+353-1-416-8900REST OF WORLD
+44-20-3973-8888REST OF WORLD
1-917-300-0470EAST COAST U.S
1-800-526-8630U.S. (TOLL FREE)

Convergence of Deep Learning in Cyber-IoT Systems and Security. Edition No. 1. Artificial Intelligence and Soft Computing for Industrial Transformation

  • Book

  • 480 Pages
  • December 2022
  • John Wiley and Sons Ltd
  • ID: 5838082
CONVERGENCE OF DEEP LEARNING IN CYBER-IOT SYSTEMS AND SECURITY

In-depth analysis of Deep Learning-based cyber-IoT systems and security which will be the industry leader for the next ten years.

The main goal of this book is to bring to the fore unconventional cryptographic methods to provide cyber security, including cyber-physical system security and IoT security through deep learning techniques and analytics with the study of all these systems.

This book provides innovative solutions and implementation of deep learning-based models in cyber-IoT systems, as well as the exposed security issues in these systems. The 20 chapters are organized into four parts. Part I gives the various approaches that have evolved from machine learning to deep learning. Part II presents many innovative solutions, algorithms, models, and implementations based on deep learning. Part III covers security and safety aspects with deep learning. Part IV details cyber-physical systems as well as a discussion on the security and threats in cyber-physical systems with probable solutions.

Audience

Researchers and industry engineers in computer science, information technology, electronics and communication, cybersecurity and cryptography.

Table of Contents

Preface xvii

Part I: Various Approaches from Machine Learning to Deep Learning 1

1 Web-Assisted Noninvasive Detection of Oral Submucous Fibrosis Using IoHT 3
Animesh Upadhyaya, Vertika Rai, Debdutta Pal, Surajit Bose and Somnath Ghosh

1.1 Introduction 3

1.2 Literature Survey 6

1.2.1 Oral Cancer 6

1.3 Primary Concepts 7

1.3.1 Transmission Efficiency 7

1.4 Propose Model 9

1.4.1 Platform Configuration 9

1.4.2 Harvard Architectural Microcontroller Base Wireless Communication Board 10

1.4.2.1 NodeMCU ESP8266 Microcontroller 10

1.4.2.2 Gas Sensor 12

1.4.3 Experimental Setup 13

1.4.4 Process to Connect to Sever and Analyzing Data on Cloud 14

1.5 Comparative Study 16

1.6 Conclusion 17

References 17

2 Performance Evaluation of Machine Learning and Deep Learning Techniques: A Comparative Analysis for House Price Prediction 21
Sajeev Ram Arumugam, Sheela Gowr, Abimala, Balakrishna and Oswalt Manoj

2.1 Introduction 22

2.2 Related Research 23

2.2.1 Literature Review on Comparing the Performance of the ML/DL Algorithms 23

2.2.2 Literature Review on House Price Prediction 25

2.3 Research Methodology 26

2.3.1 Data Collection 27

2.3.2 Data Visualization 27

2.3.3 Data Preparation 28

2.3.4 Regression Models 29

2.3.4.1 Simple Linear Regression 29

2.3.4.2 Random Forest Regression 30

2.3.4.3 Ada Boosting Regression 31

2.3.4.4 Gradient Boosting Regression 32

2.3.4.5 Support Vector Regression 33

2.3.4.6 Artificial Neural Network 34

2.3.4.7 Multioutput Regression 36

2.3.4.8 Regression Using Tensorflow - Keras 37

2.3.5 Classification Models 39

2.3.5.1 Logistic Regression Classifier 39

2.3.5.2 Decision Tree Classifier 39

2.3.5.3 Random Forest Classifier 41

2.3.5.4 Naïve Bayes Classifier 41

2.3.5.5 K-Nearest Neighbors Classifier 42

2.3.5.6 Support Vector Machine Classifier (SVM) 43

2.3.5.7 Feed Forward Neural Network 43

2.3.5.8 Recurrent Neural Networks 44

2.3.5.9 LSTM Recurrent Neural Networks 44

2.3.6 Performance Metrics for Regression Models 45

2.3.7 Performance Metrics for Classification Models 46

2.4 Experimentation 47

2.5 Results and Discussion 48

2.6 Suggestions 60

2.7 Conclusion 60

References 62

3 Cyber Physical Systems, Machine Learning & Deep Learning - Emergence as an Academic Program and Field for Developing Digital Society 67
P. K. Paul

3.1 Introduction 68

3.2 Objective of the Work 69

3.3 Methods 69

3.4 Cyber Physical Systems: Overview with Emerging Academic Potentiality 70

3.5 ml and dl Basics with Educational Potentialities 72

3.5.1 Machine Learning (ML) 72

3.5.2 Deep Learning 73

3.6 Manpower and Developing Scenario in Machine Learning and Deep Learning 74

3.7 dl & ml in Indian Context 79

3.8 Conclusion 81

References 82

4 Detection of Fake News and Rumors in the Social Media Using Machine Learning Techniques With Semantic Attributes 85
Diganta Saha, Arijit Das, Tanmay Chandra Nath, Soumyadip Saha and Ratul Das

4.1 Introduction 86

4.2 Literature Survey 87

4.3 Proposed Work 88

4.3.1 Algorithm 89

4.3.2 Flowchart 90

4.3.3 Explanation of Approach 91

4.4 Results and Analysis 92

4.4.1 Datasets 92

4.4.2 Evaluation 93

4.4.2.1 Result of 1st Dataset 93

4.4.2.2 Result of 2nd Dataset 94

4.4.2.3 Result of 3rd Dataset 94

4.4.3 Relative Comparison of Performance 95

4.5 Conclusion 95

References 96

Part II: Innovative Solutions Based on Deep Learning 99

5 Online Assessment System Using Natural Language Processing Techniques 101
S. Suriya, K. Nagalakshmi and Nivetha S.

5.1 Introduction 102

5.2 Literature Survey 103

5.3 Existing Algorithms 108

5.4 Proposed System Design 111

5.5 System Implementation 115

5.6 Conclusion 120

References 121

6 On a Reference Architecture to Build Deep-Q Learning-Based Intelligent IoT Edge Solutions 123
Amit Chakraborty, Ankit Kumar Shaw and Sucharita Samanta

6.1 Introduction 124

6.1.1 A Brief Primer on Machine Learning 124

6.1.1.1 Types of Machine Learning 124

6.2 Dynamic Programming 128

6.3 Deep Q-Learning 129

6.4 IoT 130

6.4.1 Azure 130

6.4.1.1 IoT on Azure 130

6.5 Conclusion 144

6.6 Future Work 144

References 145

7 Fuzzy Logic-Based Air Conditioner System 147
Suparna Biswas, Sayan Roy Chaudhuri, Ayusha Biswas and Arpan Bhawal

7.1 Introduction 147

7.2 Fuzzy Logic-Based Control System 149

7.3 Proposed System 149

7.3.1 Fuzzy Variables 149

7.3.2 Fuzzy Base Class 154

7.3.3 Fuzzy Rule Base 155

7.3.4 Fuzzy Rule Viewer 156

7.4 Simulated Result 157

7.5 Conclusion and Future Work 163

References 163

8 An Efficient Masked-Face Recognition Technique to Combat with COVID-19 165
Suparna Biswas

8.1 Introduction 165

8.2 Related Works 167

8.2.1 Review of Face Recognition for Unmasked Faces 167

8.2.2 Review of Face Recognition for Masked Faces 168

8.3 Mathematical Preliminaries 169

8.3.1 Digital Curvelet Transform (DCT) 169

8.3.2 Compressive Sensing-Based Classification 170

8.4 Proposed Method 171

8.5 Experimental Results 173

8.5.1 Database 173

8.5.2 Result 175

8.6 Conclusion 179

References 179

9 Deep Learning: An Approach to Encounter Pandemic Effect of Novel Corona Virus (COVID-19) 183
Santanu Koley, Pinaki Pratim Acharjya, Rajesh Mukherjee, Soumitra Roy and Somdeep Das

9.1 Introduction 184

9.2 Interpretation With Medical Imaging 185

9.3 Corona Virus Variants Tracing 188

9.4 Spreading Capability and Destructiveness of Virus 191

9.5 Deduction of Biological Protein Structure 192

9.6 Pandemic Model Structuring and Recommended Drugs 192

9.7 Selection of Medicine 195

9.8 Result Analysis 197

9.9 Conclusion 201

References 202

10 Question Answering System Using Deep Learning in the Low Resource Language Bengali 207
Arijit Das and Diganta Saha

10.1 Introduction 208

10.2 Related Work 210

10.3 Problem Statement 215

10.4 Proposed Approach 215

10.5 Algorithm 216

10.6 Results and Discussion 219

10.6.1 Result Summary for TDIL Dataset 219

10.6.2 Result Summary for SQuAD Dataset 219

10.6.3 Examples of Retrieved Answers 220

10.6.4 Calculation of TP, TN, FP, FN, Accuracy, Precision, Recall, and F1 score 221

10.6.5 Comparison of Result with other Methods and Dataset 222

10.7 Analysis of Error 223

10.8 Few Close Observations 223

10.9 Applications 224

10.10 Scope for Improvements 224

10.11 Conclusions 224

Acknowledgments 225

References 225

Part III: Security and Safety Aspects with Deep Learning 231

11 Secure Access to Smart Homes Using Biometric Authentication With RFID Reader for IoT Systems 233
K.S. Niraja and Sabbineni Srinivasa Rao

11.1 Introduction 234

11.2 Related Work 235

11.3 Framework for Smart Home Use Case With Biometric 236

11.3.1 RFID-Based Authentication and Its Drawbacks 236

11.4 Control Scheme for Secure Access (CSFSC) 237

11.4.1 Problem Definition 237

11.4.2 Biometric-Based RFID Reader Proposed Scheme 238

11.4.3 Reader-Based Procedures 240

11.4.4 Backend Server-Side Procedures 240

11.4.5 Reader Side Final Compute and Check Operations 240

11.5 Results Observed Based on Various Features With Proposed and Existing Methods 242

11.6 Conclusions and Future Work 245

References 246

12 MQTT-Based Implementation of Home Automation System Prototype With Integrated Cyber-IoT Infrastructure and Deep Learning-Based Security Issues 249
Arnab Chakraborty

12.1 Introduction 250

12.2 Architecture of Implemented Home Automation 252

12.3 Challenges in Home Automation 253

12.3.1 Distributed Denial of Service and Attack 254

12.3.2 Deep Learning-Based Solution Aspects 254

12.4 Implementation 255

12.4.1 Relay 256

12.4.2 DHT 11 257

12.5 Results and Discussions 262

12.6 Conclusion 265

References 266

13 Malware Detection in Deep Learning 269
Sharmila Gaikwad and Jignesh Patil

13.1 Introduction to Malware 270

13.1.1 Computer Security 270

13.1.2 What Is Malware? 271

13.2 Machine Learning and Deep Learning for Malware Detection 274

13.2.1 Introduction to Machine Learning 274

13.2.2 Introduction to Deep Learning 276

13.2.3 Detection Techniques Using Deep Learning 279

13.3 Case Study on Malware Detection 280

13.3.1 Impact of Malware on Systems 280

13.3.2 Effect of Malware in a Pandemic Situation 281

13.4 Conclusion 283

References 283

14 Patron for Women: An Application for Womens Safety 285
Riya Sil, Snatam Kamila, Ayan Mondal, Sufal Paul, Santanu Sinha and Bishes Saha

14.1 Introduction 286

14.2 Background Study 286

14.3 Related Research 287

14.3.1 A Mobile-Based Women Safety Application (I safe App) 287

14.3.2 Lifecraft: An Android-Based Application System for Women Safety 288

14.3.3 Abhaya: An Android App for the Safety of Women 288

14.3.4 Sakhi - The Saviour: An Android Application to Help Women in Times of Social Insecurity 289

14.4 Proposed Methodology 289

14.4.1 Motivation and Objective 290

14.4.2 Proposed System 290

14.4.3 System Flowchart 291

14.4.4 Use-Case Model 291

14.4.5 Novelty of the Work 294

14.4.6 Comparison with Existing System 294

14.5 Results and Analysis 294

14.6 Conclusion and Future Work 298

References 299

15 Concepts and Techniques in Deep Learning Applications in the Field of IoT Systems and Security 303
Santanu Koley and Pinaki Pratim Acharjya

15.1 Introduction 304

15.2 Concepts of Deep Learning 307

15.3 Techniques of Deep Learning 308

15.3.1 Classic Neural Networks 309

15.3.1.1 Linear Function 309

15.3.1.2 Nonlinear Function 309

15.3.1.3 Sigmoid Curve 310

15.3.1.4 Rectified Linear Unit 310

15.3.2 Convolution Neural Networks 310

15.3.2.1 Convolution 311

15.3.2.2 Max-Pooling 311

15.3.2.3 Flattening 311

15.3.2.4 Full Connection 311

15.3.3 Recurrent Neural Networks 312

15.3.3.1 LSTMs 312

15.3.3.2 Gated RNNs 312

15.3.4 Generative Adversarial Networks 313

15.3.5 Self-Organizing Maps 314

15.3.6 Boltzmann Machines 315

15.3.7 Deep Reinforcement Learning 315

15.3.8 Auto Encoders 316

15.3.8.1 Sparse 317

15.3.8.2 Denoising 317

15.3.8.3 Contractive 317

15.3.8.4 Stacked 317

15.3.9 Back Propagation 317

15.3.10 Gradient Descent 318

15.4 Deep Learning Applications 319

15.4.1 Automatic Speech Recognition (ASR) 319

15.4.2 Image Recognition 320

15.4.3 Natural Language Processing 320

15.4.4 Drug Discovery and Toxicology 321

15.4.5 Customer Relationship Management 322

15.4.6 Recommendation Systems 323

15.4.7 Bioinformatics 324

15.5 Concepts of IoT Systems 325

15.6 Techniques of IoT Systems 326

15.6.1 Architecture 326

15.6.2 Programming Model 327

15.6.3 Scheduling Policy 329

15.6.4 Memory Footprint 329

15.6.5 Networking 332

15.6.6 Portability 332

15.6.7 Energy Efficiency 333

15.7 IoT Systems Applications 333

15.7.1 Smart Home 334

15.7.2 Wearables 335

15.7.3 Connected Cars 335

15.7.4 Industrial Internet 336

15.7.5 Smart Cities 337

15.7.6 IoT in Agriculture 337

15.7.7 Smart Retail 338

15.7.8 Energy Engagement 339

15.7.9 IoT in Healthcare 340

15.7.10 IoT in Poultry and Farming 340

15.8 Deep Learning Applications in the Field of IoT Systems 341

15.8.1 Organization of DL Applications for IoT in Healthcare 342

15.8.2 DeepSense as a Solution for Diverse IoT Applications 343

15.8.3 Deep IoT as a Solution for Energy Efficiency 346

15.9 Conclusion 346

References 347

16 Efficient Detection of Bioweapons for Agricultural Sector Using Narrowband Transmitter and Composite Sensing Architecture 349
Arghyadeep Nag, Labani Roy, Shruti, Soumen Santra and Arpan Deyasi

16.1 Introduction 350

16.2 Literature Review 353

16.3 Properties of Insects 355

16.4 Working Methodology 357

16.4.1 Sensing 357

16.4.1.1 Specific Characterization of a Particular Species 357

16.4.2 Alternative Way to Find Those Previously Sensing Parameters 357

16.4.3 Remedy to Overcome These Difficulties 358

16.4.4 Take Necessary Preventive Actions 358

16.5 Proposed Algorithm 359

16.6 Block Diagram and Used Sensors 360

16.6.1 Arduino Uno 361

16.6.2 Infrared Motion Sensor 362

16.6.3 Thermographic Camera 362

16.6.4 Relay Module 362

16.7 Result Analysis 362

16.8 Conclusion 363

References 363

17 A Deep Learning-Based Malware and Intrusion Detection Framework 367
Pavitra Kadiyala and Kakelli Anil Kumar

17.1 Introduction 367

17.2 Literature Survey 368

17.3 Overview of the Proposed Work 371

17.3.1 Problem Description 371

17.3.2 The Working Models 371

17.3.3 About the Dataset 371

17.3.4 About the Algorithms 373

17.4 Implementation 374

17.4.1 Libraries 374

17.4.2 Algorithm 376

17.5 Results 376

17.5.1 Neural Network Models 377

17.5.2 Accuracy 377

17.5.3 Web Frameworks 377

17.6 Conclusion and Future Work 379

References 380

18 Phishing URL Detection Based on Deep Learning Techniques 381
S. Carolin Jeeva and W. Regis Anne

18.1 Introduction 382

18.1.1 Phishing Life Cycle 382

18.1.1.1 Planning 383

18.1.1.2 Collection 384

18.1.1.3 Fraud 384

18.2 Literature Survey 385

18.3 Feature Generation 388

18.4 Convolutional Neural Network for Classification of Phishing vs Legitimate URLs 388

18.5 Results and Discussion 391

18.6 Conclusion 394

References 394

Web Citation 396

Part IV: Cyber Physical Systems 397

19 Cyber Physical System - The Gen Z 399
Jayanta Aich and Mst Rumana Sultana

19.1 Introduction 399

19.2 Architecture and Design 400

19.2.1 Cyber Family 401

19.2.2 Physical Family 401

19.2.3 Cyber-Physical Interface Family 402

19.3 Distribution and Reliability Management in CPS 403

19.3.1 CPS Components 403

19.3.2 CPS Models 404

19.4 Security Issues in CPS 405

19.4.1 Cyber Threats 405

19.4.2 Physical Threats 407

19.5 Role of Machine Learning in the Field of CPS 408

19.6 Application 411

19.7 Conclusion 411

References 411

20 An Overview of Cyber Physical System (CPS) Security, Threats, and Solutions 415
Krishna Keerthi Chennam, Fahmina Taranum and Maniza Hijab

20.1 Introduction 416

20.1.1 Motivation of Work 417

20.1.2 Organization of Sections 417

20.2 Characteristics of CPS 418

20.3 Types of CPS Security 419

20.4 Cyber Physical System Security Mechanism - Main Aspects 421

20.4.1 CPS Security Threats 423

20.4.2 Information Layer 423

20.4.3 Perceptual Layer 424

20.4.4 Application Threats 424

20.4.5 Infrastructure 425

20.5 Issues and How to Overcome Them 426

20.6 Discussion and Solutions 427

20.7 Conclusion 431

References 431

Index 435

Authors

Rajdeep Chakraborty Netaji Subhash Engineering College, Kolkata, India. Anupam Ghosh Netaji Subhash Engineering College, Kolkata, India. Jyotsna Kumar Mandal S. Balamurugan Intelligent Research Consultancy Services (iRCS), Tamilnadu, India.