Convergence of Deep Learning in Cyber-IoT Systems and Security

Rajdeep Chakraborty, PhD, is an assistant professor in the Department of Computer Science and Engineering, Netaji Subhash Engineering College, Kolkata, India. His fields of interest are mainly in cryptography and computer security. He was awarded the Adarsh Vidya Saraswati Rashtriya Puraskar, National Award of Excellence 2019 conferred by Glacier Journal Research Foundation, Anupam Ghosh, PhD, is a professor in the Department of Computer Science and Engineering, Netaji Subhash Engineering College, Kolkata, India. He has published more than 80 international papers in reputed international journals and conferences. His fields of interest are mainly in AI, machine learning, deep learning, image processing, soft computing, bioinformatics, IoT, and data mining. Jyotsna Kumar Mandal, PhD, has more than 30 years of industry and academic experience. His fields of interest are coding theory, data and network security, remote sensing & GIS-based applications, data compression error corrections, information security, watermarking, steganography and document authentication, image processing, visual cryptography, MANET, wireless and mobile computing/security, unify computing, chaos theory, and applications. S. Balamurugan, PhD, is the Director of Research and Development, Intelligent Research Consultancy Services (iRCS), Coimbatore, Tamilnadu, India. He is also Director of the Albert Einstein Engineering and Research Labs (AEER Labs), as well as Vice-Chairman, Renewable Energy Society of India (RESI), India. He has published 45 books, 200+ international journals/ conferences, and 35 patents.

• Preface xviiPart I: Various Approaches from Machine Learning to Deep Learning 11 Web-Assisted Noninvasive Detection of Oral Submucous Fibrosis Using IoHT 3Animesh Upadhyaya, Vertika Rai, Debdutta Pal, Surajit Bose and Somnath Ghosh1.1 Introduction 31.2 Literature Survey 61.2.1 Oral Cancer 61.3 Primary Concepts 71.3.1 Transmission Efficiency 71.4 Propose Model 91.4.1 Platform Configuration 91.4.2 Harvard Architectural Microcontroller Base Wireless Communication Board 101.4.2.1 NodeMCU ESP8266 Microcontroller 101.4.2.2 Gas Sensor 121.4.3 Experimental Setup 131.4.4 Process to Connect to Sever and Analyzing Data on Cloud 141.5 Comparative Study 161.6 Conclusion 17References 172 Performance Evaluation of Machine Learning and Deep Learning Techniques: A Comparative Analysis for House Price Prediction 21Sajeev Ram Arumugam, Sheela Gowr, Abimala, Balakrishna and Oswalt Manoj2.1 Introduction 222.2 Related Research 232.2.1 Literature Review on Comparing the Performance of the ML/DL Algorithms 232.2.2 Literature Review on House Price Prediction 252.3 Research Methodology 262.3.1 Data Collection 272.3.2 Data Visualization 272.3.3 Data Preparation 282.3.4 Regression Models 292.3.4.1 Simple Linear Regression 292.3.4.2 Random Forest Regression 302.3.4.3 Ada Boosting Regression 312.3.4.4 Gradient Boosting Regression 322.3.4.5 Support Vector Regression 332.3.4.6 Artificial Neural Network 342.3.4.7 Multioutput Regression 362.3.4.8 Regression Using Tensorflow—Keras 372.3.5 Classification Models 392.3.5.1 Logistic Regression Classifier 392.3.5.2 Decision Tree Classifier 392.3.5.3 Random Forest Classifier 412.3.5.4 Naïve Bayes Classifier 412.3.5.5 K-Nearest Neighbors Classifier 422.3.5.6 Support Vector Machine Classifier (SVM) 432.3.5.7 Feed Forward Neural Network 432.3.5.8 Recurrent Neural Networks 442.3.5.9 LSTM Recurrent Neural Networks 442.3.6 Performance Metrics for Regression Models 452.3.7 Performance Metrics for Classification Models 462.4 Experimentation 472.5 Results and Discussion 482.6 Suggestions 602.7 Conclusion 60References 623 Cyber Physical Systems, Machine Learning & Deep Learning— Emergence as an Academic Program and Field for Developing Digital Society 67P. K. Paul3.1 Introduction 683.2 Objective of the Work 693.3 Methods 693.4 Cyber Physical Systems: Overview with Emerging Academic Potentiality 703.5 ml and dl Basics with Educational Potentialities 723.5.1 Machine Learning (ML) 723.5.2 Deep Learning 733.6 Manpower and Developing Scenario in Machine Learning and Deep Learning 743.7 dl & ml in Indian Context 793.8 Conclusion 81References 824 Detection of Fake News and Rumors in the Social Media Using Machine Learning Techniques With Semantic Attributes 85Diganta Saha, Arijit Das, Tanmay Chandra Nath, Soumyadip Saha and Ratul Das4.1 Introduction 864.2 Literature Survey 874.3 Proposed Work 884.3.1 Algorithm 894.3.2 Flowchart 904.3.3 Explanation of Approach 914.4 Results and Analysis 924.4.1 Datasets 924.4.2 Evaluation 934.4.2.1 Result of 1st Dataset 934.4.2.2 Result of 2nd Dataset 944.4.2.3 Result of 3rd Dataset 944.4.3 Relative Comparison of Performance 954.5 Conclusion 95References 96Part II: Innovative Solutions Based on Deep Learning 995 Online Assessment System Using Natural Language Processing Techniques 101S. Suriya, K. Nagalakshmi and Nivetha S.5.1 Introduction 1025.2 Literature Survey 1035.3 Existing Algorithms 1085.4 Proposed System Design 1115.5 System Implementation 1155.6 Conclusion 120References 1216 On a Reference Architecture to Build Deep-Q Learning-Based Intelligent IoT Edge Solutions 123Amit Chakraborty, Ankit Kumar Shaw and Sucharita Samanta6.1 Introduction 1246.1.1 A Brief Primer on Machine Learning 1246.1.1.1 Types of Machine Learning 1246.2 Dynamic Programming 1286.3 Deep Q-Learning 1296.4 IoT 1306.4.1 Azure 1306.4.1.1 IoT on Azure 1306.5 Conclusion 1446.6 Future Work 144References 1457 Fuzzy Logic-Based Air Conditioner System 147Suparna Biswas, Sayan Roy Chaudhuri, Ayusha Biswas and Arpan Bhawal7.1 Introduction 1477.2 Fuzzy Logic-Based Control System 1497.3 Proposed System 1497.3.1 Fuzzy Variables 1497.3.2 Fuzzy Base Class 1547.3.3 Fuzzy Rule Base 1557.3.4 Fuzzy Rule Viewer 1567.4 Simulated Result 1577.5 Conclusion and Future Work 163References 1638 An Efficient Masked-Face Recognition Technique to Combat with COVID- 19 165Suparna Biswas8.1 Introduction 1658.2 Related Works 1678.2.1 Review of Face Recognition for Unmasked Faces 1678.2.2 Review of Face Recognition for Masked Faces 1688.3 Mathematical Preliminaries 1698.3.1 Digital Curvelet Transform (DCT) 1698.3.2 Compressive Sensing–Based Classification 1708.4 Proposed Method 1718.5 Experimental Results 1738.5.1 Database 1738.5.2 Result 1758.6 Conclusion 179References 1799 Deep Learning: An Approach to Encounter Pandemic Effect of Novel Corona Virus (COVID-19) 183Santanu Koley, Pinaki Pratim Acharjya, Rajesh Mukherjee, Soumitra Roy and Somdeep Das9.1 Introduction 1849.2 Interpretation With Medical Imaging 1859.3 Corona Virus Variants Tracing 1889.4 Spreading Capability and Destructiveness of Virus 1919.5 Deduction of Biological Protein Structure 1929.6 Pandemic Model Structuring and Recommended Drugs 1929.7 Selection of Medicine 1959.8 Result Analysis 1979.9 Conclusion 201References 20210 Question Answering System Using Deep Learning in the Low Resource Language Bengali 207Arijit Das and Diganta Saha10.1 Introduction 20810.2 Related Work 21010.3 Problem Statement 21510.4 Proposed Approach 21510.5 Algorithm 21610.6 Results and Discussion 21910.6.1 Result Summary for TDIL Dataset 21910.6.2 Result Summary for SQuAD Dataset 21910.6.3 Examples of Retrieved Answers 22010.6.4 Calculation of TP, TN, FP, FN, Accuracy, Precision, Recall, and F1 score 22110.6.5 Comparison of Result with other Methods and Dataset 22210.7 Analysis of Error 22310.8 Few Close Observations 22310.9 Applications 22410.10 Scope for Improvements 22410.11 Conclusions 224Acknowledgments 225References 225Part III: Security and Safety Aspects with Deep Learning 23111 Secure Access to Smart Homes Using Biometric Authentication With RFID Reader for IoT Systems 233K.S. Niraja and Sabbineni Srinivasa Rao11.1 Introduction 23411.2 Related Work 23511.3 Framework for Smart Home Use Case With Biometric 23611.3.1 RFID-Based Authentication and Its Drawbacks 23611.4 Control Scheme for Secure Access (CSFSC) 23711.4.1 Problem Definition 23711.4.2 Biometric-Based RFID Reader Proposed Scheme 23811.4.3 Reader-Based Procedures 24011.4.4 Backend Server-Side Procedures 24011.4.5 Reader Side Final Compute and Check Operations 24011.5 Results Observed Based on Various Features With Proposed and Existing Methods 24211.6 Conclusions and Future Work 245References 24612 MQTT-Based Implementation of Home Automation System Prototype With Integrated Cyber-IoT Infrastructure and Deep Learning–Based Security Issues 249Arnab Chakraborty12.1 Introduction 25012.2 Architecture of Implemented Home Automation 25212.3 Challenges in Home Automation 25312.3.1 Distributed Denial of Service and Attack 25412.3.2 Deep Learning–Based Solution Aspects 25412.4 Implementation 25512.4.1 Relay 25612.4.2 DHT 11 25712.5 Results and Discussions 26212.6 Conclusion 265References 26613 Malware Detection in Deep Learning 269Sharmila Gaikwad and Jignesh Patil13.1 Introduction to Malware 27013.1.1 Computer Security 27013.1.2 What Is Malware? 27113.2 Machine Learning and Deep Learning for Malware Detection 27413.2.1 Introduction to Machine Learning 27413.2.2 Introduction to Deep Learning 27613.2.3 Detection Techniques Using Deep Learning 27913.3 Case Study on Malware Detection 28013.3.1 Impact of Malware on Systems 28013.3.2 Effect of Malware in a Pandemic Situation 28113.4 Conclusion 283References 28314 Patron for Women: An Application for Womens Safety 285Riya Sil, Snatam Kamila, Ayan Mondal, Sufal Paul, Santanu Sinha and Bishes Saha14.1 Introduction 28614.2 Background Study 28614.3 Related Research 28714.3.1 A Mobile-Based Women Safety Application (I safe App) 28714.3.2 Lifecraft: An Android-Based Application System for Women Safety 28814.3.3 Abhaya: An Android App for the Safety of Women 28814.3.4 Sakhi—The Saviour: An Android Application to Help Women in Times of Social Insecurity 28914.4 Proposed Methodology 28914.4.1 Motivation and Objective 29014.4.2 Proposed System 29014.4.3 System Flowchart 29114.4.4 Use-Case Model 29114.4.5 Novelty of the Work 29414.4.6 Comparison with Existing System 29414.5 Results and Analysis 29414.6 Conclusion and Future Work 298References 29915 Concepts and Techniques in Deep Learning Applications in the Field of IoT Systems and Security 303Santanu Koley and Pinaki Pratim Acharjya15.1 Introduction 30415.2 Concepts of Deep Learning 30715.3 Techniques of Deep Learning 30815.3.1 Classic Neural Networks 30915.3.1.1 Linear Function 30915.3.1.2 Nonlinear Function 30915.3.1.3 Sigmoid Curve 31015.3.1.4 Rectified Linear Unit 31015.3.2 Convolution Neural Networks 31015.3.2.1 Convolution 31115.3.2.2 Max-Pooling 31115.3.2.3 Flattening 31115.3.2.4 Full Connection 31115.3.3 Recurrent Neural Networks 31215.3.3.1 LSTMs 31215.3.3.2 Gated RNNs 31215.3.4 Generative Adversarial Networks 31315.3.5 Self-Organizing Maps 31415.3.6 Boltzmann Machines 31515.3.7 Deep Reinforcement Learning 31515.3.8 Auto Encoders 31615.3.8.1 Sparse 31715.3.8.2 Denoising 31715.3.8.3 Contractive 31715.3.8.4 Stacked 31715.3.9 Back Propagation 31715.3.10 Gradient Descent 31815.4 Deep Learning Applications 31915.4.1 Automatic Speech Recognition (ASR) 31915.4.2 Image Recognition 32015.4.3 Natural Language Processing 32015.4.4 Drug Discovery and Toxicology 32115.4.5 Customer Relationship Management 32215.4.6 Recommendation Systems 32315.4.7 Bioinformatics 32415.5 Concepts of IoT Systems 32515.6 Techniques of IoT Systems 32615.6.1 Architecture 32615.6.2 Programming Model 32715.6.3 Scheduling Policy 32915.6.4 Memory Footprint 32915.6.5 Networking 33215.6.6 Portability 33215.6.7 Energy Efficiency 33315.7 IoT Systems Applications 33315.7.1 Smart Home 33415.7.2 Wearables 33515.7.3 Connected Cars 33515.7.4 Industrial Internet 33615.7.5 Smart Cities 33715.7.6 IoT in Agriculture 33715.7.7 Smart Retail 33815.7.8 Energy Engagement 33915.7.9 IoT in Healthcare 34015.7.10 IoT in Poultry and Farming 34015.8 Deep Learning Applications in the Field of IoT Systems 34115.8.1 Organization of DL Applications for IoT in Healthcare 34215.8.2 DeepSense as a Solution for Diverse IoT Applications 34315.8.3 Deep IoT as a Solution for Energy Efficiency 34615.9 Conclusion 346References 34716 Efficient Detection of Bioweapons for Agricultural Sector Using Narrowband Transmitter and Composite Sensing Architecture 349Arghyadeep Nag, Labani Roy, Shruti, Soumen Santra and Arpan Deyasi16.1 Introduction 35016.2 Literature Review 35316.3 Properties of Insects 35516.4 Working Methodology 35716.4.1 Sensing 35716.4.1.1 Specific Characterization of a Particular Species 35716.4.2 Alternative Way to Find Those Previously Sensing Parameters 35716.4.3 Remedy to Overcome These Difficulties 35816.4.4 Take Necessary Preventive Actions 35816.5 Proposed Algorithm 35916.6 Block Diagram and Used Sensors 36016.6.1 Arduino Uno 36116.6.2 Infrared Motion Sensor 36216.6.3 Thermographic Camera 36216.6.4 Relay Module 36216.7 Result Analysis 36216.8 Conclusion 363References 36317 A Deep Learning–Based Malware and Intrusion Detection Framework 367Pavitra Kadiyala and Kakelli Anil Kumar17.1 Introduction 36717.2 Literature Survey 36817.3 Overview of the Proposed Work 37117.3.1 Problem Description 37117.3.2 The Working Models 37117.3.3 About the Dataset 37117.3.4 About the Algorithms 37317.4 Implementation 37417.4.1 Libraries 37417.4.2 Algorithm 37617.5 Results 37617.5.1 Neural Network Models 37717.5.2 Accuracy 37717.5.3 Web Frameworks 37717.6 Conclusion and Future Work 379References 38018 Phishing URL Detection Based on Deep Learning Techniques 381S. Carolin Jeeva and W. Regis Anne18.1 Introduction 38218.1.1 Phishing Life Cycle 38218.1.1.1 Planning 38318.1.1.2 Collection 38418.1.1.3 Fraud 38418.2 Literature Survey 38518.3 Feature Generation 38818.4 Convolutional Neural Network for Classification of Phishing vs Legitimate URLs 38818.5 Results and Discussion 39118.6 Conclusion 394References 394Web Citation 396Part IV: Cyber Physical Systems 39719 Cyber Physical System—The Gen Z 399Jayanta Aich and Mst Rumana Sultana19.1 Introduction 39919.2 Architecture and Design 40019.2.1 Cyber Family 40119.2.2 Physical Family 40119.2.3 Cyber-Physical Interface Family 40219.3 Distribution and Reliability Management in CPS 40319.3.1 CPS Components 40319.3.2 CPS Models 40419.4 Security Issues in CPS 40519.4.1 Cyber Threats 40519.4.2 Physical Threats 40719.5 Role of Machine Learning in the Field of CPS 40819.6 Application 41119.7 Conclusion 411References 41120 An Overview of Cyber Physical System (CPS) Security, Threats, and Solutions 415Krishna Keerthi Chennam, Fahmina Taranum and Maniza Hijab20.1 Introduction 41620.1.1 Motivation of Work 41720.1.2 Organization of Sections 41720.2 Characteristics of CPS 41820.3 Types of CPS Security 41920.4 Cyber Physical System Security Mechanism—Main Aspects 42120.4.1 CPS Security Threats 42320.4.2 Information Layer 42320.4.3 Perceptual Layer 42420.4.4 Application Threats 42420.4.5 Infrastructure 42520.5 Issues and How to Overcome Them 42620.6 Discussion and Solutions 42720.7 Conclusion 431References 431Index 435