Convergence of Deep Learning in Cyber-IoT Systems and Security

Description

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. Cover Title Page Copyright Page Contents Preface Part I: Various Approaches from Machine Learning to Deep Learning Chapter 1 Web-Assisted Noninvasive Detection of Oral Submucous Fibrosis Using IoHT 1.1 Introduction 1.2 Literature Survey 1.2.1 Oral Cancer 1.3 Primary Concepts 1.3.1 Transmission Efficiency 1.4 Propose Model 1.4.1 Platform Configuration 1.4.2 Harvard Architectural Microcontroller Base Wireless Communication Board 1.4.2.1 NodeMCU ESP8266 Microcontroller 1.4.2.2 Gas Sensor 1.4.3 Experimental Setup 1.4.4 Process to Connect to Sever and Analyzing Data on Cloud 1.5 Comparative Study 1.6 Conclusion References Chapter 2 Performance Evaluation of Machine Learning and Deep Learning Techniques: A Comparative Analysis for House Price Prediction 2.1 Introduction 2.2 Related Research 2.2.1 Literature Review on Comparing the Performance of the ML/DL Algorithms 2.2.2 Literature Review on House Price Prediction 2.3 Research Methodology 2.3.1 Data Collection 2.3.2 Data Visualization 2.3.3 Data Preparation 2.3.4 Regression Models 2.3.4.1 Simple Linear Regression 2.3.4.2 Random Forest Regression 2.3.4.3 Ada Boosting Regression 2.3.4.4 Gradient Boosting Regression 2.3.4.5 Support Vector Regression 2.3.4.6 Artificial Neural Network 2.3.4.7 Multioutput Regression 2.3.4.8 Regression Using Tensorflow—Keras 2.3.5 Classification Models 2.3.5.1 Logistic Regression Classifier 2.3.5.2 Decision Tree Classifier 2.3.5.3 Random Forest Classifier 2.3.5.4 Naïve Bayes Classifier 2.3.5.5 K-Nearest Neighbors Classifier 2.3.5.6 Support Vector Machine Classifier (SVM) 2.3.5.7 Feed Forward Neural Network 2.3.5.8 Recurrent Neural Networks 2.3.5.9 LSTM Recurrent Neural Networks 2.3.6 Performance Metrics for Regression Models 2.3.7 Performance Metrics for Classification Models 2.4 Experimentation 2.5 Results and Discussion 2.6 Suggestions 2.7 Conclusion References Chapter 3 Cyber Physical Systems, Machine Learning & Deep Learning—Emergence as an Academic Program and Field for Developing Digital Society 3.1 Introduction 3.2 Objective of the Work 3.3 Methods 3.4 Cyber Physical Systems: Overview with Emerging Academic Potentiality 3.5 ML and DL Basics with Educational Potentialities 3.5.1 Machine Learning (ML) 3.5.2 Deep Learning 3.6 Manpower and Developing Scenario in Machine Learning and Deep Learning 3.7 DL & ML in Indian Context 3.8 Conclusion References Chapter 4 Detection of Fake News and Rumors in the Social Media Using Machine Learning Techniques With Semantic Attributes 4.1 Introduction 4.2 Literature Survey 4.3 Proposed Work 4.3.1 Algorithm 4.3.2 Flowchart 4.3.3 Explanation of Approach 4.4 Results and Analysis 4.4.1 Datasets 4.4.2 Evaluation 4.4.2.1 Result of 1st Dataset 4.4.2.2 Result of 2nd Dataset 4.4.2.3 Result of 3rd Dataset 4.4.3 Relative Comparison of Performance 4.5 Conclusion References Part II: Innovative Solutions Based on Deep Learning Chapter 5 Online Assessment System Using Natural Language Processing Techniques 5.1 Introduction 5.2 Literature Survey 5.3 Existing Algorithms 5.4 Proposed System Design 5.5 System Implementation 5.6 Conclusion References Chapter 6 On a Reference Architecture to Build Deep-Q Learning-Based Intelligent IoT Edge Solutions 6.1 Introduction 6.1.1 A Brief Primer on Machine Learning 6.1.1.1 Types of Machine Learning 6.2 Dynamic Programming 6.3 Deep Q-Learning 6.4 IoT 6.4.1 Azure 6.4.1.1 IoT on Azure 6.5 Conclusion 6.6 Future Work References Chapter 7 Fuzzy Logic-Based Air Conditioner System 7.1 Introduction 7.2 Fuzzy Logic-Based Control System 7.3 Proposed System 7.3.1 Fuzzy Variables 7.3.2 Fuzzy Base Class 7.3.3 Fuzzy Rule Base 7.3.4 Fuzzy Rule Viewer 7.4 Simulated Result 7.5 Conclusion and Future Work References Chapter 8 An Efficient Masked-Face Recognition Technique to Combat with COVID-19 8.1 Introduction 8.2 Related Works 8.2.1 Review of Face Recognition for Unmasked Faces 8.2.2 Review of Face Recognition for Masked Faces 8.3 Mathematical Preliminaries 8.3.1 Digital Curvelet Transform (DCT) 8.3.2 Compressive Sensing–Based Classification 8.4 Proposed Method 8.5 Experimental Results 8.5.1 Database 8.5.2 Result 8.6 Conclusion References Chapter 9 Deep Learning: An Approach to Encounter Pandemic Effect of Novel Corona Virus (COVID-19) 9.1 Introduction 9.2 Interpretation With Medical Imaging 9.3 Corona Virus Variants Tracing 9.4 Spreading Capability and Destructiveness of Virus 9.5 Deduction of Biological Protein Structure 9.6 Pandemic Model Structuring and Recommended Drugs 9.7 Selection of Medicine 9.8 Result Analysis 9.9 Conclusion References Chapter 10 Question Answering System Using Deep Learning in the Low Resource Language Bengali 10.1 Introduction 10.2 Related Work 10.3 Problem Statement 10.4 Proposed Approach 10.5 Algorithm 10.6 Results and Discussion 10.6.1 Result Summary for TDIL Dataset 10.6.2 Result Summary for SQuAD Dataset 10.6.3 Examples of Retrieved Answers 10.6.4 Calculation of TP, TN, FP, FN, Accuracy, Precision, Recall, and F1 score 10.6.5 Comparison of Result with other Methods and Dataset 10.7 Analysis of Error 10.8 Few Close Observations 10.9 Applications 10.10 Scope for Improvements 10.11 Conclusions Acknowledgments References Part III: Security and Safety Aspects with Deep Learning Chapter 11 Secure Access to Smart Homes Using Biometric Authentication With RFID Reader for IoT Systems 11.1 Introduction 11.2 Related Work 11.3 Framework for Smart Home Use Case With Biometric 11.3.1 RFID-Based Authentication and Its Drawbacks 11.4 Control Scheme for Secure Access (CSFSC) 11.4.1 Problem Definition 11.4.2 Biometric-Based RFID Reader Proposed Scheme 11.4.3 Reader-Based Procedures 11.4.4 Backend Server-Side Procedures 11.4.5 Reader Side Final Compute and Check Operations 11.5 Results Observed Based on Various Features With Proposed and Existing Methods 11.6 Conclusions and Future Work References Chapter 12 MQTT-Based Implementation of Home Automation System Prototype With Integrated Cyber-IoT Infrastructure and Deep Learning–Based Security Issues 12.1 Introduction 12.2 Architecture of Implemented Home Automation 12.3 Challenges in Home Automation 12.3.1 Distributed Denial of Service and Attack 12.3.2 Deep Learning–Based Solution Aspects 12.4 Implementation 12.4.1 Relay 12.4.2 DHT11 12.5 Results and Discussions 12.6 Conclusion References Chapter 13 Malware Detection in Deep Learning 13.1 Introduction to Malware 13.1.1 Computer Security 13.1.2 What Is Malware? 13.2 Machine Learning and Deep Learning for Malware Detection 13.2.1 Introduction to Machine Learning 13.2.2 Introduction to Deep Learning 13.2.3 Detection Techniques Using Deep Learning 13.3 Case Study on Malware Detection 13.3.1 Impact of Malware on Systems 13.3.2 Effect of Malware in a Pandemic Situation 13.4 Conclusion References Chapter 14 Patron for Women: An Application for Womens Safety 14.1 Introduction 14.2 Background Study 14.3 Related Research 14.3.1 A Mobile-Based Women Safety Application (I safe App) 14.3.2 Lifecraft: An Android-Based Application System for Women Safety 14.3.3 Abhaya: An Android App for the Safety of Women 14.3.4 Sakhi—The Saviour: An Android Application to Help Women in Times of Social Insecurity 14.4 Proposed Methodology 14.4.1 Motivation and Objective 14.4.2 Proposed System 14.4.3 System Flowchart 14.4.4 Use-Case Model 14.4.5 Novelty of the Work 14.4.6 Comparison with Existing System 14.5 Results and Analysis 14.6 Conclusion and Future Work References Chapter 15 Concepts and Techniques in Deep Learning Applications in the Field of IoT Systems and Security 15.1 Introduction 15.2 Concepts of Deep Learning 15.3 Techniques of Deep Learning 15.3.1 Classic Neural Networks 15.3.1.1 Linear Function 15.3.1.2 Nonlinear Function 15.3.1.3 Sigmoid Curve 15.3.1.4 Rectified Linear Unit 15.3.2 Convolution Neural Networks 15.3.2.1 Convolution 15.3.2.2 Max-Pooling 15.3.2.3 Flattening 15.3.2.4 Full Connection 15.3.3 Recurrent Neural Networks 15.3.3.1 LSTMs 15.3.3.2 Gated RNNs 15.3.4 Generative Adversarial Networks 15.3.5 Self-Organizing Maps 15.3.6 Boltzmann Machines 15.3.7 Deep Reinforcement Learning 15.3.8 Auto Encoders 15.3.8.1 Sparse 15.3.8.2 Denoising 15.3.8.3 Contractive 15.3.8.4 Stacked 15.3.9 Back Propagation 15.3.10 Gradient Descent 15.4 Deep Learning Applications 15.4.1 Automatic Speech Recognition (ASR) 15.4.2 Image Recognition 15.4.3 Natural Language Processing 15.4.4 Drug Discovery and Toxicology 15.4.5 Customer Relationship Management 15.4.6 Recommendation Systems 15.4.7 Bioinformatics 15.5 Concepts of IoT Systems 15.6 Techniques of IoT Systems 15.6.1 Architecture 15.6.2 Programming Model 15.6.3 Scheduling Policy 15.6.4 Memory Footprint 15.6.5 Networking 15.6.6 Portability 15.6.7 Energy Efficiency 15.7 IoT Systems Applications 15.7.1 Smart Home 15.7.2 Wearables 15.7.3 Connected Cars 15.7.4 Industrial Internet 15.7.5 Smart Cities 15.7.6 IoT in Agriculture 15.7.7 Smart Retail 15.7.8 Energy Engagement 15.7.9 IoT in Healthcare 15.7.10 IoT in Poultry and Farming 15.8 Deep Learning Applications in the Field of IoT Systems 15.8.1 Organization of DL Applications for IoT in Healthcare 15.8.2 DeepSense as a Solution for Diverse IoT Applications 15.8.3 Deep IoT as a Solution for Energy Efficiency 15.9 Conclusion References Chapter 16 Efficient Detection of Bioweapons for Agricultural Sector Using Narrowband Transmitter and Composite Sensing Architecture 16.1 Introduction 16.2 Literature Review 16.3 Properties of Insects 16.4 Working Methodology 16.4.1 Sensing 16.4.1.1 Specific Characterization of a Particular Species 16.4.2 Alternative Way to Find Those Previously Sensing Parameters 16.4.3 Remedy to Overcome These Difficulties 16.4.4 Take Necessary Preventive Actions 16.5 Proposed Algorithm 16.6 Block Diagram and Used Sensors 16.6.1 Arduino Uno 16.6.2 Infrared Motion Sensor 16.6.3 Thermographic Camera 16.6.4 Relay Module 16.7 Result Analysis 16.8 Conclusion References Chapter 17 A Deep Learning–Based Malware and Intrusion Detection Framework 17.1 Introduction 17.2 Literature Survey 17.3 Overview of the Proposed Work 17.3.1 Problem Description 17.3.2 The Working Models 17.3.3 About the Dataset 17.3.4 About the Algorithms 17.4 Implementation 17.4.1 Libraries 17.4.2 Algorithm 17.5 Results 17.5.1 Neural Network Models 17.5.2 Accuracy 17.5.3 Web Frameworks 17.6 Conclusion and Future Work References Chapter 18 Phishing URL Detection Based on Deep Learning Techniques 18.1 Introduction 18.1.1 Phishing Life Cycle 18.1.1.1 Planning 18.1.1.2 Collection 18.1.1.3 Fraud 18.2 Literature Survey 18.3 Feature Generation 18.4 Convolutional Neural Network for Classification of Phishing vs Legitimate URLs 18.5 Results and Discussion 18.6 Conclusion References Web Citation Part IV: Cyber Physical Systems Chapter 19 Cyber Physical System—The Gen Z 19.1 Introduction 19.2 Architecture and Design 19.2.1 Cyber Family 19.2.2 Physical Family 19.2.3 Cyber-Physical Interface Family 19.3 Distribution and Reliability Management in CPS 19.3.1 CPS Components 19.3.2 CPS Models 19.4 Security Issues in CPS 19.4.1 Cyber Threats 19.4.2 Physical Threats 19.5 Role of Machine Learning in the Field of CPS 19.6 Application 19.7 Conclusion References Chapter 20 An Overview of Cyber Physical System (CPS) Security, Threats, and Solutions 20.1 Introduction 20.1.1 Motivation of Work 20.1.2 Organization of Sections 20.2 Characteristics of CPS 20.3 Types of CPS Security 20.4 Cyber Physical System Security Mechanism—Main Aspects 20.4.1 CPS Security Threats 20.4.2 Information Layer 20.4.3 Perceptual Layer 20.4.4 Application Threats 20.4.5 Infrastructure 20.5 Issues and How to Overcome Them 20.6 Discussion and Solutions 20.7 Conclusion References Index EULA