume Number3

Page Number5

Published YearMay 2012

Abstract

Video object segmentation is an important part of real time surveillance system. For any video segmentation algorithm to be suitable in real time, must require less computational load. This paper addresses the problem of maintaining the background with the changes in the scene. The algorithm proposed in this paper enables to update the background image timely without compromising the time taken fo

Performance Measure of Image Processing Algorithms on DSP Processor & FPGA Based Coprocessor

Conference

Title of PaperPerformance Measure of Image Processing Algorithms on DSP Processor & FPGA Based Coprocessor

Proceeding Name2010 International Conference on Advances in Communication, Network, and Computing

Published YearOctober 2010

Abstract

As the processing capability of processor increases the computation requirements of application two folds, especially Digital Image Processing algorithms applied on satellite images require tremendous amount of calculations because high resolution images are common in aerial and satellite surveillance. Fourier Transform, Convolution and Correlation are fundamental algorithms required in many image

A sample selection method based on similarity measure and fuzziness for crop classification from hyperspectral data

Journal

Journal NameAdvances in Space Research

Title of PaperA sample selection method based on similarity measure and fuzziness for crop classification from hyperspectral data

PublisherScience Direct

Published YearJune 2022

Indexed INScopus, Web of Science

Band Selection Technique for Crop Classification Using Hyperspectral Data

Journal

Journal NameJournal of the Indian Society of Remote Sensing

Title of PaperBand Selection Technique for Crop Classification Using Hyperspectral Data

PublisherSpringer

Published YearApril 2022

Indexed INScopus, Web of Science

Security and privacy issues in fog computing for healthcare 4.0

Journal

Journal NameFog Computing for Healthcare 4.0 Environment

Title of PaperSecurity and privacy issues in fog computing for healthcare 4.0

PublisherSpringer, Cham

Published YearAugust 2021

Indexed INScopus

Deep learning- based scheme to diagnose Parkinson's disease

Journal

Journal NameExpert Systems

Title of PaperDeep learning- based scheme to diagnose Parkinson's disease

PublisherWiley

Published YearMay 2021

Indexed INScopus, Web of Science

Gujarati language model: Word sense disambiguation using supervised technique

Journal

Journal NameInternational Journal of Recent Technology and Engineering

Title of PaperGujarati language model: Word sense disambiguation using supervised technique

PublisherBlue Eyes Intelligence Engineering & Sciences Publication

Published YearSeptember 2019

Indexed INScopus

Crop Identification and Discrimination Using AVIRIS- NG Hyperspectral Data Based on Deep Learning Techniques

Conference

Title of PaperCrop Identification and Discrimination Using AVIRIS- NG Hyperspectral Data Based on Deep Learning Techniques

Proceeding Name39th IEEE International Geoscience and Remote Sensing Symposium

PublisherIEEE

Published YearJuly 2019

Indexed INScopus

A survey and evaluation of supervised machine learning techniques for spam e-mail filtering

Conference

Title of PaperA survey and evaluation of supervised machine learning techniques for spam e-mail filtering

Proceeding Name IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT)

PublisherIEEE

Author NameCoimbatore, India

Published YearJanuary

ISSN/ISBN No978-1-4799-6084-2

Indexed INScopus

Music Information Retrieval: A Window into the Needs and Challenges

Conference

Title of PaperMusic Information Retrieval: A Window into the Needs and Challenges

Proceeding NameInternational Conference on Emerging Research in Computing, Information, Communication and Applications

PublisherSpringer, Singapore

Published YearNovember 2017

Indexed INScopus

Word Sense Disambiguation for Indian Languages

Conference

Title of PaperWord Sense Disambiguation for Indian Languages

Proceeding NameInternational Conference on Emerging Research in Computing, Information, Communication and Applications

PublisherSpringer, Singapore

Published YearNovember 2017

Indexed INOthers

Google AdWords: A Window into the Google Display Network

Book Chapter

Book Name Lecture Notes in Networks and Systems

PublisherSpringer

Chapter TitleGoogle AdWords: A Window into the Google Display Network

Published YearNovember 2017

ISSN/ISBN No978-981-10-3931-7

Indexed INScopus

MobiCloud: Performance Improvement, Application Models and Security Issues

Book Chapter

Book Name Smart Innovation, Systems and Technologies

PublisherSpringer

Chapter TitleMobiCloud: Performance Improvement, Application Models and Security Issues

Published YearAugust 2017

ISSN/ISBN No978-3-319-63672-6

Indexed INScopus

Towards the Next Generation of Web of Things: A Survey on Semantic Web of Things’ Framework

Book Chapter

Book Name Smart Innovation, Systems and Technologies

PublisherSpringer

Page Number31-39

Chapter TitleTowards the Next Generation of Web of Things: A Survey on Semantic Web of Things’ Framework

Published YearJuly 2016

ISSN/ISBN No978-3-319-30932-3

Indexed INScopus

Text Categorization and State-of-Art Support Vector Machine

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperText Categorization and State-of-Art Support Vector Machine

PublisherCSI journals

Published YearMarch 2016

Indexed INOthers

A Study of Working of Ad Auctioning by Google AdWords

Book Chapter

Book Name Advances in Intelligent Systems and Computing

PublisherSpringer

Page Number471-480

Chapter TitleA Study of Working of Ad Auctioning by Google AdWords

Published YearFebruary 2016

ISSN/ISBN No978-981-10-0133-8

Indexed INScopus

Movie Related Information Retrieval Using Ontology Based Semantic Search

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperMovie Related Information Retrieval Using Ontology Based Semantic Search

PublisherCSI journals

Published YearSeptember 2014

Indexed INOthers

Video Search Engine Tool

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperVideo Search Engine Tool

PublisherCSI journals

Published YearSeptember 2014

Indexed INOthers

Study and Analysis of Gene Expression Clustering with Gaussian Mixed Effects Models and Smoothing

Journal

Journal NameInternational Journal of Computer Science and Network Security

Title of PaperStudy and Analysis of Gene Expression Clustering with Gaussian Mixed Effects Models and Smoothing

Volume Number20

Published YearMay 2020

ISSN/ISBN No1738-7906

Indexed INWeb of Science

Abstract

A large number of longitudinal studies measuring gene expression aim to stratify the genes according to their differential temporal behaviors. Genes with similar expression patterns may reflect functional responses of biological relevance. However, these measurements come with intrinsic noise which makes their time series clustering a difficult task. Here, we have shown how to cluster such data with mixed effects models with nonparametric smoothing spline fitting and is able to robustly stratify genes by their complex time series patterns. The article has, besides the main clustering methods, a set of functionalities assisting the user to visualize and assess the clustering results, and to choose the optimal clustering solution. The first part is about the introduction to gene expression, how time series can be applied and how the clustering is important to gene expression. The Gaussian mixed effect model is also explain. The second part is about the related work already done with some references. The third part is about our own process and workflow with diagram. How the clustering is applied and diagrams of different cluster sets. The fourth part is about results and discussion, how the silhouette analysis is important and using 3 clusters and 4 clusters how the data sets look like. The fifth part is shown with applications of clustering effects, how the yeast data sets can be divided into clusters etc. The sixth part shows the methodology of mixed Gaussian effects and smoothing splines. The last part is about conclusion and references.

Learning an unsupervised - clustering algorithm Monte Carlo over Consensus Clustering for Genomic Data for Tumour Identification

Journal

Journal NameInternational Journal of Recent Technology and Engineering

Title of PaperLearning an unsupervised - clustering algorithm Monte Carlo over Consensus Clustering for Genomic Data for Tumour Identification

Volume NumberX

Published YearJuly 2019

ISSN/ISBN No2277-3878

Indexed INScopus

Abstract

Clustering cluster International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-8 Issue-4, November 2019 Learning an un-supervised – Clustering algorithm Monte Carlo over Consensus Clustering for Genomic Data for Tumor Identification involves the grouping of similar objects into a set known as . Objects in one different when compared to objects grouped under another cluster . Gene expressionis the process by which information from a gene is used in the synthesis of a Functional Gene Products. Subgroup classification is a basic task in high-throughput genomic data analysis, especially for gene expression and methylation data analysis. Mostly, unsupervised clustering methods are applied to predict new subgroups or test the consistency with known annotations. To get a stable classification of subgroups, consensus clustering is always performed. It clusters repeatedly with a randomly sampled subset of data and summarizes the robustness of the clustering. When faced with significant uncertainty in the process of making a forecast or estimation, the Monte Carlo Simulation might prove to be a better solution. Monte Carlo3C is a consensus clustering algorithm that uses a Monte Carlo simulation to eliminate overfitting and can reject the null hypothesis when only one cluster is there

Identifying subtypes of cancer using Genomic Data by Applying Data Mining Techniques

Journal

Journal NameInternational Journal of Natural Computing Research

Title of PaperIdentifying subtypes of cancer using Genomic Data by Applying Data Mining Techniques

PublisherIGI-Global

Volume Number8

Published YearJanuary 2019

ISSN/ISBN No1947-928X

Indexed INIndian citation Index

Abstract

Cancer is the disorder of body chemicals. In a wide range of disease, a portion of the body's cells start to separate ceaselessly and spread into encompassing tissues. Ordinarily human cells develop and partition to frame another cell as the body needs them. When cells grow abnormally and cells are added unnecessarily. That cells produced tumor, tumor in human body is either benign or malignant. Malignant tumors are spread into other part of body while benign tumors are sometimes be quite large. When we remove benign cells, they usually do not grow back while malignant tumor may occur recurrently. Normal cells are dissent from cancer cells that they develop crazy and find yourself intrusive malignancy cells might need the capability to impact the everyday cells, particles and veins that comprehend and feed a tumor a territory called the microenvironment. Malignancy cells will instigate close-by standard cells to form veins that provide tumors with element and supplements, that they need to develop. These veins likewise expel squander things from tumors. Malignant growth is caused by specific changes to qualities, the essential physical units of heritage. Genes are organized in long stands of tightly packed chemical compound named as chromosomes. The main three types of genetic changes may occur in developing cancer cells:

Classification of Blood Cancer and Form Associated Gene Networks Using Gene Expression Profiles

Journal

Journal NameInformation and Communication Technology for Intelligent Systems

Title of PaperClassification of Blood Cancer and Form Associated Gene Networks Using Gene Expression Profiles

PublisherSpringer

Page Number95-106

Published YearApril 2018

ISSN/ISBN No2190-3018

Indexed INScopus

Abstract

Blood cells are produced at bone marrow called the soft, spongy center of bones. Leukemia is a one type of cancer which occurs either at blood or at bone marrow. It can happen when there is a problem with the production of blood cells. It usually affects the leukocytes or white blood cells. Once the blood cancer develops, the body produces huge amount of abnormal blood cells. In most varieties of Leukemia, the abnormal cells are white blood cells and they look completely different from traditional blood cells. In this paper, the categories of Leukemia are briefly justified, the method shows a robust performance applied to patient-based gene expression datasets. In this article, we have taken 60 microarray samples from the patient’s bone marrow and that samples are of four different types: ALL, AML, CLL, and AML with non-leukemia also. The article projected associate algorithmic rule to make clear classifier associated gene networks supported genome-wide expression knowledge. The input for this algorithmic rule is the Expression Set or Expression Matrix of the samples and output provides three completely different categories such as Gene Ranking, Classifier, and gene Network associated to every class.

Design and Experience of Mobile Applications: A Pilot Survey

Journal

Journal NameMathematics, MDPI

Title of PaperDesign and Experience of Mobile Applications: A Pilot Survey

PublisherMultidisciplinary Digital Publishing Institute

Volume Number10

Page Number1-20

Published YearJuly 2022

ISSN/ISBN No2227-7390

Indexed INScopus, Web of Science, Others

Abstract

With the tremendous growth in mobile phones, mobile application development is an important emerging arena. Moreover, various applications fail to serve the purpose of getting the attention of the intended users, which is determined by their User Interface (UI) and User Experience (UX). As a result, developers often find it challenging to meet the users’ expectations. To date, several reviews have been carried out which explored various aspects of design and the experience of mobile applications using UX/UI. However, many of these existing surveys primarily focused on only some of the issues in isolation but did not consider all the major parameters such as visualisation/graphics, context, user behaviour/emotions/control, usability, adaptability/flexibility, language, and feedback. In our pilot survey, we gathered the preferences and perceptions of a heterogeneous group of concerned people and considered all the aforementioned parameters. These preferences would serve as a reference to mobile application developers, giving them useful insights. Our proposed approach would help mobile application developers and designers focus on the particular UI/UX problems of mobile applications as per their relevant context. A comparative analysis of the various UI and UX factors that determine a mobile application interface is presented in this paper

Blockchain-assisted industrial automation beyond 5G networks

Journal

Journal NameComputers & Industrial Engineering

Title of PaperBlockchain-assisted industrial automation beyond 5G networks

PublisherPergamon

Volume Number169

Page Number1-16

Published YearJuly 2022

ISSN/ISBN No0360-8352

Indexed INScopus, ABDC, Others

Abstract

Automation of industrial tasks becomes the necessity of organizations due to high risks and low operational efficiency associated with traditional procedures. The industrial Internet-of-thing (IIoT) has proved it a reality with ubiquitous computing, which interconnects tens of billions of objects, such as devices and machines, for real-time data transfer. However, the rapid increase in the number of connected devices and machines leads to various security issues, such as data modification, sniffing, and many more. Achieving secure and reliable communication between devices becomes challenging as the entire communication takes place over an open channel, i.e., the Internet. Most of the security solutions presented in the literature are centralized and susceptible to security, latency, reliability, and single-point-of-failure issues. Blockchain is a plausible solution to mitigate the aforementioned issues with reduced capital and operating expenditures, whereas the sixth-generation (6G) network makes communication faster and more reliable. Motivated by these facts, this paper presents an exhaustive survey on blockchain-based industrial automation in the 6G environment. Also, a blockchain and 6G-enabled industrial automation architecture for secure and efficient communication among IIoT devices is proposed. This paper also presents a case study on blockchain-based additive manufacturing for designing three-dimensional products to validate the proposed architecture. The performance of the proposed case study is evaluated based on network parameters such as delay, packet loss, scalability, network bandwidth, computation time, and data storage cost. Finally, various research challenges and future directions are suggested in this emerging area.

P2COMM: A Secure and Low-Cost Message Dissemination Scheme for Connected Vehicles

Conference

Title of PaperP2COMM: A Secure and Low-Cost Message Dissemination Scheme for Connected Vehicles

Proceeding NameIEEE INFOCOM 2022-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

PublisherIEEE

Author NameUmesh Bodkhe; Sudeep Tanwar

OrganizationIEEE COMSoc

Year , VenueMay 2022 , New York, NY, USA

Page Number1-6

ISSN/ISBN No978-1-6654-0926-1

Indexed INScopus, Others

Abstract

Internet of Vehicles (IoV) allows the vehicles to disseminate and exchange various messages among nearby vehicles in the network. These messages include road safety, road accidents, location sharing, driver assistance, navigation, collision warning, and toll payment. Moreover, the exchange of these messages is carried out using an insecure channel, which leads to several issues during transmission of these messages, such as reliable data dissemination, dynamic topology, mobility of the vehicles, vehicle user’s privacy, and low-cost authentication mechanism. The existing vehicle-to-anything (V2X) data dissemination techniques have issues like security attacks, high computational-communication cost, and low throughput. Motivated by these, we propose a secure and Low-Cost (V2X) data dissemination scheme known as P 2 COMM for connected vehicles using SHA256 concatenation and XoR operation. We evaluate the proposed scheme in terms of security and vehicle users’ privacy against several security attacks. Then, we carried out an in-depth formal security analysis of the proposed scheme using the AVISPA tool and informal security analysis along with security proofs. The performance of the proposed scheme is better in comparison to existing state-of-the-art schemes in terms of security, communication overhead, computation cost, and energy cost

Blockchain-Based Federated Cloud Environment: Issues and Challenges

Book Chapter

Book NameBlockchain for Information Security and Privacy

PublisherCRC Press

Author NameA Verma, P Bhattacharya, U Bodkhe, M Zuhair, RK Dewangan

Page Number155-176

Chapter TitleBlockchain-Based Federated Cloud Environment: Issues and Challenges

Published YearJanuary 2022

ISSN/ISBN No9781003129486

Indexed INScopus, Others

Abstract

Over the past decade, service provisioning in federated cloud environments (FCE) through multiple cloud service providers (CSP) is distributed among multi-cloud users (CU). In such ecosystems, multiple broker entities facilitate seamless performance and delivery of cloud services among CU and CSP in FCE. However, due to the exchange of information through public heterogeneous channels, the service transactions among cloud stakeholders are bounded by security issues such as privacy, the authenticity of stakeholders, chronology among transactions, and responsive availability of CSP. Thus, in such peer decentralized ecosystems, the blockchain (BC) framework is applicable to solve the aforementioned issues. BC also automates the Service level agreement (SLA) contracts between CU and CSP through smart contract (SC) execution as logical software codes. In the same direction, the proposed survey addresses the gaps in earlier multi-cloud surveys and discusses a BC-based secure broker provisioning framework for performance and security parameters, concerning associated attack vectors. The proposed survey presents a detailed analysis of different existing solutions and proposes a solution taxonomy for service provisioning in BC-envisioned cloud ecosystems. The survey also identifies the research challenges for industry professionals, academicians, and the research community, to build scalable services for CUs in FCE

Blockchain-enabled secure Internet of Vehicles: A solution taxonomy, architecture, and future directions In Book

Book Chapter

Book NameBlockchain for Information Security and Privacy

PublisherCRC Press

Author NameM Zuhair, P Bhattacharya, A Verma, U Bodkhe

Page Number1-20

Chapter TitleBlockchain-enabled secure Internet of Vehicles: A solution taxonomy, architecture, and future directions In Book

Published YearJanuary 2022

ISSN/ISBN No9781000483093

Indexed INScopus, Others

Abstract

Smart cities provide sustainable transport ecosystems to connect autonomous vehicles through sensors and networking units. Similarly, the Internet of Vehicles (IoV) plays a prominent role in addressing issues of road safety, traffic, and the security of autonomous vehicles. Due to the mission-critical nature of IoV, it requires effective and real-time communication among Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) units. However, due to the open nature of wireless channels, an adversary can form informed attacks on IoV nodes and can cause potential disruptions. Motivated by the aforementioned facts, we present a systematic review of blockchain adoption in IoV to mitigate attacks. A solution taxonomy of potential attack vectors and the attack countermeasures are proposed. A blockchain-based certification case study is presented in the survey to build trust and secure data exchange in the untrusted decentralized IoV ecosystem. Next, we present the research challenges and possible countermeasures, with concluding remarks. The survey intends to bridge the gap in earlier surveys to address issues of blockchain adoption in IoV with a possible adversary model.

Amalgamation of blockchain and sixth‐generation‐envisioned responsive edge orchestration in future cellular vehicle‐to‐anything ecosystems: Opportunities and challenges

Journal

Journal NameTransactions on Emerging Telecommunications Technologies

Title of PaperAmalgamation of blockchain and sixth‐generation‐envisioned responsive edge orchestration in future cellular vehicle‐to‐anything ecosystems: Opportunities and challenges

PublisherWiley

Volume Number1

Page Number1-20

Published YearDecember 2021

ISSN/ISBN No2161-3915

Indexed INScopus, Web of Science, Indian citation Index, Others

Abstract

In modern decentralized cellular-vehicle-to-anything (C-V2X) infrastructures, connected autonomous smart vehicles (CASVs) exchange vehicular information with peer CASVs. To leverage responsive communication, sensors deployed in CASVs communicate through responsive edge computing (REC) infrastructures to support device-to-device- (D2D) based communication. To support low-latency, high-bandwidth, dense mobility, and high availability, researchers worldwide have proposed efficient 5G REC infrastructures to end vehicular users (VU). However, with the growing number of sensor units, intelligent automation, dense sensor integration at massive ultra-low latency is required. To address the issue, the focus has shifted toward sixth-generation (6G)-based intelligent C-V2X orchestration. However, the sensor data is exchanged through open channels, and thus trust and privacy among C-V2X nodes is a prime concern. Thus, blockchain (BC) is a potential solution to allow immutable exchange ledgers among CASV sensor units for secure data exchange. With this motivation, the proposed survey integrates BC and 6G-leveraged REC in C-V2X to address the issues of fifth-generation (5G)-REC through immutable, verified, and chronological timestamped data exchanged through 6G-envisioned terahertz (THz) channels, at high mobility, extremely low latency, and high availability. The survey also presents the open issues and research challenges in the 6G-envisioned BC-enabled REC C-V2X ecosystems via a proposed framework. A case study 6Edge is presented for smart 6G intelligent edge integration with BC-based ledgers. Finally, the concluding remarks and future direction of research are proposed. Thus, the proposed survey forms a guideline for automotive stakeholders, academicians, and researchers to explore the various opportunities of the possible integration in more significant detail.

EVBlocks: A blockchain-based secure energy trading scheme for electric vehicles underlying 5G-V2X ecosystems

Journal

Journal NameWireless Personal Communications,

Title of PaperEVBlocks: A blockchain-based secure energy trading scheme for electric vehicles underlying 5G-V2X ecosystems

PublisherSpringer

Volume Number1

Page Number1-41

Published YearDecember 2021

ISSN/ISBN No0929-6212

Indexed INScopus, Web of Science, Indian citation Index, Others

Abstract

In this paper, the authors propose a secure and trusted energy trading (ET) scheme for electric vehicles (EVs) for vehicle-to-anything (V2X) ecosystems. The scheme, named as EVBlocks, facilitates ET among entities (i.e., EVs, charging stations (CS), and smart grids (SG)) in a secured and trusted manner through a consortium blockchain (CBC) network. The scheme operates in three phases. In the first phase, to allow real-time and resilient network orchestration of V2X nodes, we consider the ET service designed over a fifth-generation (5G) enabled software-defined networking (SDN) environment. Integration of SDN in 5G-V2X ecosystems allows V2X nodes to eliminate intermediaries and handle many requests with a minimum response time. Then, in the second phase, a non-cooperative game is presented that optimizes a cost function and converges to reach at least one Nash equilibrium point. Finally, a consensus algorithm Proof-of-Greed (PoG) is proposed that handles fluctuations in charging/discharging EVs through an event-driven scheduling mechanism. The obtained results are compared against parameters, such as ET time, State-of-Charge (SoC) levels, EV utility, block-convergence time, profits, computation, and communication costs. For example, EVBlocks achieve an average SOC charge of 22.8MW, with a peak at 377.5MW, the average power dissipation of 4.1125 kWH that is lower than 25% against existing conventional and fixed tariff schemes. The scheme converges at stable profit values for 5 EVs through a non-cooperative game. For proposed PoG consensus, the block convergence time for 1000 nodes is 138.96 seconds, at a computation cost of 46.92 milliseconds (ms) and communication cost of 149 bytes. The comparative analysis suggests the proposed scheme is efficient as compared to existing state-of-the-art approaches against compared parameters.

Blockchain-based royalty contract transactions scheme for Industry 4.0 supply-chain management

Journal

Journal NameInformation processing & management

Title of PaperBlockchain-based royalty contract transactions scheme for Industry 4.0 supply-chain management

Volume Number58

Page Number1-14

Published YearJuly 2021

ISSN/ISBN No0306-4573

Indexed INScopus, Web of Science, Indian citation Index, Others

Abstract

Industry 4.0-based oil and gas supply-chain (OaG-SC) industry automates and efficiently executes most of the processes by using cloud computing (CC), artificial intelligence (AI), Internet of things (IoT), and industrial Internet of things (IIoT). However, managing various operations in OaG-SC industries is a challenging task due to the involvement of various stakeholders. It includes landowners, Oil and Gas (OaG) company operators, surveyors, local and national level government bodies, financial institutions, and insurance institutions. During mining, OaG company needs to pay incentives as a royalty to the landowners. In the traditional existing schemes, the process of royalty transaction is performed between the OaG company and landowners as per the contract between them before the start of the actual mining process. These contracts can be manipulated by attackers (insiders or outsiders) for their advantages, creating an unreliable and un-trusted royalty transaction. It may increase disputes between both parties. Hence, a reliable, cost-effective, trusted, secure, and tamper-resistant scheme is required to execute royalty contract transactions in the OaG industry. Motivated from these research gaps, in this paper, we propose a blockchain-based scheme, which securely executes the royalty transactions among various stakeholders in OaG industries. We evaluated the performance of the proposed scheme and the smart contracts’ functionalities and compared it with the existing state-of-the-art schemes using various parameters. The results obtained illustrate the superiority of the proposed scheme compared to the existing schemes in the literature.

Blockchain adoption for trusted medical records in healthcare 4.0 applications: a survey

Book Chapter

Book Name Lecture Notes in Networks and Systems book series (LNNS,volume 203): Proceedings of Second International Conference on Computing, Communications, and Cyber-Security

PublisherSpringer, Singapore

Author NameUmesh Bodkhe, Sudeep Tanwar, Pronaya Bhattacharya, Ashwin Verma

Page Number759-774

Chapter TitleBlockchain adoption for trusted medical records in healthcare 4.0 applications: a survey

Published YearMay 2021

ISSN/ISBN No978-981-16-0733-2

Indexed INScopus, Others

Abstract

Healthcare 4.0 allows monitoring of electronic health record (EHR) at distributed locations, through wireless infrastructures like Bluetooth, ZigBee, near-field communication (NFC), and GPRS. Thus, the private EHR data can be tampered by malicious entities that affect updates through different stakeholders like patients, doctors, laboratory technicians, and insurance agencies. Hence, there must be a notion of trust among aforementioned stakeholders. Moreover, the accessed volume of data is humongous; thus, to ensure security and trust, blockchain (BC)-based solutions can handle timestamped volumetric data as chronological ledger. Motivated from the same, the paper presents a systematic survey of BC applications in Healthcare 4.0 ecosystems. The contribution of the paper is to conduct a systematic survey of BC adoption in Healthcare 4.0. The survey identifies tools and technologies to support BC-based healthcare applications and addresses open challenges for future research of integrating BC to secure EHR in Healthcare 4.0 ecosystem.

Secure Data Dissemination Techniques for IoT Applications: Research Challenges and Opportunities

Journal

Journal NameSoftware Practice and Experience

Title of PaperSecure Data Dissemination Techniques for IoT Applications: Research Challenges and Opportunities

PublisherWiley

Volume Number1

Page Number1-23

Published YearFebruary 2021

ISSN/ISBN No1097-024X

Indexed INScopus, Web of Science, Indian citation Index, Others

Abstract

Internet of Things (IoT) connects different objects in the physical world to the Internet, and various Internet protocols are used to provide communication services to a large number of these embedded devices termed as smart devices. But, these devices are resource-constrained, low configured, and have very low power storage capacity, which depends on the services offered by the protocols. For the exchange of information to the end-users, smart devices communicate through an open channel, such as the Internet, which is not secure enough. Moreover, efficient delivery ratio, secure data forwarding are not achieved because of the enormous amount of data produced by these smart devices and the possibility of security threats. So there is a need to devise a secure and reliable data dissemination scheme for the IoT environment. Motivated from the these facts, this paper presents a systematic review and propose a solution taxonomy for secure data dissemination techniques for various smart IoT-based applications. This paper also includes a comparison of the state-of-the-art data dissemination techniques used for the Internet of Vehicles (IoVs), Internet of Drones (IoDs), and Internet of Battlefield Things (IoBTs) applications along with their merits and demerits. Finally, the research challenges and possible countermeasures are also discussed in detail, which gives insights to the beginners who want to start work in this emerging area.

P2IoV:Privacy Preserving Lightweight Secure Data Dissemination Scheme for Internet of Vehicles

Conference

Title of PaperP2IoV:Privacy Preserving Lightweight Secure Data Dissemination Scheme for Internet of Vehicles

Proceeding Name2021 IEEE Globecom Workshops (GC Wkshps)

PublisherIEEE

Author NameUmesh Bodkhe; Sudeep Tanwar

OrganizationIEEE

Year , VenueJanuary 2021 , Madrid, Spain

Page Number1-6

ISSN/ISBN No:978-1-6654-2391-5

Indexed INScopus

Abstract

Intelligent Transportation System (ITS) and Internet of Vehicles (IoV) allows the vehicles to disseminate and exchange various messages among nearby vehicles in the network. It includes road safety, road accidents, location sharing, driver assistance, navigation, collision warning, traffic data, and toll payment. Moreover, the exchange of these messages is carried out in an insecure channel. Hence, it leads to several issues during transmission of these messages in resource constrained IoV networks. It includes reliable data dissemination, dynamic topology, mobility of the vehicles, vehicle user’s privacy, and lightweight authentication mechanism. The existing Vehicle to Vehicle (V2V) data dissemination techniques have limitations in security attacks such as side channel, device stolen, cloning attacks, high computational overhead, throughput, and high communication cost. In this article, we propose P 2 IoV: Privacy Preserving Lightweight Secure (V2V) Data Dissemination Scheme for IoV environment using lightweight cryptographic primitives such as SHA-256, concatenation and XoR operation. We evaluate P 2 IoV in terms of security and vehicle user’s privacy against several security attacks. We do an in-depth security analysis of the P 2 IoV by using informal security analysis and provides security proofs. We also perform a comparative analysis of P 2 IoV with the existing state-of-the-art IoV environment using various performance parameters. The test-bed experimental result shows that P 2 IoV outperforms the existing V2V data dissemination technique in terms of computational cost, communication overhead, and energy consumption.

Full View Taxonomy of secure data dissemination techniques for IoT environment

Journal

Journal NameIET Software

Title of PaperFull View Taxonomy of secure data dissemination techniques for IoT environment

PublisherIET Software

Volume Number14

Page Number6

Published YearSeptember 2020

ISSN/ISBN No1751-8814

Indexed INScopus, Web of Science, Indian citation Index, Others

Abstract

A huge amount of data is generated from the interaction of various sensors and Internet of Things (IoT) enabled devices used in various smart industrial applications. This enormous amount of data requires fast processing, huge storage capacity, secure dissemination, and aggregation to make it resistant from the attackers. Secure data dissemination for IoT-based applications has been a prominent issue in consideration with the heterogeneity in generated data. Existing secure data dissemination schemes are inadequate to handle secure data distribution. Research communities across the globe are focused on the delivery of the data among the sensor nodes and overlook the difficulty of its secure streaming. Hence, there is a need to validate the performance of secure data distribution schemes for IoT networks using relevant parameters. Motivated from the aforementioned facts, in this study, we perform a comprehensive review on the state-of-the-art techniques, which can verify and validate the performance of data dissemination schemes for IoT networks. We present a solution taxonomy of various verification and validation methods along with their merits and demerits. Finally, recent issues and future directions on verification and validation methods for the secure data distribution in an IoT network is presented.

Blockchain for precision irrigation: Opportunities and challenges

Journal

Journal NameTransactions on Emerging Telecommunications Technologies

Title of PaperBlockchain for precision irrigation: Opportunities and challenges

PublisherJohn Wiley & Sons, Ltd.

Volume Number1

Page Number1-21

Published YearJuly 2020

ISSN/ISBN No2161-3915

Indexed INScopus, Web of Science, Others

Abstract

In modern cities, smart irrigation systems are designed to operate via Internet of things (IoT) based sensor units having precise measurements of irrigation requirements such as amount of water, crop temperature, and humidity to build a robust supply chain ecosystem. The usage of sensors and networking units enable the optimal usage of irrigation resources, and is termed as precision irrigation (PI). Thus, PI leverage an efficient solution to handle the scarcity of essential resources such as food, water, land units, and crop yields. Thus, farmers gets better returns in the market due to high production. However, in PI, the exchange of crop readings from sensor units to actuators are processed through open channels, that is, Internet. Thus, it open the doors for malicious intruders to deploy network and sensor-based attacks on PI-sensors, to drain the available resources, and battery power of sensor nodes in the network. This reduces the optimum and precise utilization of irrigation resources, low-yield crops and damaged crops in supply chain systems. This leads to dissatisfaction among agriculture stakeholders such as quality control units, logistics, suppliers, and customers. Motivated from the above discussions, the survey presents the advantages of integrating blockchain (BC) with PI to handle issues pertaining to security, trust, and transactional payments among agriculture stakeholders. The survey is directed to achieve threefold objective- attack models and countermeasures in PI systems, integration of BC in PI to mitigate attack models, and research challenges in deploying BC in PI. To address the first objective, the survey proposes an in-depth comparative analysis of traditional irrigation systems with PI, with discussions on attack models. To address the second objective, the survey proposes an integration model of BC with PI to secure IoT sensors, and maintain trust and transparency among stakeholders. Finally, the survey addresses the open research challenges of deploying BC in PI-based irrigation systems, and presents a case-study of AgriChain as an industry ready-solution that envisions BC with PI ecosystem. Thus, the proposed survey acts as a roadmap for agriculture industry stakeholders, researchers, to deploy BC in IoT-based PI that leverages an efficient, robust, trust-worthy, and secure ecosystem.

Markov Model for Password Attack Prevention

Book Chapter

Book NameIn: Singh, P., Pawłowski, W., Tanwar, S., Kumar, N., Rodrigues, J., Obaidat, M. (eds) Proceedings of First International Conference on Computing, Communications, and Cyber-Security (IC4S 2019). Lecture Notes in Networks and Systems, vol 121. Springe

PublisherSpringer Nature Singapore Pte Ltd.

Author NameUmesh Bodkhe, Jay Chaklasiya, Pooja Shah, Sudeep Tanwar, Maanuj Vora

Page Number1-14

Chapter TitleMarkov Model for Password Attack Prevention

Published YearApril 2020

ISSN/ISBN No978-981-15-3368-6

Indexed INScopus, Others

Abstract

With the rapid increase in multi-user systems, the strength of passwords plays a crucial role in password authentication methods. Password strength meters help the users for the selection of secured passwords. But existing password strength meters are not enough to provide high level of security that makes the selection of strong password by users. Rule-based methods that measure the strength of passwords fall short in terms of accuracy and password frequencies differ among platforms. Use of Markov model-based strength meters improves the strength of password in more accurate way than the existing state-of-the-art methods. This paper describes how to proactively evaluate passwords with a strength meter by using Markov models. A mathematical proof of the prevention of guessable password attacks is presented. The proposed method improves the accuracy of current password protection methods significantly with a simpler, faster, and more secure implementation

Blockchain for industry 4.0: a comprehensive review

Journal

Journal NameIEEE Access

Title of PaperBlockchain for industry 4.0: a comprehensive review

PublisherIEEE

Volume Number8

Page Number79764-79800

Published YearApril 2020

ISSN/ISBN NoIEEE Access 2169-3536

Indexed INScopus, Web of Science, Others

Abstract

Due to the proliferation of ICT during the last few decades, there is an exponential increase in the usage of various smart applications such as smart farming, smart healthcare, supply-chain & logistics, business, tourism and hospitality, energy management etc. However, for all the aforementioned applications, security and privacy are major concerns keeping in view of the usage of the open channel, i.e., Internet for data transfer. Although many security solutions and standards have been proposed over the years to enhance the security levels of aforementioned smart applications, but the existing solutions are either based upon the centralized architecture (having single point of failure) or having high computation and communication costs. Moreover, most of the existing security solutions have focussed only on few aspects and fail to address scalability, robustness, data storage, network latency, auditability, immutability, and traceability. To handle the aforementioned issues, blockchain technology can be one of the solutions. Motivated from these facts, in this paper, we present a systematic review of various blockchain-based solutions and their applicability in various Industry 4.0-based applications. Our contributions in this paper are in four fold. Firstly, we explored the current state-of-the-art solutions in the blockchain technology for the smart applications. Then, we illustrated the reference architecture used for the blockchain applicability in various Industry 4.0 applications. Then, merits and demerits of the traditional security solutions are also discussed in comparison to their countermeasures. Finally, we provided a comparison of existing blockchain-based security solutions using various parameters to provide deep insights to the readers about its applicability in various applications

IIGPTS: IoT-based framework for Intelligent Green Public Transportation System

Book Chapter

Book Name Lecture Notes in Networks and Systems book series (LNNS,volume 121) : Proceedings of First International Conference on Computing, Communications, and Cyber-Security (IC4S 2019)

PublisherSpringer Nature Singapore Pte Ltd.

Author NameAkhilesh Ladha, Nirbhay Chaubey, Pronoya Bhattacharya, Umesh Bodkhe

Page Number1-14

Chapter TitleIIGPTS: IoT-based framework for Intelligent Green Public Transportation System

Published YearMarch 2020

ISSN/ISBN No 978-981-15-3368-6

Indexed INScopus, Others

Abstract

Today, growing urbanization coupled with the high demands of daily commute for working professionals has increased the popularity of public transport systems (PTS). The traditional PTS is in high demand in urban cities and heavily contributes to air pollution, traffic accidents, road congestion, increase of green house gases like oxides of carbon (OC), methane (CH4), and oxides of nitrogen (NOx) emissions. PTS also suffers from the limitations of preset routes, privacy, crowd, and less space for passengers. Some PTS are densely crowded in few routes, whereas in other routes they are not crowded at all. Thus, the aforementioned limitations of toxic emissions coupled with load management and balancing in PTS are a critical issue. The paper proposes IIGPTS: IoT-based framework for Intelligent Green Public Transportation System that addresses the mentioned issues by measuring emission sensor readings with respect to varying parameters like passenger density (total carrying load), fuel consumption, and routing paths. The performance of IIGPTS is analyzed at an indicated time slot to measure emissions and load on the system. Then, the simulation is performed based on dynamic routes by increasing passenger load and measuring the service time for user traffic as requests, also considering the request drops. The results obtained by IIGPTS framework indicate a delay of 104 s for 10,000 requests spread across an entire day, which is negligible considering the load. Thus, IIGPTS can intelligently handle varying capacity loads at varying routes, with fewer emissions, making the realization of green eco-friendly PTS systems a reality.

A Survey on Decentralized Consensus Mechanisms for Cyber Physical Systems

Journal

Journal NameIEEE ACCESS

Title of PaperA Survey on Decentralized Consensus Mechanisms for Cyber Physical Systems

PublisherIEEE

Volume Number8

Page Number54371 - 54401

Published YearMarch 2020

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science, Others

Abstract

Modern industry 4.0 applications are shifting towards decentralized automation of computing and cyber-physical systems (CPS), which necessitates building a robust, secure, and efficient system that performs complex interactions with other physical processes. To handle complex interactions in CPS, trust and consensus among various stakeholders is a prime concern. In a similar direction, consensus algorithms in blockchain have evolved over the years that focus on building smart, robust, and secure CPS. Thus, it is imperative to understand the key components, functional characteristics, and architecture of different consensus algorithms used in CPS. Many consensus algorithms exist in the literature with a specified set of functionalities, performance, and computing services. Motivated from these facts, in this survey, we present a comprehensive analysis of existing state-of-the-art consensus mechanisms and highlight their strength and weaknesses in decentralized CPS applications. In the first part, we present the scope of the proposed survey and identify gaps in the existing surveys. Secondly, we present the review method and objectives of the proposed survey based on research questions that address the gaps in existing studies. Then, we present a solution taxonomy of decentralized consensus mechanisms for various CPS applications. Then, open issues and challenges are also discussed in deploying various consensus mechanisms in the CPS with their merits and demerits. The proposed survey will act as a road-map for blockchain developers and researchers to evaluate and design future consensus mechanisms, which helps to build an efficient CPS for industry 4.0 stakeholders

BinDaaS: Blockchain-Based Deep-Learning as-a-Service in Healthcare 4.0 Applications

Journal

Journal NameIEEE Transactions on Network Science and Engineering

Title of PaperBinDaaS: Blockchain-Based Deep-Learning as-a-Service in Healthcare 4.0 Applications

PublisherIEEE

Volume Number1

Page Number1-12

Published YearDecember 2019

Indexed INScopus, Web of Science, Indian citation Index, Others

Abstract

Electronic Health Records (EHRs) allows patients to control, share, and manage their health records among family members, friends, and healthcare service providers using an open channel, i.e., Internet. Thus, privacy, confidentiality, and data consistency are major challenges in such an environment. Although, cloud-based EHRs addresses the aforementioned discussions, but these are prone to various malicious attacks, trust management, and non-repudiation among servers. Hence, blockchain-based EHR systems are most popular to create the trust, security, and privacy among healthcare users. Motivated from the aforementioned discussions, we proposes a framework called as Blockchain-Based Deep Learning as-a-Service (BinDaaS). It integrates blockchain and deep-learning techniques for sharing the EHR records among multiple healthcare users and operates in two phases. In the first phase, an authentication and signature scheme is proposed based on lattices-based cryptography to resist collusion attacks among N-1 healthcare authorities from N. In the second phase, Deep Learning as-a-Service (DaaS) is used on stored EHR datasets to predict future diseases based on current indicators and features of patient. The obtained results are compared using various parameters such as accuracy, end-to-end latency, mining time, and computation and communication costs in comparison to the existing state-of-the-art proposals. From the results obtained, it is inferred that BinDaaS outperforms the other existing proposals with respect to the aforementioned parameters.

BloHosT: Blockchain enabled smart tourism and hospitality management

Conference

Title of PaperBloHosT: Blockchain enabled smart tourism and hospitality management

Proceeding Name2019 international conference on computer, information and telecommunication systems (CITS)

PublisherIEEE

Author NameUmesh Bodkhe, Pronaya Bhattacharya, Sudeep Tanwar, Sudhanshu Tyagi, Neeraj Kumar, Mohammad S Obaidat

OrganizationIEEE

Year , VenueAugust 2019 , Beijing, China

Page Number1-5

ISSN/ISBN No978-1-7281-1374-6

Indexed INScopus, EBSCO

Abstract

In the era of Industry 4.0, e-tourism uses bulk of digital payments through applications supported by heterogeneous payment gateways. These heterogeneous payment gateways open the doors for the attackers to perform malicious activities such as-hacking of wallet accounts, identity theft, attacks on payment clearance cycles. In e-tourism, financial data is maintained in a centralized cloud server, which can lead to payment failures during peak traffic. The aforementioned issues can be addressed by the usage of a decentralized mechanism such as-blockchain, which enables trust and reputation management among various stakeholders such as-banks, travel agencies, airports, railways, cruises, hotels, restaurants, and local taxis. Motivated by the above discussion, we propose a framework named as BloHosT (Blockchain Enabled Smart Tourism and Hospitality Management), which allows tourists to interact with various stakeholders through a single wallet identifier linked with a cryptocurrency server to initiate payments. BloHosT uses an immutable ledger, where no proofs are required during travel that provides a hassle-free experience to tourists. Also, a Tourism enabled Deep-Learning (TeDL) framework is presented as a part of BloHosT framework, which is trained on experience of previous visited travelers. It provides rating scores to prospective travelers about the recently visited locations by previous travelers. Finally, through case studies, we demonstrate that BloHosT achieves a high Return of Investment (ROI) in tourism sector as compared to traditional frameworks

“Managing Cooperative Behaviour in Social Communication” ICASCCT 2014, Hyderabad

Conference

Title of Paper“Managing Cooperative Behaviour in Social Communication” ICASCCT 2014, Hyderabad

Proceeding NameAdvances in Soft Computing and Communication Technologies (ICASCCT) 2014, Hyderabad

Year , VenueAugust 2014 , Hyderabad

ISSN/ISBN No 2229-3515

Indexed INUGC List

Crop type classification with hyperspectral images using deep learning : a transfer learning approach

Journal

Journal NameModeling Earth Systems and Environment

Title of PaperCrop type classification with hyperspectral images using deep learning : a transfer learning approach

PublisherSpringer

Published YearJanuary 2022

Indexed INScopus

Hyperspectral Image Classification using Uncertainty and Diversity based Active Learning

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperHyperspectral Image Classification using Uncertainty and Diversity based Active Learning

Volume Number22

Page Number283-293

Published YearJanuary 2022

Indexed INScopus

Towards automating irrigation: a fuzzy logic-based water irrigation system using iot and deep learning

Journal

Journal NameModeling Earth Systems and Environment

Title of PaperTowards automating irrigation: a fuzzy logic-based water irrigation system using iot and deep learning

PublisherSpringer

Volume Number8

Page Number5235-5250

Published YearJanuary 2022

Indexed INScopus, Web of Science

Document classification using deep neural network with different word embedding techniques

Journal

Journal NameInternational Journal of Web Engineering and Technology

Title of PaperDocument classification using deep neural network with different word embedding techniques

PublisherInderscience

Volume Number17

Page Number203-222

Published YearJanuary 2022

Blockchain and AI-Empowered Healthcare Insurance Fraud Detection: An Analysis, Architecture, and Future Prospects

Journal

Journal NameIEEE Access

Title of PaperBlockchain and AI-Empowered Healthcare Insurance Fraud Detection: An Analysis, Architecture, and Future Prospects

PublisherIEEE

Volume Number10

Page Number79606-79627

Published YearJanuary 2022

Indexed INScopus, Web of Science

Hardware Implementation of Public Key Cryptography for Small-Scale Devices

Book Chapter

Book NameLecture Notes in Networks and Systems book series

PublisherSpringer

Page Number9-15

Chapter TitleHardware Implementation of Public Key Cryptography for Small-Scale Devices

Published YearNovember 2018

ISSN/ISBN No978-981-13-2323-2

Indexed INScopus

Abstract

Ocean Surface Pollution Detection: Applicability Analysis of V-Net with Data Augmentation for Oil Spill and Other Related Ocean Surface Feature Monitoring

Book Chapter

Book NameCommunication and Intelligent Systems

PublisherSpringer

Author NameNaishadh Mehta, Pooja Shah, Pranshav Gajjar, Vijay Ukani

Page Number11-25

Chapter Title Ocean Surface Pollution Detection: Applicability Analysis of V-Net with Data Augmentation for Oil Spill and Other Related Ocean Surface Feature Monitoring

Published YearAugust 2022

ISSN/ISBN No978-981-19-2130-8

Indexed INScopus

Optimized Reverse TCP Shell Using One-Time Persistent Connection

Book Chapter

Book NameInnovations in Information and Communication Technologies

PublisherSpringer

Author NameAnush Manglani, Tadrush Desai, Pooja Shah, Vijay Ukani

Page Number351-358

Chapter TitleOptimized Reverse TCP Shell Using One-Time Persistent Connection

Published YearJuly 2021

ISSN/ISBN No978-3-030-66218-9

Indexed INScopus

Applicability Analysis Of VGGNET Based Transfer Learning For Oil Spill Classification On SAR Data

Journal

Journal NameTurkish Journal of Computer and Mathematics Education

Title of PaperApplicability Analysis Of VGGNET Based Transfer Learning For Oil Spill Classification On SAR Data

PublisherScience Research Society

Volume Number12

Page Number1489-1494

Published YearApril 2021

Combining user-based and item-based collaborative filtering using machine learning

Book Chapter

Book NameInformation and Communication Technology for Intelligent Systems

PublisherSpringer

Author NamePriyank Thakkar, Krunal Varma, Vijay Ukani, Sapan Mankad, Sudeep Tanwar

Page Number173-180

Chapter TitleCombining user-based and item-based collaborative filtering using machine learning

Published YearDecember 2018

ISSN/ISBN No978-981-13-1747-7

Indexed INScopus

Detection of Mimicry Attacks on Speaker Verification System for Cartoon Characters’ Dataset

Book Chapter

Book NameInformation and Communication Technology for Intelligent Systems

PublisherSpringer

Author NameRaag Anarkat, Sapan H Mankad, Priyank Thakkar, Vijay Ukani

Page Number319-326

Chapter TitleDetection of Mimicry Attacks on Speaker Verification System for Cartoon Characters’ Dataset

Published YearDecember 2018

ISSN/ISBN No978-981-13-1747-7

Indexed INScopus

A Range-Based Adaptive and Collaborative Localization for Wireless Sensor Networks

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer

Page Number293-302

Chapter TitleA Range-Based Adaptive and Collaborative Localization for Wireless Sensor Networks

Published YearDecember 2018

ISSN/ISBN No978-981-13-1747-7

Indexed INScopus, UGC List

Outcome fusion-based approaches for user-based and item-based collaborative filtering

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer

Author NamePriyank Thakkar, Krunal Varma, Vijay Ukani

Page Number127-135

Chapter TitleOutcome fusion-based approaches for user-based and item-based collaborative filtering

Published YearAugust 2017

ISSN/ISBN No978-3-319-63645-0

Indexed INScopus

Routing Protocols for Wireless Multimedia Sensor Networks: Challenges and Research Issues

Book Chapter

Book Name Smart Innovation, Systems and Technologies

PublisherSpringer

Page Number157-164

Chapter TitleRouting Protocols for Wireless Multimedia Sensor Networks: Challenges and Research Issues

Published YearAugust 2017

ISSN/ISBN No978-3-319-63645-0

Indexed INScopus, UGC List

Efficient Vehicle Detection and Classification for Traffic Surveillance System

Book Chapter

Book NameCommunications in Computer and Information Science

PublisherSpringer, Singapore

Page Number495-503

Chapter TitleEfficient Vehicle Detection and Classification for Traffic Surveillance System

Published YearJuly 2017

ISSN/ISBN No978-981-10-5426-6

Indexed INScopus, UGC List, Others

Open Issues in Named Data Networking - A Survey

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer, Cham

Page Number285-292

Chapter TitleOpen Issues in Named Data Networking - A Survey

Published YearMarch 2017

ISSN/ISBN No978-3-319-63672-6

Indexed INScopus, UGC List

Abstract

Internet is now being used as content distribution network also. Internet users are interested in specific contents rather than host machines where the content is located. Named Data Networking (NDN) is a step towards future Internet architecture that would be based on named data rather than numerically identified hosts.

QoS Aware Geographic Routing Protocol for Multimedia Transmission in Wireless Sensor Network

Conference

Title of PaperQoS Aware Geographic Routing Protocol for Multimedia Transmission in Wireless Sensor Network

Proceeding Name2015 5th Nirma University International Conference on Engineering (NUiCONE)

PublisherIEEEXplore

OrganizationNirma University

Year , VenueDecember 2015 , Nirma University

Indexed INOthers

A Realistic Coverage Model with Backup Set Computation for Wireless Video Sensor Network

Journal

Journal NameNirma University Journal of Technology

Title of PaperA Realistic Coverage Model with Backup Set Computation for Wireless Video Sensor Network

PublisherNirma University

Volume Number4

Page Number20-24

Published YearAugust 2015

Computation of Coverage Backup Set for Wireless Video Sensor Networks

Conference

Title of PaperComputation of Coverage Backup Set for Wireless Video Sensor Networks

Proceeding NameTENSYMP 2015 - An International Conference of IEEE region 10

PublisherIEEEXplore

OrganizationIEEE Region 10

Year , VenueMay 2015 , GIFT City, Gandhinagar

Page Number37-40

Indexed INOthers

An Energy Efficient Routing Protocol for Wireless Multimedia Sensor Networks

Conference

Title of PaperAn Energy Efficient Routing Protocol for Wireless Multimedia Sensor Networks

Proceeding NameDevices, Circuits and Communications (ICDCCom), 2014 International Conference on

PublisherIEEEXplore

OrganizationKrishna Engineering College

Year , VenueSeptember 2014 , Gaziabad

Page Number1-6

Indexed INOthers

VAQMAC: Video Aware QoS MAC Protocol for Wireless Video Sensor Networks

Journal

Journal NameInternational Journal of Electronics and Communication Engineering And Technology

Title of PaperVAQMAC: Video Aware QoS MAC Protocol for Wireless Video Sensor Networks

Volume Number4

Page Number103-115

Published YearApril 2014

Aggregation in Wireless Multimedia Sensor Networks

Conference

Title of PaperAggregation in Wireless Multimedia Sensor Networks

Proceeding NameEngineering (NUiCONE), 2013 Nirma University International Conference on

PublisherIEEEXplore

OrganizationNirma University

Year , VenueNovember 2013 , Nirma University

Page Number1-6

Indexed INOthers

An Empirical Analysis of Multiclass Classification Techniques in Data Mining

Conference

Title of PaperAn Empirical Analysis of Multiclass Classification Techniques in Data Mining

Proceeding NameEngineering (NUiCONE), 2011 Nirma University International Conference on

PublisherIEEEXplore

OrganizationNirma University

Year , VenueDecember 2011 , Nirma University

Page Number1-5

Indexed INOthers

Security Analysis of Multi-factor Authentication with Legitimate Key Exchange for Vehicle to Vehicle Communication

Book Chapter

Book NameLecture Notes in Networks and Systems

PublisherSpringer, Singapore

Author NameVipul Chudasama

Page Number437-446

Chapter TitleSecurity Analysis of Multi-factor Authentication with Legitimate Key Exchange for Vehicle to Vehicle Communication

Published YearNovember 2023

ISSN/ISBN No978-981-99-5652-4

Indexed INScopus

Abstract

Internet of Vehicles (IOV) in which the vehicles share information like traffic, road safety, location sharing, toll payment, road accident, etc. with each other wirelessly. Vehicle Ad-hoc Network (VANET) includes reliable data transmission on a network, frequently changing topology, mobility of vehicles, and security of each component where vehicles can communicate securely and effectively. However, the existing framework has some security issues for which the security properties like nonce and multi-factor authentication needs to consider. At last, we suggest that our framework is more secure and efficient for V2V communication.

Next-Generation Firewall with Intelligent IPS

Book Chapter

Book NameLecture Notes in Electrical Engineering

PublisherSpringer, Singapore

Author NameParth Barot, Sharada Valiveti , Vipul Chudasama

Page Number 387–395

Chapter TitleNext-Generation Firewall with Intelligent IPS

Published YearMay 2023

ISSN/ISBN No978-981-19-8865-3

Indexed INScopus

Abstract

These days, Internet is used for almost everything. There are several mediums (channels) available for people to search for information that is relevant either in terms of business or entertainment perspective. These mediums can be used by a hacker to steal information and perform an attack on any network infrastructure using various techniques. Hence, securing the network is essential for cybersecurity. Accordingly, various types of attacks like denial of service (DoS) attacks, backdoors, buffer overflow, guess the password, Smurf DoS, etc., are quite prevalent and are commonly used by an attacker. This paper presents the complete process to detect and re-mediate/mitigate these attacks using automatic detection techniques. The paper includes ways to improve network security using the feature of intrusion prevention system in firewall by detecting and analyzing the packet flows. The main objective of the paper is to detect the attack, analyze it, and if it is risky then drop the attacking packet before it harms the network. Also, the paper presents the error and accuracy rate of detecting attacks using the different machine learning algorithms which can be used in the IPS.

Voice Based Pathology Detection from Respiratory Sounds using Optimized Classifiers

Journal

Journal NameInternational Journal of Computing and Digital Systems

Title of Paper Voice Based Pathology Detection from Respiratory Sounds using Optimized Classifiers

PublisherUniversity of Bahrain

Volume Number13

Page Number327-339

Published YearJanuary 2023

ISSN/ISBN No2210-142X

Indexed INScopus

Abstract

Speech is an important tool for communication. When a person speaks, the vocal cords come closer and the glottis is partially closed. The airflow which passes through glottis is disturbed by vocal cords and speech waveform is produced. The person who suffers from the vocal cord paralysis or vocal cord blister, his lungs are filled with fluid and airway blockage cannot generate a similar waveform as a healthy person. In this work, we compare traditional approaches with deep learning based approaches for respiratory disease detection to distinguish between a healthy person and the victim of pathological voice disorder. Four conventional machine learning classifiers and a one-dimensional convolution neural network based classifier have been implemented on two benchmark datasets ICBHI 2017 and Coswara. Our experiments show that the CNN based approach and Random Forest algorithm exhibit superior performance over other approaches on ICBHI 2017 and Coswara datasets, respectively.

A Dynamic Prediction for Elastic Resource Allocation in Hybrid Cloud Environment

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperA Dynamic Prediction for Elastic Resource Allocation in Hybrid Cloud Environment

Volume Number21

Page Number661-672

Published YearDecember 2020

ISSN/ISBN No1895-1767

Indexed INScopus

Abstract

Cloud applications heavily use resources and generate more traffic specifically during specific events. In order to achieve quality in service provisioning, the elasticity of resources is a major requirement. With the use of a hybrid cloud model, organizations combine the private and public cloud services to deploy applications for the elasticity of resources. For elasticity, a traditional adaptive policy implements threshold-based auto-scaling approaches that are adaptive and simple to follow. However, during a high dynamic and unpredictable workload, such a static threshold policy may not be effective. An efficient auto-scaling technique that predicts the system load is highly necessary. Balancing a dynamism of load through the best auto-scale policy is still a challenging issue. In this paper, we suggest an algorithm using Deep learning and queuing theory concepts that proactively indicate an appropriate number of future computing resources for short term resource demand. Experiment results show that the proposed model predicts SLA violation with higher accuracy 5% than the baseline model. The suggested model enhances the elasticity of resources with performance metrics.

Establishing Trust in the Cloud Using Machine Learning Methods

Conference

Title of PaperEstablishing Trust in the Cloud Using Machine Learning Methods

Proceeding NameProceedings of First International Conference on Computing, Communications, and Cyber-Security (IC4S 2019)

PublisherSpringer, Singapore

Author NameVipul Chudasama

Year , VenueJanuary 2020 , Gaziabad, india

Page Number791-805

Indexed INScopus

Abstract

n the modern era of digitization, cloud computing is playing an important key role. Tons of user’s data is on the cloud and to manage it with all the odds is a mesmerizing task. To provide user’s data integrity and security are the major task for any cloud service provider. In the last few decades, researchers have been motivated to provide security on a cloud with reference to the categorization and classification of security concerns. In the cloud, trust is a major issue with respect to cloud security. The facilities provided by the cloud are too attractive for customers. Cloud has distributed and non-transparent services due to that the users may lose their control over the data and they are not sure whether the cloud provider is trusted one or not. This paper mainly focuses on establishing trust in the cloud using machine learning methods.

Energy Aware Computing Resource Allocation Using PSO in Cloud

Book Chapter

Book NameInformation and Communication Technology for Intelligent Systems

PublisherSpringer, Singapore

Page Number511-519

Chapter TitleEnergy Aware Computing Resource Allocation Using PSO in Cloud

Published YearDecember 2018

ISSN/ISBN No978-981-13-1746-0

Indexed INScopus, UGC List

Abstract

In cloud computing, a large number of resources are used like data Centres, servers, computing resources (VMs), and IoT devices. One of the key challenges in cloud computing is to provide energy-efficient resource management. In this resource management, energy is one of the key parameters which is to be resolved.

A Trust Rating Model Using Fuzzy Logic in Cloud

Book Chapter

Book NameInternational Conference on Innovative Computing and Communications

PublisherSpringer, Singapore

Page Number339-348

Chapter TitleA Trust Rating Model Using Fuzzy Logic in Cloud

Published YearNovember 2018

ISSN/ISBN No978-981-13-2353-9

Indexed INScopus

Abstract

Cloud computing provides services from the available pool of resources. Even with the available condition, cloud computing can reach the peak of success amongst cloud user. The issue they face is the barrier of trust between the end users for using the given services. Conventional security and protection controls keeps on being executed on cloud; however, because of its liquid and dynamic nature, a testable trust estimate of the cloud is required. This research paper exhibits an analysis of the present trust administration strategies for cloud operations. In this research paper, we proposed a model for trust administration using Fuzzy Logic, which can be beneficial for cloud service providers to select trusted datacenter for consumers.

SLA Management in Cloud Federation

Journal

Journal NameInternational Conference on Information and Communication Technology for Intelligent Systems

Title of PaperSLA Management in Cloud Federation

PublisherSpringer, Singapore

Volume Number84

Page Number397-404

Published YearNovember 2017

ISSN/ISBN No978319636443

Indexed INScopus

Abstract

Now a days cloud computing is the major area of research Because cloud computing has own many benefits. Cloud computing also provides cost effective Resources so that it can become more and more helpful to IT trends. Distributed computing is an extensive arrangement that conveys IT as an administration. It is an Internet-based registering arrangement where shared assets are given like power disseminated on the electrical grid. Cloud suggest to a particular IT environment that is expected with the end goal of remotely provisioning versatile and measured IT resources. Whereas the Internet gives open access to many Web-based IT assets, a cloud is commonly exclusive and offers access to IT assets that is metered following SLAs implementation depends on guidelines that are redesigned in runtime so as to proactively recognize conceivable SLA Violations and handle them in a proper manner. Our proposed framework allows the creation and implementation of effective SLA for provisioning of service. SLA management are one kind of common comprehension between CSP (Cloud Service Provider) and customer.

Weight Based Workflow Scheduling in Cloud Federation

Journal

Journal NameInternational Conference on Information and Communication Technology for Intelligent Systems

Title of PaperWeight Based Workflow Scheduling in Cloud Federation

PublisherSpringer, Singapore

Volume Number84

Page Number405-411

Published YearAugust 2017

ISSN/ISBN No978319636443

Indexed INScopus

Abstract

To cater the need of a user as the requirement of infrastructure, application building environment or contemporary software private and public clouds are exiting for provisioning of such services. But cloud providers are facing the problem of how to deploy their applications over different clouds keeping in mind their different requirements in terms of QoS (Cost, resource utilization, execution time). Different clouds have different advantages such as one cloud will be more reliable and efficient whereas, private cloud will be more secure or less expensive. In order to get the benefits of both clouds, we can use the concept of cloud federation. When using cloud federation it becomes important how to schedule large workflows over federated clouds. Proposed work addresses the issue of scheduling large workflow over federated clouds. SMARTFED is used for the cloud federation and our algorithm is used to schedule different workflows according to the QoS parameters over the federation.

Intelligent Video Analytic Based Framework for Multi-view Video Summarization

Journal

Journal NameInternational Journal of Computing and Digital Systems

Title of PaperIntelligent Video Analytic Based Framework for Multi-view Video Summarization

PublisherUniversity of Bahrain Scientific Journals

Volume Number12

Page Number619-628

Published YearAugust 2022

ISSN/ISBN No2210-142X

Indexed INScopus

Abstract

A multi-view surveillance system captures the scenic details from a different perspective, defined by camera placements. The recorded data is used for feature extraction, which can be further utilized for various pattern-based analytic processes like object detection, event identification, and object tracking. In this proposed work, we present a method for creating a network of the optimal number of video cameras, to cover the maximum overlapping area under surveillance. In the proposed work, the focus is on developing algorithms for deciding efficient camera placement of multiple cameras at various junctions and intersections to generate a video summary based on the multiple views. Deep learning models like YOLO have been used for object detection based on the generation of a large number of bounding boxes and the associated search technique for generating rankings based on the views of the multiple cameras. Based on the view quality, the dominant views will be located. Further, keyframes are selected based on maximum frame coverage from these views. A video summary will be generated based on these keyframes. Thus, the video summary is generated through solving a multi-objective optimization problem based on keyframe importance evaluated using a maximum frame coverage.

Comparative Analysis of Key-frame Extraction Techniques for Video Summarization

Journal

Journal NameRecent Advances in Computer Science and Communications

Title of PaperComparative Analysis of Key-frame Extraction Techniques for Video Summarization

PublisherBentham Science

Volume Number14

Page Number2753-2763

Published YearJuly 2020

ISSN/ISBN No2666-2558

Indexed INScopus

Abstract

Background: With technological advancement, the quality of life of people has improved. Also, with technological advancement, large amounts of data are produced by people. The data is in the forms of text, images and videos. Hence, there is a need for significant efforts and means of devising methodologies for analyzing and summarizing them to manage with the space constraints. Video summaries can be generated either by keyframes or by skim/shot. The keyframe extraction is done based on deep learning-based object detection techniques. Various object detection algorithms have been reviewed for generating and selecting the best possible frames as keyframes. A set of frames is extracted out of the original video sequence and based on the technique used, one or more frames of the set are decided as a keyframe, which then becomes the part of the summarized video. The following paper discusses the selection of various keyframe extraction techniques in detail. Methods: The research paper is focused on the summary generation for office surveillance videos. The major focus of the summary generation is based on various keyframe extraction techniques. For the same, various training models like Mobilenet, SSD, and YOLO are used. A comparative analysis of the efficiency for the same showed that YOLO gives better performance as compared to the other models. Keyframe selection techniques like sufficient content change, maximum frame coverage, minimum correlation, curve simplification, and clustering based on human presence in the frame have been implemented. Results: Variable and fixed-length video summaries were generated and analyzed for each keyframe selection technique for office surveillance videos. The analysis shows that the output video obtained after using the Clustering and the Curve Simplification approaches is compressed to half the size of the actual video but requires considerably less storage space. The technique depending on the change of frame content between consecutive frames for keyframe selection produces the best output for office surveillance videos. Conclusion: In this paper, we discussed the process of generating a synopsis of a video to highlight the important portions and discard the trivial and redundant parts. Firstly, we have described various object detection algorithms like YOLO and SSD, used in conjunction with neural networks like MobileNet, to obtain the probabilistic score of an object that is present in the video. These algorithms generate the probability of a person being a part of the image for every frame in the input video. The results of object detection are passed to keyframe extraction algorithms to obtain the summarized video. Our comparative analysis for keyframe selection techniques for office videos will help in determining which keyframe selection technique is preferable.

Optimal Camera Placement for Multimodal Video Summarization

Book Chapter

Book NameCommunications in Computer and Information Science

PublisherSpringer

Author NameVishal Parikh, Priyanka Sharma, Vijay Ukani

Page Number123-134

Chapter TitleOptimal Camera Placement for Multimodal Video Summarization

Published YearDecember 2018

ISSN/ISBN No978-981-13-3804-5

Indexed INScopus, UGC List

Routing Protocols for Wireless Multimedia Sensor Networks: Challenges and Research Issues

Book Chapter

Book NameSmart Innovation, Systems and Technologies

PublisherSpringer

Author NameVijay Ukani

Page Number157-164

Chapter TitleRouting Protocols for Wireless Multimedia Sensor Networks: Challenges and Research Issues

Published YearAugust 2017

ISSN/ISBN No2190-3026

Indexed INScopus, EBSCO, Others

Abstract

Due to miniaturization of hardware and availability of low-cost, low-power sensors, Wireless Sensor Network and Multimedia Sensor Network applications are increasing day by day. Each application has a specific quality of service and experience requirements. The design of routing and MAC protocol which can fulfill the requirements of the application is challenging given the constrained nature of these devices. Considerable efforts are directed towards the design of energy efficient QoS-aware routing protocols. In this article, we present state of the art review of routing protocols for Wireless Multimedia Sensor Networks while addressing the challenges and providing insight into research issues.

Improving Security in P2P File Sharing Based on Network Coding for DTN

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperImproving Security in P2P File Sharing Based on Network Coding for DTN

PublisherIJCSC

Volume Number7

Page Number167-172

Published YearMarch 2016

ISSN/ISBN No0973-7391

Indexed INOthers

E-commerce Recommendation System usingAssociation Rule Mining and Clustering

Journal

Journal NameInternational Journal of Innovations & Advancement in Computer Science

Title of PaperE-commerce Recommendation System usingAssociation Rule Mining and Clustering

PublisherAcademic Science

Volume Number4

Page Number148-155

Published YearMay 2015

ISSN/ISBN No2347-8616

Stock Prediction and Automated Trading System

Journal

Journal NameInternational Journal of Computer Science & Communication

Title of PaperStock Prediction and Automated Trading System

PublisherIJCSC

Volume Number6

Page Number104-111

Published YearMarch 2015

ISSN/ISBN No0973-7391

Efficient Resource Utilization in IoT and Cloud Computing

Journal

Journal NameMDPI: Information

Title of PaperEfficient Resource Utilization in IoT and Cloud Computing

PublisherMDPI

Volume Number14

Page Number2-39

Published YearNovember 2023

ISSN/ISBN No2078-2489

Indexed INScopus, Web of Science

Abstract

With the proliferation of IoT devices, there has been exponential growth in data gen- eration, placing substantial demands on both cloud computing (CC) and internet infrastructure. CC, renowned for its scalability and virtual resource provisioning, is of paramount importance in e-commerce applications. However, the dynamic nature of IoT and cloud services introduces unique challenges, notably in the establishment of service-level agreements (SLAs) and the continuous moni- toring of compliance. This paper presents a versatile framework for the adaptation of e-commerce applications to IoT and CC environments. It introduces a comprehensive set of metrics designed to support SLAs by enabling periodic resource assessments, ensuring alignment with service-level objectives (SLOs). This policy-driven approach seeks to automate resource management in the era of CC, thereby reducing the dependency on extensive human intervention in e-commerce applica- tions. This paper culminates with a case study that demonstrates the practical utilization of metrics and policies in the management of cloud resources. Furthermore, it provides valuable insights into the resource requisites for deploying e-commerce applications within the realms of the IoT and CC. This holistic approach holds the potential to streamline the monitoring and administration of CC services, ultimately enhancing their efficiency and reliability.

CIA-CVD: cloud based image analysis for COVID-19 vaccination distribution

Journal

Journal NameJournal of Cloud Computing-Springer

Title of PaperCIA-CVD: cloud based image analysis for COVID-19 vaccination distribution

PublisherSpringer

Volume Number12

Page Number1-12

Published YearJuly 2023

ISSN/ISBN No2192-113X

Indexed INScopus, Web of Science

Abstract

Due to the huge impact of COVID-19, the world is currently facing a medical emergency and shortage of vaccine. Many countries do not have enough medical equipment and infrastructure to tackle this challenge. Due to the lack of a central administration to guide the countries to take the necessary precautions, they do not proactively identify the cases in advance. This has caused Covid-19 cases to be on the increase, with the number of cases increasing at a geometric progression. Rapid testing, RT-PCR testing, and a CT-Scan/X-Ray of the chest are the primary procedures in identifying the covid-19 disease. Proper immunization is delivered on a priority basis based on the instances discovered in order to preserve human lives. In this research paper, we suggest a technique for identifying covid-19 positive cases and determine the most affected locations of covid-19 cases for vaccine distribution in order to limit the disease's impact. To handle the aforementioned issues, we propose a cloud based image analysis approach for using a COVID-19 vaccination distribution (CIA-CVD) model. The model uses a deep learning, machine learning, digital image processing and cloud solution to deal with the increasing cases of COVID-19 and its priority wise distribution of the vaccination.

Game-o-Meta: Trusted Federated Learning Scheme for P2P Gaming Metaverse beyond 5G Networks

Journal

Journal NameMDPI: Sensors

Title of PaperGame-o-Meta: Trusted Federated Learning Scheme for P2P Gaming Metaverse beyond 5G Networks

PublisherMDPI

Volume Number23

Page Number1-25

Published YearApril 2023

ISSN/ISBN No1424-8220

Indexed INScopus, Web of Science

Abstract

The aim of the peer-to-peer (P2P) decentralized gaming industry has shifted towards realistic gaming environment (GE) support for game players (GPs). Recent innovations in the metaverse have motivated the gaming industry to look beyond augmented reality and virtual reality engines, which improve the reality of virtual game worlds. In gaming metaverses (GMs), GPs can play, socialize, and trade virtual objects in the GE. On game servers (GSs), the collected GM data are analyzed by artificial intelligence models to personalize the GE according to the GP. However, communication with GSs suffers from high-end latency, bandwidth concerns, and issues regarding the security and privacy of GP data, which pose a severe threat to the emerging GM landscape. Thus, we proposed a scheme, Game-o-Meta, that integrates federated learning in the GE, with GP data being trained on local devices only. We envisioned the GE over a sixth-generation tactile internet service to address the bandwidth and latency issues and assure real-time haptic control. In the GM, the GP’s game tasks are collected and trained on the GS, and then a pre-trained model is downloaded by the GP, which is trained using local data. The proposed scheme was compared against traditional schemes based on parameters such as GP task offloading, GP avatar rendering latency, and GS availability. The results indicated the viability of the proposed scheme.

Federated Learning for the Internet-of-Medical-Things: A Survey

Journal

Journal NameMDPI: Mathematics

Title of PaperFederated Learning for the Internet-of-Medical-Things: A Survey

PublisherMDPI

Volume Number11

Page Number1-47

Published YearDecember 2022

ISSN/ISBN NoISSN: 2227-7390

Indexed INScopus, Web of Science

Abstract

Recently, in healthcare organizations, real-time data have been collected from connected or implantable sensors, layered protocol stacks, lightweight communication frameworks, and end devices, named the Internet-of-Medical-Things (IoMT) ecosystems. IoMT is vital in driving healthcare analytics (HA) toward extracting meaningful data-driven insights. Recently, concerns have been raised over data sharing over IoMT, and stored electronic health records (EHRs) forms due to privacy regulations. Thus, with less data, the analytics model is deemed inaccurate. Thus, a transformative shift has started in HA from centralized learning paradigms towards distributed or edge-learning paradigms. In distributed learning, federated learning (FL) allows for training on local data without explicit data-sharing requirements. However, FL suffers from a high degree of statistical heterogeneity of learning models, level of data partitions, and fragmentation, which jeopardizes its accuracy during the learning and updating process. Recent surveys of FL in healthcare have yet to discuss the challenges of massive distributed datasets, sparsification, and scalability concerns. Because of this gap, the survey highlights the potential integration of FL in IoMT, the FL aggregation policies, reference architecture, and the use of distributed learning models to support FL in IoMT ecosystems. A case study of a trusted cross-cluster-based FL, named Cross-FL, is presented, highlighting the gradient aggregation policy over remotely connected and networked hospitals. Performance analysis is conducted regarding system latency, model accuracy, and the trust of consensus mechanism. The distributed FL outperforms the centralized FL approaches by a potential margin, which makes it viable for real-IoMT prototypes. As potential outcomes, the proposed survey addresses key solutions and the potential of FL in IoMT to support distributed networked healthcare organizations.

Explainable AI for Healthcare 5.0: Opportunities and Challenges

Journal

Journal NameIEEE Access

Title of PaperExplainable AI for Healthcare 5.0: Opportunities and Challenges

PublisherIEEE

Volume Number10

Page Number2169-3536

Published YearAugust 2022

ISSN/ISBN No2169-3536

Indexed INScopus, Web of Science

Abstract

In the healthcare domain, a transformative shift is envisioned towards Healthcare 5.0. It expands the operational boundaries of Healthcare 4.0 and leverages patient-centric digital wellness. Healthcare 5.0 focuses on real-time patient monitoring, ambient control and wellness, and privacy compliance through assisted technologies like artificial intelligence (AI), Internet-of-Things (IoT), big data, and assisted networking channels. However, healthcare operational procedures, verifiability of prediction models, resilience, and lack of ethical and regulatory frameworks are potential hindrances to the realization of Healthcare 5.0. Recently, explainable AI (EXAI) has been a disruptive trend in AI that focuses on the explainability of traditional AI models by leveraging the decision-making of the models and prediction outputs. The explainability factor opens new opportunities to the black-box models and brings confidence in healthcare stakeholders to interpret the machine learning (ML) and deep learning (DL) models. EXAI is focused on improving clinical health practices and brings transparency to the predictive analysis, which is crucial in the healthcare domain. Recent surveys on EXAI in healthcare have not significantly focused on the data analysis and interpretation of models, which lowers its practical deployment opportunities. Owing to the gap, the proposed survey explicitly details the requirements of EXAI in Healthcare 5.0, the operational and data collection process. Based on the review method and presented research questions, systematically, the article unfolds a proposed architecture that presents an EXAI ensemble on the computerized tomography (CT) image classification and segmentation process. A solution taxonomy of EXAI in Healthcare 5.0 is proposed, and operational challenges are presented. A supported case study on electrocardiogram (ECG) monitoring is presented that preserves the privacy of local models via federated learning (FL) and EXAI for metric validation. The case-study is supported through experimental validation. The analysis proves the efficacy of EXAI in health setups that envisions real-life model deployments in a wide range of clinical applications.

ABV-CoViD: An Ensemble Forecasting Model to Predict Availability of Beds and Ventilators for COVID-19 Like Pandemics

Journal

Journal NameIEEE Access

Title of PaperABV-CoViD: An Ensemble Forecasting Model to Predict Availability of Beds and Ventilators for COVID-19 Like Pandemics

PublisherIEEE

Volume Number10

Page Number74131 - 74151

Published YearJuly 2022

ISSN/ISBN No978-3-16-148410-0

Indexed INScopus, Web of Science

Abstract

Recently, healthcare stakeholders have orchestrated steps to strengthen and curb the COVID-19 wave. There has been a surge in vaccinations to curb the virus wave, but it is crucial to strengthen our healthcare resources to fight COVID-19 and like pandemics. Recent researchers have suggested effective forecasting models for COVID-19 transmission rate, spread, and the number of positive cases, but the focus on healthcare resources to meet the current spread is not discussed. Motivated from the gap, in this paper, we propose a scheme, ABV-CoViD ( A vailibility of B eds and V entilators for COVID -19 patients), that forms an ensemble forecasting model to predict the availability of beds and ventilators (ABV) for the COVID-19 patients. The scheme considers a region-wise demarcation for the allotment of beds and ventilators (BV), termed resources, based on region-wise ABV and COVID-19 positive patients (inside the hospitals occupying the BV resource). We consider an integration of artificial neural network (ANN) and auto-regressive integrated neural network (ARIMA) model to address both the linear and non-linear dependencies. We also consider the effective wave spread of COVID-19 on external patients (not occupying the BV resources) through a θ - ARNN model, which gives us long-term complex dependencies of BV resources in the future time window. We have considered the COVID-19 healthcare dataset on 3 USA regions (Illinois, Michigan, and Indiana) for testing our ensemble forecasting scheme from January 2021 to May 2022. We evaluated our scheme in terms of statistical performance metrics and validated that ensemble methods have higher accuracy. In simulation, for linear modelling, we considered the ARIMA(1,0,12) model, and N8−3−2 model for ANN modelling. We considered the θ−ARNN (12,6) forecasting. On a population of 2,93,90,897, the obtained mean absolute error (MAE) on average for 3 regions is 170.5514. The average root means squa...

Intensify Cloud Security and Privacy Against Phishing Attacks

Journal

Journal NameECS transactions

Title of PaperIntensify Cloud Security and Privacy Against Phishing Attacks

PublisherIoP science

Volume Number107

Page Number1387

Published YearJune 2021

ISSN/ISBN No1938-6737

Indexed INScopus

Abstract

The world of computation has shifted from centralized (client-server, not web-based) to distributed systems during the last three decades. We are now reverting to virtual centralization, i.e., Cloud Computing (CC). In the world of computation, the location of data and processes makes all the difference. A person has complete control over the data and operations in their computer. On the other side, CC involves a vendor providing service and data upkeep. At the same time, the client/customer is ignorant of where the processes are operating or where the data is kept. As a result, the client does not influence it and doesn't have the right to do it. When it comes to data security in cloud computing, the vendor must guarantee service level agreements (SLAs) to persuade the client. As a result, the SLA must define several degrees of security and their complexity depending on the benefits for the client to comprehend the security rules in place. Phishing is a social engineering assault that is frequently used to obtain user information, such as login passwords and credit card details. It happens when an attacker poses as a trustworthy entity and tricks the victim into opening an e-mail, instant message, or text message. In this research paper, the methodology that tries to identify the phishing attack in the cloud eco-system has been explored and mentioned. The approach used here classifies the malicious and non-malicious URLs.

SLAMMP Framework for Cloud Resource Management and Its Impact on Healthcare Computational Techniques

Journal

Journal NameInternational Journal of E-Health and Medical Communications

Title of PaperSLAMMP Framework for Cloud Resource Management and Its Impact on Healthcare Computational Techniques

PublisherIGI Global

Volume Number12

Page Number1-31

Published YearApril 2021

ISSN/ISBN No1947-3168

Indexed INScopus, Web of Science

Abstract

Technology such as cloud computing(CC) is constantly evolving and being adopted by the industries to manage their data and tasks. CC provides the resources for managing the tasks of the cloud users. The acceptance of the CC in healthcare industries is proven to be more cost-effective and convenient. CC manager has to manage the resources to provide services to the end-users of the healthcare sector. The SLAMMP framework discussed here shows how the resources are managed by using the concept of reinforcement learning (RL) and LSTM (long short-term memory) for monitoring and prediction of the cloud resources for healthcare organizations. The task(s) pattern and anti-pattern scenarios have been observed using HMM (hidden Markov model). These patterns will tune the SLA parameters (service level agreement) using blockchain-based smart contracts (SC). The result discussed here indicates that the variations in the cloud resource demand will be handled carefully using the SLAMMP framework. From the result obtained, it is identified that SLAMMP performs well with the parameter used here.

Preserving SLA Parameters for Trusted IaaS Cloud: An Intelligent Monitoring Approach

Journal

Journal NameRecent Patents on Engineering

Title of PaperPreserving SLA Parameters for Trusted IaaS Cloud: An Intelligent Monitoring Approach

PublisherBentham Science Publishers

Volume Number14

Page Number530-540

Published YearDecember 2020

ISSN/ISBN No872-2121

Indexed INScopus

Abstract

Background: Cloud Computing (CC) provides an open computing feature where a large number of customers can interact with the cloud services hosted by the cloud service providers (CSP) for their business requirements. Objectives: Service Level Agreements (SLAs) are legal agreements between an enterprise and the CSP. To increase the confidence of the customer towards their CSP(s) will be determined by SLA fulfillment and possible actions should be adopted to minimize the violation of the SLAs. Which in turn will also lead to the revenue generation towards CSP. When SLA is breached by the customer, penalties are imposed; whereas SLA breach by the CSP will affect the trust of its valuable customers. Methods: Identify the metrics with respect to the resources and its Service level agreements (SLAs) and measure (monitoring) this to maintain its value and if the value is less as per the SLAs (threshold values) then take precautionary actions to maintain this. Results: The results indicate the present status of the resource utilization of the CPU and categories into three levels and based upon this take necessary actions to maintain the SLAs. Conclusion: The methodology discussed herein this paper can be used for monitoring the SLA parameter and to avoid the circumstances that can lead to breaching of the SLA(s).

Monitoring IaaS Cloud for Healthcare Systems Healthcare Information Management and Cloud Resources Utilization

Journal

Journal NameInternational Journal of E-Health and Medical Communications

Title of PaperMonitoring IaaS Cloud for Healthcare Systems Healthcare Information Management and Cloud Resources Utilization

PublisherIGI Global

Volume Number11

Page Number54-70

Published YearSeptember 2020

ISSN/ISBN No1947-3168

Indexed INScopus, Web of Science

Abstract

Healthcare functionality is enriched by cloud services which offers a perspective for broad integration and interoperability. Cloud-based facilities support healthcare systems to remain connected to remote access devices to various tasks and information. The healthcare actors should have an understanding of the risks and benefits associated with the usage of Cloud Computing resources utilization. Also, they must launch an appropriate contract-based relationship between the Cloud Service Providers and the actors of healthcare systems by means of Service Level Agreements (SLAs). The variation in both demand and supply within the healthcare information affects the use of information technology. Hence, monitoring resources can play an important role in accommodating the healthcare data. To deal with the aforementioned problems; reinforcement learning mechanisms along with the metrics has been used and experimented with the various dynamics of workload to deliver services with quality assurance. Article Pr

Monitoring and Prediction of SLA for IoT based Cloud

Journal

Journal NameScalable Computing: Practice and Experience

Title of PaperMonitoring and Prediction of SLA for IoT based Cloud

PublisherSCPE

Volume Number21

Page Number349-357

Published YearAugust 2020

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science

Abstract

Internet of Things (IoT) and cloud computing are the expertise captivating the technology. The most astonishing thing is their interdependence. IoT deals with the production of an additional amount of information that requires transmission of data, storage, and huge infrastructural processing power, posing a solemn delinquent. This is where cloud computing fits into the scenario. Cloud computing can be treated as the utility factor nowadays and can be used by pay as you go manner. As a cloud is a multi-tenant approach, and the resources will be used by multiple users. The cloud resources are required to be monitored, maintained, and configured and set-up as per the need of the end-users. This paper describes the mechanisms for monitoring by using the concept of reinforcement learning and prediction of the cloud resources, which forms the critical parts of cloud expertise in support of controlling and evolution of the IT resources and has been implemented using LSTM. The resource management system coordinates the IT resources among the cloud provider and the end users; accordingly, multiple instances can be created and managed as per the demand and availability of the support in terms of resources. The proper utilization of the resources will generate revenues to the provider and also increases the trust factor of the provider of cloud services. For experimental analysis, four parameters have been used i.e. CPU utilization, disk read/write throughput and memory utilization. The scope of this research paper is to manage the Cloud Computing resources during the peak time and avoid the conditions of the over and under-provisioning proactively.

Influence of Montoring: Fog and Edge Computing

Journal

Journal NameScalable Computing: Practice and Experience:Influence of Motoring: Fog and Edge Computing

Title of PaperInfluence of Montoring: Fog and Edge Computing

PublisherSCPE

Volume Number20

Page Number365–376

Published YearMay 2019

ISSN/ISBN No1895-1767

Indexed INScopus, Web of Science, UGC List

Abstract

The evolution of the Internet of Things (IoT) has augmented the necessity for Cloud, edge and fog platforms. The chief benefit of cloud-based schemes is they allow data to be collected from numerous services and sites, which is reachable from any place of the world. The organizations will be benefited by merging the cloud platform with the on-site fog networks and edge devices and as result, this will increase the utilization of the IoT devices and end users too. The network traffic will reduce as data will be distributed and this will also improve the operational efficiency. The impact of monitoring in edge and fog computing can play an important role to efficiently utilize the resources available at these layers. This paper discusses various techniques involved for monitoring for edge and fog computing and its advantages. The paper ends with a case study to demonstarte the need of monitoring in fog and edge in the healthcare system.

Inspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

Journal

Journal NameProcedia Computer Science: Inspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

Title of PaperInspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

PublisherElsevier

Volume Number132

Page Number1280-1289

Published YearMay 2018

ISSN/ISBN No1877-0509

Indexed INScopus, UGC List

Abstract

Cloud Computing is an example of the distributed system where the end user has to connect to the services given by the cloudwhich is maintained by the cloud service provider (CSP). The user has to have certain trust upon the cloud as finally, the end userhas to migrate the jobs into the cloud of some third party, as the on-premises data or sources are to be kept across the globe,theCSP have to mai

Reducing the Operative Resource Monitoring Mechanism Overhead in Cloud: An IaaS Perspective

Conference

Title of PaperReducing the Operative Resource Monitoring Mechanism Overhead in Cloud: An IaaS Perspective

PublisherElsevier

Page Number-

Published YearApril 2018

ISSN/ISBN No1556-5068

Indexed INUGC List

Abstract

Today we are in the era of distributed system and cloud computing is the best example for the same. Resource management is an important issue in cloud computing, we need to keep track of the available resources in cloud, so that we can give services to user to fulfil their requirement. Which leads in helping to generate maximum revenue, lower power consumption, carbon emission and ultimately leads to green computing. So with the help of resource monitoring we can get the data about how, when, in what amount of resources for a particular cloud and the user. With effective resource monitoring, by minimizing some monitoring units we can reduce the cost of monitoring in terms of computation and power consumption. Our main objective is to reduce the monitoring technique, so that the amount of computation and power consumption can be saved which will lead to smart and green computing. In this research paper we are discussing about the algorithm that will reduce the activation period of the monitoring and also we had discussed the Hidden Markov Model (HMM) for the decision making in monitoring aspect.

Chronicles of Assaults at Cloud Computing and Its Influence at an IaaS

Conference

Title of PaperChronicles of Assaults at Cloud Computing and Its Influence at an IaaS

Proceeding NameProceedings of 3rd International Conference on Internet of Things and Connected Technologies (ICIoTCT), 2018 held at Malaviya National Institute of Technology, Jaipur (India) on March 26-27, 2018

PublisherElsevier SSRN

Author NameElsevier SSRN

OrganizationMalaviya National Institute of Technology, Jaipur (India)

Published YearMarch 2018

ISSN/ISBN No1556-5068

Indexed INUGC List

Inspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

Journal

Journal NameElsevier Procedia:Inspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

Title of PaperInspection of Trust Based Cloud Using Security and Capacity Management at an IaaS Level

PublisherElsevier

Volume Number132

Page Number1280-1289

Published YearFebruary 2018

ISSN/ISBN No1877-0509

Indexed INScopus, UGC List

Abstract

Cloud Computing is an example of the distributed system where the end user has to connect to the services given by the cloud which is maintained by the cloud service provider (CSP). The user has to have certain trust upon the cloud as finally, the end user has to migrate the jobs into the cloud of some third party, as the on-premises data or sources are to be kept across the globe, the CSP have to maintain the trust level so that the end user can opt for the services given by the certain trusted Cloud. Ultimately there will be various elements of levels happening at the CSP side to maintain the trust level, like the safety features for security has to be identified, federation related or Virtual Machine migration techniques status has to be always monitored to maintain and avoid certain uncertainty which will affect the trust level of the cloud, which can lead to the compromised situation in between the end user and CSP, as a result the trust value will decrease, In this paper we are proposing a techniques where the security features and conditions for load balancing monitoring technique with proactive actions will be analyzed to maintain the specified trust level.

Efficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

Book Chapter

Book NameFuture Internet Technologies and Trends:Efficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

PublisherSringer

Author NameSringer

Page Number47-55

Chapter TitleEfficient Resource Monitoring and Prediction Techniques in an IaaS Level of Cloud Computing: Survey

Published YearJanuary 2018

ISSN/ISBN No1867-8211

Indexed INScopus, UGC List

Abstract

In this paper, we have discussed about the various techniques through which the cloud computing monitoring and prediction can be achieved, This paper provides the survey of the techniques related to monitoring and prediction for the efficient usages of the resources available at the IaaS level of cloud. As cloud provides the services, which are elastic, scalable or highly dynamic in nature, which binds us to make the correct usages of the resources, but in real situations the (Cloud Service Provider)CSP’s has to face the situation of under provisioning and over provisioning, where the resources are not fully utilized and being wasted, though this is the survey paper, it ends up with the proposed model where both the concepts of the Monitoring and Prediction will be combined together to give a better vision of the future resource demand in IaaS layer of Cloud Computing.

Capacity Planning Through Monitoring of Context Aware Tasks at IaaS Level of Cloud Computing

Book Chapter

Book NameFuture Internet Technologies and Trends:Capacity Planning Through Monitoring of Context Aware Tasks at IaaS Level of Cloud Computing

PublisherSringer

Author NameSringer

Page Number66-74

Chapter TitleCapacity Planning Through Monitoring of Context Aware Tasks at IaaS Level of Cloud Computing

Published YearJanuary 2018

ISSN/ISBN No1867-8211

Indexed INScopus, UGC List

Abstract

Cloud Computing is the exercise of using a network of remote servers held on the Internet to store, manage, and process data which have the characteristics as an elasticity, scalability or scalable resource sharing managed by the resource management. Even the growing demand of cloud computing has radically increased the energy consumption of the data centres, which is a critical scenario in the er

Exhausting Autonomic Techniques for Meticulous Consumption of Resource at an IaaS Layer of Cloud Computing

Book Chapter

Book NameFuture Internet Technologies and Trends:Exhausting Autonomic Techniques for Meticulous Consumption of Resource at an IaaS Layer of Cloud Computing

PublisherSpringer,LNICST, volume 220

Author NameSpringer

Page Number37-46

Chapter TitleExhausting Autonomic Techniques for Meticulous Consumption of Resource at an IaaS Layer of Cloud Computing

Published YearJanuary 2018

ISSN/ISBN No1867-8211

Indexed INScopus, UGC List

Abstract

Internet-based computing has provided lots of flexibility with respect to the usages of resources, as per the current demand of the users, and granting them the said resources has its own benefits if given in proper manner i.e. exactly what the user has asked. In this paper, the autonomic computing concepts have been discussed which will be very useful for the better utilization of the resources a

A comprehensive survey on machine learning techniques in opportunistic networks: Advances, challenges and future directions

Journal

Journal NamePervasive and Mobile Computing

Title of PaperA comprehensive survey on machine learning techniques in opportunistic networks: Advances, challenges and future directions

PublisherElsevier

Volume Number100

Page Number101917

Published YearMarch 2024

ISSN/ISBN No1873-1589

Indexed INScopus, Web of Science

Abstract

Machine Learning (ML) is growing in popularity and is applied in numerous fields to solve complex problems. Opportunistic Networks are a type of Ad-hoc Network where a contemporaneous path does not always exist. So, forwarding methods that assume the availability of contemporaneous paths does not work. ML techniques are applied to resolve the fundamental problems in Opportunistic Networks, including contact probability, link prediction, making a forwarding decision, friendship strength, and dynamic topology. The paper summarises different ML techniques applied in Opportunistic Networks with their benefits, research challenges, and future opportunities. The study provides insight into the Opportunistic Networks with ML and motivates the researcher to apply ML techniques to overcome various challenges in Opportunistic Networks.

A case study on the estimation of sensor data generation in smart cities and the role of opportunistic networks in sensor data collection

Journal

Journal NamePeer-to-Peer Networking and Applications

Title of PaperA case study on the estimation of sensor data generation in smart cities and the role of opportunistic networks in sensor data collection

PublisherElsevier

Volume Number17

Page Number337-357

Published YearJanuary 2024

ISSN/ISBN No1936-6450

Indexed INScopus, Web of Science

Abstract

Smart cities rely on real-time sensor data to improve services and quality of life. However, the rapid growth of sensor data poses challenges in transmission, storage, and processing. This paper presents a case study on estimating sensor data generation and the role of Opportunistic Networks (OppNets) in data collection in Ahmedabad and Gandhinagar, India. We highlight the challenges of managing large amounts of sensor data, particularly in densely populated cities. We propose OppNets as a promising solution, as they can leverage the mobility of devices to relay data in a distributed manner. We present a detailed analysis of sensor requirements and data generation for different smart city applications and discuss the potential benefits of OppNets for smart city data collection. Our study shows that Ahmedabad and Gandhinagar require approximately 4.6 million and 1.3 million sensors, producing an estimated 2702 Terabytes and 704 Terabytes of sensor data daily, respectively.

Coverage, Capacity and Cost Analysis of 4G-LTE and 5G Networks: A Case Study of Ahmedabad and Gandhinagar

Conference

Title of PaperCoverage, Capacity and Cost Analysis of 4G-LTE and 5G Networks: A Case Study of Ahmedabad and Gandhinagar

Proceeding NameFuturistic Trends in Networks and Computing Technologies: Select Proceedings of Fourth International Conference on FTNCT 2021

PublisherSpringer Nature

Author NameJay Gandhi and Zunnun Narmawala

Year , VenueNovember 2022 , Nirma University

Page Number25-38

ISSN/ISBN No978-981-19-5037-7

Indexed INScopus

Abstract

The prediction of future ten years shows exponential growth in wireless connections, high-speed Internet and data demands. Mobile network operators (MNOs) need to provide essential capacity for more than 100 billion connections in the global mobile communications network. The contribution of this paper is the analysis of the coverage, capacity and cost requirement of 4G-LTE and 5G networks across the Ahmedabad and Gandhinagar cities for the period of 2019–2029. We forecast the number of 4G-LTE and 5G subscribers and their data demands over the years. To accomplish such capacity requirement and to ensure the coverage across the cities, various radio propagation models are used to calculate the base station site requirement. The published data on networks deployment cost for various scenario (rural, urban, suburban, dense urban) are used to evaluate capital expenditure (CAPEX) and operational expenditure (OPEX) cost. The key findings of the study are as follows: (a) 4G-LTE is insufficient to provide high-speed data without acquiring additional spectrum bandwidth (b) 5G technologies can provide significant coverage and capacity even in the dense urban area (c) The cost of deploying 5G infrastructure is almost three times higher than the 4G-LTE.

Log Transformed Coherency Matrix for Differentiating Scattering Behaviour of Oil Spill Emulsions Using SAR Images

Journal

Journal NameMathematics

Title of PaperLog Transformed Coherency Matrix for Differentiating Scattering Behaviour of Oil Spill Emulsions Using SAR Images

PublisherMDPI

Volume Number10

Page Number1697

Published YearMay 2022

Indexed INScopus, Web of Science

Abstract

Oil spills on the ocean surface are a serious threat to the marine ecosystem. Automation of oil spill detection through full/dual polarimetric Synthetic Aperture Radar (SAR) images is considered a good aid for oil spill disaster management. This paper uses the power of log transformation to discern the scattering behavior more effectively from the coherency matrix (T3). The proposed coherency matrix is tested on patches of the clean sea surface and four different classes of oil spills, viz. heavy sedimented oil, thick oil, oil-water emulsion, fresh oil; by analyzing the entropy (H), anisotropy (A), and mean scattering angle alpha (𝛼 ), following the H/A/𝛼 decomposition. Experimental results show that not only does the proposed T3 matrix differentiate between Bragg scattering of the clean sea surface from a random scattering of thick oil spills but is also able to distinguish between different emulsions of oil spills with water and sediments. Moreover, unlike classical T3, the proposed method distinguishes concrete-like structures and heavy sedimented oil even though both exhibit similar scattering behavior. The proposed algorithm is developed and validated on the data acquired by the UAVSAR full polarimetric L band SAR sensor over the Gulf of Mexico (GOM) region during the Deepwater Horizon (DWH) oil spill accident in June 2010.

A Survey on Green Internet of Things

Conference

Title of PaperA Survey on Green Internet of Things

Proceeding Name2018 Fourteenth International Conference on Information Processing (ICINPRO)

Author NameKrishna Shah, Zunnun Narmawala

Published YearMay 2020

Indexed INScopus

A systematic review on scheduling public transport using IoT as tool

Journal

Journal NameAdvances in Intelligent Systems and Computing

Title of PaperA systematic review on scheduling public transport using IoT as tool

PublisherSpringer

Volume Number670

Page Number39-48

Published YearJuly 2018

ISSN/ISBN No21945357

Indexed INScopus, UGC List

Abstract

Public transport can play an important role in reducing usage of private vehicles by individuals which can, in turn, reduce traffic congestion, pollution, and usage of fossil fuel. But, for that public transport needs to be reliable. People should not have to wait for the bus for a long time without having any idea when the bus will come. Further, people should get a seat in the bus. To ensure this, efficiently and accurately scheduling and provisioning of buses is of paramount importance. In fact, nowadays buses are scheduled as per the need. But these scheduling is being done manually in India. Our survey shows that there are many algorithms proposed in the literature for scheduling and provisioning of buses. There is a need to tailor these algorithms for Indian scenario. We present a brief overview of these algorithms in this paper. We also identify open issues which need to be addressed.

Proximity and community aware heterogeneous human mobility (P-CAHM) model for mobile social networks (MSN)

Journal

Journal NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

Title of PaperProximity and community aware heterogeneous human mobility (P-CAHM) model for mobile social networks (MSN)

PublisherSpringer

Volume Number220

Page Number137-146

Published YearJanuary 2018

ISSN/ISBN No18678211

Indexed INScopus, UGC List

Abstract

Peer-to-peer opportunistic communication between mobile devices carried by humans without using any infrastructure is largely unexploited. The encounter pattern of the devices depends on human mobility pattern which is governed by human social behaviour. Individuals belong to multiple communities. These social ties significantly affect humans’ movement pattern. Traditional mobility models, such as

A comparative study of various community detection algorithms in the mobile social network

Conference

Title of PaperA comparative study of various community detection algorithms in the mobile social network

Proceeding NameNUiCONE 2015 - 5th Nirma University International Conference on Engineering

PublisherIEEE

Author NameAnkit Didwania

OrganizationNirma University

Year , VenueNovember 2015 , Nirma University

Page Number1-6

ISSN/ISBN No978-1-4799-9991-0

Indexed INScopus

Abstract

Mobile social network is a type of delay tolerant network of mobile devices in which there is no end-to-end path available in advance for communication. It works on the principle of a store-carry-forward mechanism. The community is a very useful property of the mobile social network as humans are social animals and they like to live in a community. Such community structure enables efficient communication between devices carried by humans without any infrastructure. We have analyzed various community detection methods and identified those suitable for mobile social network. We have also analyzed various existing distributed community detection algorithms in mobile social networks based on important parameters like complexity and type of community detected. Such analysis will help in discovering strengths and shortcomings of various existing algorithms. As the mobile social network is self-organizing real network working on highly resource constraint mobile devices, it is necessary to enable each mobile device to detect its own community with minimal information, computation and space requirements. This is a very challenging task and very little work is done in it. So there is an immense opportunity available for research in this area.

Community Aware Heterogeneous Human Mobility (CAHM): Model and analysis

Journal

Journal NamePervasive and Mobile Computing

Title of PaperCommunity Aware Heterogeneous Human Mobility (CAHM): Model and analysis

PublisherElsevier

Volume Number21

Page Number119-132

Published YearAugust 2015

ISSN/ISBN No1574-1192

Indexed INScopus, Web of Science, UGC List

Abstract

Community Aware Heterogeneous Human Mobility Model (CAHM) is based on Heterogeneous Human Walk (HHW) Yang et al. (2010) mobility model. CAHM achieves heterogeneous local popularity as observed in real mobility traces which HHW fails to achieve. It also incorporates following additional properties of human mobility: preference of nearby locations, speed as a function of distance to be traveled and

Scalable micro-blogging in mobile social communities

Conference

Title of PaperScalable micro-blogging in mobile social communities

Proceeding Name2015 IEEE Region 10 Symposium, TENSYMP 2015

PublisherIEEE

OrganizationIEEE

Year , VenueMay 2015 , GIFT City, Gandhinagar

Page Number66-69

ISSN/ISBN No978-1-4799-1782-2

Indexed INScopus

Abstract

Micro-blogging in Mobile Social Network can be very successful because of spatiotemporal properties of user interests and generated messages. Users can follow their interests and receive messages of their interests without getting overwhelmed instead of having to identify and follow users having similar interests. We propose a distributed and scalable micro-blogging protocol...

Viral spread in mobile social network using network coding

Conference

Title of PaperViral spread in mobile social network using network coding

Proceeding Name11th IEEE India Conference: Emerging Trends and Innovation in Technology, INDICON 2014

PublisherIEEE

OrganizationIEEE Pune Section

Year , VenueDecember 2014 , Pune

ISSN/ISBN No2325-9418

Indexed INScopus

Abstract

Delay tolerant ad hoc network between mobile devices is a promising paradigm which can avoid significant cost of cellular data transfer. Many interesting applications such as peer-to-peer file transfer, micro-blogging etc. are possible on this network. We propose viral spread (Many-to-all broadcast) for such networks. Viral spread can be useful to variety of such applications as well as...

Improved heterogeneous human walk mobility model with hub and gateway identification

Journal

Journal NameLecture Notes in Computer Science

Title of PaperImproved heterogeneous human walk mobility model with hub and gateway identification

PublisherSpringer

Volume Number8314

Page Number469-483

Published YearJanuary 2014

ISSN/ISBN No03029743

Indexed INScopus, UGC List

Abstract

Heterogeneous Human Walk (HHW) model [1] mimics human mobility and is based on two important properties of social network: overlapping community structure and heterogeneous popularity. But, it does not produce heterogeneous local popularities of nodes in a community as observed in real mobility traces. Further, it does not consider Levy walk nature of human mobility which has significant impact on performance of protocols. We propose Improved Heterogeneous Human Walk (IHHW) model that correctly produces heterogeneous local popularities and also incorporates Levy walk nature of human mobility within overlapping community structure. As popular nodes are very useful for data dissemination, we also propose theoretical methods to identify popular nodes within community (hubs) and in entire network (gateways) from overlapping community structure itself. These nodes can act as hubs/gateways till overlapping community structure does not change. Our methods eliminate the need to identify and change these nodes dynamically when network is operational.

Performance enhancement of multimedia traffic over wireless ad hoc networks using network coding

Conference

Title of PaperPerformance enhancement of multimedia traffic over wireless ad hoc networks using network coding

Proceeding Name3rd Nirma University International Conference on Engineering, NUiCONE 2012

PublisherIEEE

Author NameTwisa Mehta

OrganizationNirma University

Year , VenueDecember 2012 , Nirma University

Page Number1-6

ISSN/ISBN No2375-1282

Indexed INScopus

Abstract

Network coding is a new area of networking, in which data is processed inside the network to increase throughput, to balance traffic load and to save bandwidth of a network. Network Coding performs well in lossy wireless networks in both multicast and broadcast scenarios. Even in wireless networks with low density of nodes network coding performs well using its multi-copy packet transmission scheme. Because of Wireless Ad hoc Network's ease in configuration and quick deployment, such networks are widely preferred for instant data transmission for many applications including multimedia. But the available bandwidth for Wireless Ad hoc Networks fails to meet the requirements of multimedia video data transmission and results in packets loss, delay as well as decreases the quality of transmitted multimedia data. So, to overcome Wireless Ad hoc Networks limitations for multimedia video (video considered in MPEG 4 format) transmission, a variant of Network Coding that is Random Linear Network Coding with Multi Generation Mixing is employed by network nodes. So, in this work, each sender node encodes packet using RLNC with Multi Generation Mixing (MGM) with the aim to provide more protection to I (Intra frame of MPEG 4 video traffic) frames in order to minimize multiplicative loss by incurring slight delay in transmission. In this work, simulations are carried out by changing protocol parameters and its effects on network parameters and performance parameters are analyzed. Simulation results confirm with intuition that the performance get enhanced using Random Linear Network Coding with MGM.

A survey on MPEG-4 streaming using network coding in wireless networks

Conference

Title of PaperA survey on MPEG-4 streaming using network coding in wireless networks

Proceeding Name3rd Nirma University International Conference on Engineering, NUiCONE 2012

PublisherIEEE

Author NameRahul Shrimali

OrganizationNirma University

Year , VenueDecember 2012 , Nirma University

ISSN/ISBN No2375-1282

Indexed INScopus

Abstract

he streaming of real-time audio/video data is very challenging because of the time-varying and unreliable wireless channels, video content characteristics, limited bandwidth, dynamic topology, heterogeneous and distributed environment and high packet loss rate because of wireless interference and channel fading. Because of such open issues present in wireless networks, it is very difficult to satisfy the requirements of audio/video streaming applications such as low delay, low packet loss, jitter control etc. In such scenarios of opportunistic networks where real time data is being streamed from server node to client node, Network Coding and its variants can be used by such nodes to meet different requirements. Network coding changes the role of such multimedia nodes from store and forward to encode data packets. Encoding process includes mathematical operations on data packets. This survey paper has considered number of speculative and practical approaches and cases where network coding or its variant applied either fully or partially on multimedia traffic with the aim to improve performance and to provide protection against packet losses. This review has mainly focused on the opportunity of performance enhancement of MPEG-4 traffic over Wireless Network using Random Linear Network Coding (RLNC) with Multi Generation Mixing (MGM). Using Multi Generation Mixing, packets of greater importance has got more protection, less loss, more reconstruction and recovery of real time data.

Review on variants of network coding in wireless ad-hoc networks`

Conference

Title of PaperReview on variants of network coding in wireless ad-hoc networks`

Proceeding NameNirma University International Conference on Engineering: Current Trends in Technology, NUiCONE 2011

PublisherIEEE

Author NameJitendra Bhatia

OrganizationNirma University

Year , VenueDecember 2011 , Nirma University

ISSN/ISBN No2375-1282

Indexed INScopus

Abstract

Network coding is a technique in which node is allowed to combine and encode one or more input packets into encoded packets instead of directly forwarding them. It increases throughput and delivery ratio. In this paper, we review basic linear network coding variants with their performance benefits and theoretical results. In practical setting, linear network coding requires central authority to control generation of meaningful encoding coefficients and for coordination between the nodes of network. In wireless network, due to dynamic nature of nodes and heterogeneity of network, centralized approach is not suitable. So, distributed approach should be used. We reviewed distributed linear network coding technique named as Random Linear Network Coding (RLNC). We also reviewed RLNC variants called Generation-by-Generation RLNC and RLNC with Multi Generation Mixing (MGM). We also reviewed the options to recover the lost encoded packets in networks where losses prevent efficient propagation of sender packets. MGM increases the decodable rate of encoded packets. We compared the performance of Generation-by-Generation Network Coding and Network coding with MGM.

Survey on multimedia transmission using network coding over wireless networks

Conference

Title of PaperSurvey on multimedia transmission using network coding over wireless networks

Proceeding NameSurvey on multimedia transmission using network coding over wireless networks

PublisherIEEE

Author NameTwisa Mehta

OrganizationNirma University

Year , VenueDecember 2011 , Nirma University

Page Number1-6

ISSN/ISBN No2375-1282

Indexed INScopus

Abstract

These days the growth of multimedia applications (e.g. VOIP, teleconferencing etc) over Wireless Networks is on its peak and will further increase with the time. The available bandwidth for Wireless Networks fails to meet the requirements which result in high packet loss of multimedia data, delay in transmission and decreases the quality of multimedia applications. So many approaches are proposed for multimedia streams over Wireless Networks to deal with packet loss and delay over time varying bandwidth. Network Coding is one of the many proposed approaches. This approach works well for transmission of multimedia traffic in a distributed lossy environment where only partial or uncertain information is available for decision making. Network Coding technique allows an intermediate node to combine the data (packets) from different input links and sends encoded data on its output links. So, by employing appropriate variant of Network Coding scheme at each intermediate node (linear combination of input data with the concept of generation) can achieve the network capacity. This paper presents the survey of various papers in which a Network Coding technique is applied on multimedia transmission over Wireless Networks.

MIDTONE: Multicast in delay tolerant networks

Conference

Title of PaperMIDTONE: Multicast in delay tolerant networks

Proceeding Name4th International Conference on Communications and Networking in China, CHINACOM 2009

PublisherIEEE

Author NameZunnun Narmawala

OrganizationXidian University and Xi'an Jiaotong University.

Year , VenueAugust 2009 , Xian, China

Page Number1-8

ISSN/ISBN No978-1-4244-4337-6

Indexed INScopus

Abstract

Delay Tolerant Networks (DTN) are sparse ad hoc networks in which no contemporaneous path exists between any two nodes in the network most of the time. Due to non-availability of end-to-end paths, multicast protocols of traditional networks fail in DTN because they try to find connected multicast graph between source and destination nodes before forwarding data packets. Routing protocols proposed for DTN follow `store-carry-forward' paradigm in which two nodes exchange messages with each other only when they come into contact. In the process, `single-copy' schemes maintain only one copy of the message in the network at any time and the forwarding node waits for the pre-determined next node to transfer the message. `Multi-copy' schemes spread more than one copy of the message opportunistically when nodes come into contact rather than waiting for pre-determined next node. While multi-copy schemes improve chances of delivery and work well even without any knowledge of the network, communication overhead and buffer occupancy are quite high for these schemes. We propose multi-copy routing protocol for multicasting in DTN called ldquoMulticast in Delay Tolerant Networks (MIDTONE)rdquo which uses `network coding' to reduce this overhead without compromising performance. Network coding is a mechanism in which nodes encode two or more incoming packets and forward encoded packets instead of forwarding them as it is. We also propose three novel packet purging schemes to drain packets out of the network which takes advantage of features of network coding to increase buffer efficiency. As simulation results suggest, our protocol achieves significantly less delay to deliver all the packets in infinite buffer case and higher delivery ratio in finite buffer case compared to non-network coding based multi-copy scheme. We also provide empirical relation to estimate optimal generation size for given network and performance parameters.

Effect of network coding on buffer management in wireless sensor network

Conference

Title of PaperEffect of network coding on buffer management in wireless sensor network

Proceeding NameISSNIP 2008 - Proceedings of the 2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing

PublisherIEEE

Author NameSunil Jardosh

OrganizationThe University of Melbourne

Year , VenueDecember 2008 , Sydney, Australia

ISSN/ISBN No978-1-4244-3822-8

Indexed INScopus

Abstract

In resource constrained wireless sensor networks (WSN), it is highly desirable to make efficient use of available buffer. Hence for the WSN designed for the monitoring applications, buffer management is a key requirement at sensor nodes. We have proposed an efficient buffer management scheme based on random linear network coding as the in-network processing on data packets. With buffer allocation from source to sink path, our scheme distributes the buffer requirement among the nodes on the path. Further in the case of a packet loss, the proposed scheme recovers packet from available information distributed on the path from source to sink. We have compared our scheme with conventional buffer management scheme. Results show that network coding based buffer management scheme has better buffer availability with less redundancy and reduced loss recovery cost.

Survey of applications of network coding in wired and wireless networks

Conference

Title of PaperSurvey of applications of network coding in wired and wireless networks

Proceeding NameProceedings of the 14th National Conference on Communications

Author NameZunnun Narmawala

OrganizationIIT Bombay

Year , VenueFebruary 2008 , IIT Bombay

Abstract

We review the basic works in the area of network coding and present a detailed survey of applications of network coding in network problems. It is shown that both in wired and wireless networks, multicast and broadcast protocols perform better with network coding. Even in unicast applications, network coding based protocols perform as well as the protocols without network coding. We also survey the applications of network coding in the domains of Peer-to-Peer Networks, Delay Tolerant Networks and Wireless Sensor Networks. It is apparent from the results that innovative use of network coding can improve the performance of a variety of applications in these domains. Finally, we also suggest a number of interesting open problems in these domains where network coding can be used.