SK Hafizul Islam received his PhD degree in Computer Science and Engineering in 2013 from the Indian Institute of Technology [IIT (ISM)] Dhanbad, Jharkhand, India. He is an assistant professor in the Department of Computer Science and Engineering, Indian Institute of Information Technology Kalyani (IIIT Kalyani), West Bengal, India. He has authored or coauthored 110 research papers in journals and conference proceedings.Debabrata Samanta is an assistant professor in the Department of Computer Science, CHRIST (Deemed to be University), Bangalore, India. He obtained his PhD in Computer Science and Engg. from the National Institute of Technology, Durgapur, India, in the area of SAR Image Processing. He is the owner of 17 Indian patents and has authored and coauthored more than 135 research papers in international journals.

• Preface xviiAcknowledgments xxiii1 Machine Learning Technologies in IoT EEG-Based Healthcare Prediction 1Karthikeyan M.P., Krishnaveni K. and Muthumani N.1.1 Introduction 21.1.1 Descriptive Analytics 31.1.2 Analytical Methods 31.1.3 Predictive Analysis 41.1.4 Behavioral Analysis 41.1.5 Data Interpretation 41.1.6 Classification 41.2 Related Works 71.3 Problem Definition 91.4 Research Methodology 91.4.1 Components Used 101.4.2 Specifications and Description About Components 101.4.2.1 Arduino 101.4.2.2 EEG Sensor—Mindwave Mobile Headset 111.4.2.3 Raspberry pi 121.4.2.4 Working 131.4.3 Cloud Feature Extraction 131.4.4 Feature Optimization 141.4.5 Classification and Validation 151.5 Result and Discussion 161.5.1 Result 161.5.2 Discussion 231.6 Conclusion 271.6.1 Future Scope 27References 282 Smart Health Application for Remote Tracking of Ambulatory Patients 33Shariq Aziz Butt, Muhammad Waqas Anjum, Syed Areeb Hassan, Arindam Garai and Edeh Michael Onyema2.1 Introduction 342.2 Literature Work 342.3 Smart Computing for Smart Health for Ambulatory Patients 352.4 Challenges With Smart Health 362.4.1 Emergency Support 362.4.2 The Issue With Chronic Disease Monitoring 382.4.3 An Issue With the Tele-Medication 382.4.4 Mobility of Doctor 402.4.5 Application User Interface Issue 402.5 Security Threats 412.5.1 Identity Privacy 412.5.2 Query Privacy 422.5.3 Location of Privacy 422.5.4 Footprint Privacy and Owner Privacy 432.6 Applications of Fuzzy Set Theory in Healthcare and Medical Problems 432.7 Conclusion 51References 513 Data-Driven Decision Making in IoT Healthcare Systems—COVID-19: A Case Study 57Saroja S., Haseena S. and Blessa Binolin Pepsi M.3.1 Introduction 583.1.1 Pre-Processing 593.1.2 Classification Algorithms 603.1.2.1 Dummy Classifier 603.1.2.2 Support Vector Machine (SVM) 603.1.2.3 Gradient Boosting 613.1.2.4 Random Forest 623.1.2.5 Ada Boost 633.2 Experimental Analysis 633.3 Multi-Criteria Decision Making (MCDM) Procedure 633.3.1 Simple Multi Attribute Rating Technique (SMART) 643.3.1.1 COVID-19 Disease Classification Using SMART 643.3.2 Weighted Product Model (WPM) 663.3.2.1 COVID-19 Disease Classification Using WPM 663.3.3 Method for Order Preference by Similarity to the Ideal Solution (TOPSIS) 673.3.3.1 COVID-19 Disease Classification Using TOPSIS 683.4 Conclusion 69References 694 Touch and Voice-Assisted Multilingual Communication Prototype for ICU Patients Specific to COVID-19 71B. Rajesh Kanna and C.Vijayalakshmi4.1 Introduction and Motivation 724.1.1 Existing Interaction Approaches and Technology 734.1.2 Challenges and Gaps 744.2 Proposed Prototype of Touch and Voice-Assisted Multilingual Communication 754.3 A Sample Case Study 824.4 Conclusion 82References 845 Cloud-Assisted IoT System for Epidemic Disease Detection and Spread Monitoring 87Himadri Nath Saha, Reek Roy and Sumanta Chakraborty5.1 Introduction 885.2 Background & Related Works 925.3 Proposed Model 985.3.1 ThinkSpeak 1005.3.2 Blood Oxygen Saturation (SpO2) 1005.3.3 Blood Pressure (BP) 1015.3.4 Electrocardiogram (ECG) 1015.3.5 Body Temperature (BT) 1025.3.6 Respiration Rate (RR) 1025.3.7 Environmental Parameters 1035.4 Methodology 1035.5 Performance Analysis 1105.6 Future Research Direction 1115.7 Conclusion 112References 1136 Impact of Healthcare 4.0 Technologies for Future Capacity Building to Control Epidemic Diseases 115Himadri Nath Saha, Sumanta Chakraborty, Sourav Paul, Rajdeep Ghosh and Dipanwita Chakraborty Bhattacharya6.1 Introduction 1166.2 Background and Related Works 1206.3 System Design and Architecture 1286.4 Methodology 1316.5 Performance Analysis 1386.6 Future Research Direction 1386.7 Conclusion 139References 1397 Security and Privacy of IoT Devices in Healthcare Systems 143Himadri Nath Saha and Subhradip Debnath7.1 Introduction 1447.2 Background and Related Works 1457.3 Proposed System Design and Architecture 1477.3.1 Modules 1487.3.1.1 Wireless Body Area Network 1487.3.1.2 Centralized Network Coordinator 1497.3.1.3 Local Server 1497.3.1.4 Cloud Server 1507.3.1.5 Dedicated Network Connection 1517.4 Methodology 1517.5 Performance Analysis 1607.6 Future Research Direction 1617.7 Conclusion 163References 1648 An IoT-Based Diet Monitoring Healthcare System for Women 167Suganyadevi S., Shamia D. and Balasamy K.8.1 Introduction 1688.2 Background 1778.2.1 Food Consumption 1778.2.2 Food Consumption Monitoring 1788.2.3 Health Monitoring Methods Using Physical Methodology 1798.2.3.1 Traditional Form of Self-Report 1798.2.3.2 Self-Reporting Methodology Through Smart Phones 1798.2.3.3 Food Frequency Questionnaire 1798.2.4 Methods for Health Tracking Using Automated Approach 1808.2.4.1 Pressure Process 1808.2.4.2 Surveillance Video Method 1808.2.4.3 Method of Doppler Sensing 1808.3 Necessity of Wearable Approach? 1818.4 Different Approaches for Wearable Sensing 1818.4.1 Approach of Acoustics 1828.4.1.1 Detection of Chewing 1828.4.1.2 Detection of Swallowing 1838.4.1.3 Shared Chewing/Swallowing Discovery 1838.5 Description of the Methodology 1848.6 Description of Various Components Used 1858.6.1 Sensors 1858.6.1.1 Sensors for Cardio-Vascular Monitoring 1858.6.1.2 Sensors for Activity Monitoring 1868.6.1.3 Sensors for Body Temperature Monitoring 1878.6.1.4 Sensor for Galvanic Skin Response (GSR) Monitoring 1888.6.1.5 Sensor for Monitoring the Blood Oxygen Saturation (SpO2 ) 1898.7 Strategy of Communication for Wearable Systems 1898.8 Conclusion 192References 1949 A Secure Framework for Protecting Clinical Data in Medical IoT Environment 203Balasamy K., Krishnaraj N., Ramprasath J. and Ramprakash P.9.1 Introduction 2039.1.1 Medical IoT Background & Perspective 2049.1.1.1 Medical IoT Communication Network 2049.2 Medical IoT Application Domains 2099.2.1 Smart Doctor 2099.2.2 Smart Medical Practitioner 2099.2.3 Smart Technology 2099.2.4 Smart Receptionist 2109.2.5 Disaster Response Systems (DRS) 2109.3 Medical IoT Concerns 2109.3.1 Security Concerns 2119.3.2 Privacy Concerns 2129.3.3 Trust Concerns 2129.4 Need for Security in Medical IoT 2129.5 Components for Enhancing Data Security in Medical IoT 2149.5.1 Confidentiality 2149.5.2 Integrity 2149.5.3 Authentication 2159.5.4 Non-Repudiation 2159.5.5 Privacy 2159.6 Vulnerabilities in Medical IoT Environment 2159.6.1 Patient Privacy Protection 2159.6.2 Patient Safety 2169.6.3 Unauthorized Access 2169.6.4 Medical IoT Security Constraints 2179.7 Solutions for IoT Healthcare Cyber-Security 2189.7.1 Architecture of the Smart Healthcare System 2189.7.1.1 Data Perception Layer 2189.7.1.2 Data Communication Layer 2199.7.1.3 Data Storage Layer 2199.7.1.4 Data Application Layer 2199.8 Execution of Trusted Environment 2209.8.1 Root of Trust Security Services 2209.8.2 Chain of Trust Security Services 2229.9 Patient Registration Using Medical IoT Devices 2239.9.1 Encryption 2249.9.2 Key Generation 2259.9.3 Security by Isolation 2259.9.4 Virtualization 2259.10 Trusted Communication Using Block Chain 2299.10.1 Record Creation Using IoT Gateways 2299.10.2 Accessibility to Patient Medical History 2309.10.3 Patient Enquiry With Hospital Authority 2309.10.4 Block Chain Based IoT System Architecture 2319.10.4.1 First Layer 2319.10.4.2 Second Layer 2319.10.4.3 Third Layer 2329.11 Conclusion 232References 23310 Efficient Data Transmission and Remote Monitoring System for IoT Applications 235Laith Farhan, Firas MaanAbdulsattar, Laith Alzubaidi, Mohammed A. Fadhel, Banu ÇalýþUslu and Muthana Al-Amidie10.1 Introduction 23610.2 Network Configuration 23610.2.1 Message Queuing Telemetry Transport (MQTT) Protocol 23810.2.2 Embedded Database SQLite 24210.2.3 Eclipse Paho Library 24210.2.4 Raspberry Pi Single Board Computer 24210.2.5 Custard Pi Add-On Board 24310.2.6 Pressure Transmitter (Type 663) 24410.3 Data Filtering and Predicting Processes 24510.3.1 Filtering Process 24510.3.2 Predicting Process 24610.3.3 Remote Monitoring Systems 24810.4 Experimental Setup 24910.4.1 Implementation Using Python 25110.4.1.1 Prerequisites 25110.4.2 Monitoring Data 25110.4.3 Experimental Results 25510.4.3.1 IoT Device Results 25510.4.3.2 Traditional Network Results 25710.5 Conclusion 261References 26111 IoT in Current Times and its Prospective Advancements 265T. Venkat Narayana Rao, Abhishek Duggirala, Muralidhar Kurni and Syed Tabassum Sultana11.1 Introduction 26611.1.1 Introduction to Industry 4.0 26611.1.2 Introduction to IoT 26611.1.3 Introduction to IIoT 26711.2 How IIoT Advances Industrial Engineering in Industry 4.0 Era 26711.3 IoT and its Current Applications 26811.3.1 Home Automation 26811.3.2 Wearables 26911.3.3 Connected Cars 26911.3.4 Smart Grid 26911.4 Application Areas of IIoT 27011.4.1 IIoT in Healthcare 27011.4.2 IIoT in Mining 27011.4.3 IIoT in Agriculture 27111.4.4 IIoT in Aerospace 27111.4.5 IIoT in Smart Cities 27211.4.6 IIoT in Supply Chain Management 27211.5 Challenges of Existing Systems 27211.5.1 Security 27211.5.2 Integration 27311.5.3 Connectivity Issues 27311.6 Future Advancements 27311.6.1 Data Analytics in IoT 27411.6.2 Edge Computing 27411.6.3 Secured IoT Through Blockchain 27411.6.4 A Fusion of AR and IoT 27511.6.5 Accelerating IoT Through 5G 27511.7 Case Study of DeWalt 27511.8 Conclusion 276References 27612 Reliance on Artificial Intelligence, Machine Learning and Deep Learning in the Era of Industry 4.0 281T. Venkat Narayana Rao, Akhila Gaddam, Muralidhar Kurni and K. Saritha12.1 Introduction to Artificial Intelligence 28212.1.1 History of AI 28212.1.2 Views of AI 28212.1.3 Types of AI 28312.1.4 Intelligent Agents 28412.2 AI and its Related Fields 28612.3 What is Industry 4.0? 28912.4 Industrial Revolutions 28912.4.1 First Industrial Revolution (1765) 29012.4.2 Second Industrial Revolution (1870) 29012.4.3 Third Industrial Revolution (1969) 29012.4.4 Fourth Industrial Revolution 29112.5 Reasons for Shifting Towards Industry 4.0 29112.6 Role of AI in Industry 4.0 29212.7 Role of ML in Industry 4.0 29212.8 Role of Deep Learning in Industry 4.0 29312.9 Applications of AI, ML, and DL in Industry 4.0 29412.10 Challenges 29512.11 Top Companies That Use AI to Augment Manufacturing Processes in the Era of Industry 4.0 29612.12 Conclusion 297References 29713 The Implementation of AI and AI-Empowered Imaging System to Fight Against COVID-19—A Review 301Sanjay Chakraborty and Lopamudra Dey13.1 Introduction 30213.2 AI-Assisted Methods 30413.2.1 AI-Driven Tools to Diagnose COVID-19 and Drug Discovery 30413.2.2 AI-Empowered Image Processing to Diagnosis 30613.3 Optimistic Treatments and Cures 30713.4 Challenges and Future Research Issues 30813.5 Conclusion 308References 30914 Implementation of Machine Learning Techniques for the Analysis of Transmission Dynamics of COVID-19 313C. Vijayalakshmi and S. Bangusha Devi14.1 Introduction 31414.2 Data Analysis 31514.3 Methodology 31514.3.1 Linear Regression Model 31514.3.2 Time Series Model 31814.4 Results and Discussions 32014.4.1 Model Estimation and Studying its Adequacy 32314.4.2 Regression Model for Daily New Cases and New Deaths 33014.5 Conclusions 348References 348Index 351

SK Hafizul Islam received his PhD degree in Computer Science and Engineering in 2013 from the Indian Institute of Technology [IIT (ISM)] Dhanbad, Jharkhand, India. He is an assistant professor in the Department of Computer Science and Engineering, Indian Institute of Information Technology Kalyani (IIIT Kalyani), West Bengal, India. He has authored or coauthored 110 research papers in journals and conference proceedings.Debabrata Samanta is an assistant professor in the Department of Computer Science, CHRIST (Deemed to be University), Bangalore, India. He obtained his PhD in Computer Science and Engg. from the National Institute of Technology, Durgapur, India, in the area of SAR Image Processing. He is the owner of 17 Indian patents and has authored and coauthored more than 135 research papers in international journals.

• Preface xviiAcknowledgments xxiii1 Machine Learning Technologies in IoT EEG-Based Healthcare Prediction 1Karthikeyan M.P., Krishnaveni K. and Muthumani N.1.1 Introduction 21.1.1 Descriptive Analytics 31.1.2 Analytical Methods 31.1.3 Predictive Analysis 41.1.4 Behavioral Analysis 41.1.5 Data Interpretation 41.1.6 Classification 41.2 Related Works 71.3 Problem Definition 91.4 Research Methodology 91.4.1 Components Used 101.4.2 Specifications and Description About Components 101.4.2.1 Arduino 101.4.2.2 EEG Sensor—Mindwave Mobile Headset 111.4.2.3 Raspberry pi 121.4.2.4 Working 131.4.3 Cloud Feature Extraction 131.4.4 Feature Optimization 141.4.5 Classification and Validation 151.5 Result and Discussion 161.5.1 Result 161.5.2 Discussion 231.6 Conclusion 271.6.1 Future Scope 27References 282 Smart Health Application for Remote Tracking of Ambulatory Patients 33Shariq Aziz Butt, Muhammad Waqas Anjum, Syed Areeb Hassan, Arindam Garai and Edeh Michael Onyema2.1 Introduction 342.2 Literature Work 342.3 Smart Computing for Smart Health for Ambulatory Patients 352.4 Challenges With Smart Health 362.4.1 Emergency Support 362.4.2 The Issue With Chronic Disease Monitoring 382.4.3 An Issue With the Tele-Medication 382.4.4 Mobility of Doctor 402.4.5 Application User Interface Issue 402.5 Security Threats 412.5.1 Identity Privacy 412.5.2 Query Privacy 422.5.3 Location of Privacy 422.5.4 Footprint Privacy and Owner Privacy 432.6 Applications of Fuzzy Set Theory in Healthcare and Medical Problems 432.7 Conclusion 51References 513 Data-Driven Decision Making in IoT Healthcare Systems—COVID-19: A Case Study 57Saroja S., Haseena S. and Blessa Binolin Pepsi M.3.1 Introduction 583.1.1 Pre-Processing 593.1.2 Classification Algorithms 603.1.2.1 Dummy Classifier 603.1.2.2 Support Vector Machine (SVM) 603.1.2.3 Gradient Boosting 613.1.2.4 Random Forest 623.1.2.5 Ada Boost 633.2 Experimental Analysis 633.3 Multi-Criteria Decision Making (MCDM) Procedure 633.3.1 Simple Multi Attribute Rating Technique (SMART) 643.3.1.1 COVID-19 Disease Classification Using SMART 643.3.2 Weighted Product Model (WPM) 663.3.2.1 COVID-19 Disease Classification Using WPM 663.3.3 Method for Order Preference by Similarity to the Ideal Solution (TOPSIS) 673.3.3.1 COVID-19 Disease Classification Using TOPSIS 683.4 Conclusion 69References 694 Touch and Voice-Assisted Multilingual Communication Prototype for ICU Patients Specific to COVID-19 71B. Rajesh Kanna and C.Vijayalakshmi4.1 Introduction and Motivation 724.1.1 Existing Interaction Approaches and Technology 734.1.2 Challenges and Gaps 744.2 Proposed Prototype of Touch and Voice-Assisted Multilingual Communication 754.3 A Sample Case Study 824.4 Conclusion 82References 845 Cloud-Assisted IoT System for Epidemic Disease Detection and Spread Monitoring 87Himadri Nath Saha, Reek Roy and Sumanta Chakraborty5.1 Introduction 885.2 Background & Related Works 925.3 Proposed Model 985.3.1 ThinkSpeak 1005.3.2 Blood Oxygen Saturation (SpO2) 1005.3.3 Blood Pressure (BP) 1015.3.4 Electrocardiogram (ECG) 1015.3.5 Body Temperature (BT) 1025.3.6 Respiration Rate (RR) 1025.3.7 Environmental Parameters 1035.4 Methodology 1035.5 Performance Analysis 1105.6 Future Research Direction 1115.7 Conclusion 112References 1136 Impact of Healthcare 4.0 Technologies for Future Capacity Building to Control Epidemic Diseases 115Himadri Nath Saha, Sumanta Chakraborty, Sourav Paul, Rajdeep Ghosh and Dipanwita Chakraborty Bhattacharya6.1 Introduction 1166.2 Background and Related Works 1206.3 System Design and Architecture 1286.4 Methodology 1316.5 Performance Analysis 1386.6 Future Research Direction 1386.7 Conclusion 139References 1397 Security and Privacy of IoT Devices in Healthcare Systems 143Himadri Nath Saha and Subhradip Debnath7.1 Introduction 1447.2 Background and Related Works 1457.3 Proposed System Design and Architecture 1477.3.1 Modules 1487.3.1.1 Wireless Body Area Network 1487.3.1.2 Centralized Network Coordinator 1497.3.1.3 Local Server 1497.3.1.4 Cloud Server 1507.3.1.5 Dedicated Network Connection 1517.4 Methodology 1517.5 Performance Analysis 1607.6 Future Research Direction 1617.7 Conclusion 163References 1648 An IoT-Based Diet Monitoring Healthcare System for Women 167Suganyadevi S., Shamia D. and Balasamy K.8.1 Introduction 1688.2 Background 1778.2.1 Food Consumption 1778.2.2 Food Consumption Monitoring 1788.2.3 Health Monitoring Methods Using Physical Methodology 1798.2.3.1 Traditional Form of Self-Report 1798.2.3.2 Self-Reporting Methodology Through Smart Phones 1798.2.3.3 Food Frequency Questionnaire 1798.2.4 Methods for Health Tracking Using Automated Approach 1808.2.4.1 Pressure Process 1808.2.4.2 Surveillance Video Method 1808.2.4.3 Method of Doppler Sensing 1808.3 Necessity of Wearable Approach? 1818.4 Different Approaches for Wearable Sensing 1818.4.1 Approach of Acoustics 1828.4.1.1 Detection of Chewing 1828.4.1.2 Detection of Swallowing 1838.4.1.3 Shared Chewing/Swallowing Discovery 1838.5 Description of the Methodology 1848.6 Description of Various Components Used 1858.6.1 Sensors 1858.6.1.1 Sensors for Cardio-Vascular Monitoring 1858.6.1.2 Sensors for Activity Monitoring 1868.6.1.3 Sensors for Body Temperature Monitoring 1878.6.1.4 Sensor for Galvanic Skin Response (GSR) Monitoring 1888.6.1.5 Sensor for Monitoring the Blood Oxygen Saturation (SpO2 ) 1898.7 Strategy of Communication for Wearable Systems 1898.8 Conclusion 192References 1949 A Secure Framework for Protecting Clinical Data in Medical IoT Environment 203Balasamy K., Krishnaraj N., Ramprasath J. and Ramprakash P.9.1 Introduction 2039.1.1 Medical IoT Background & Perspective 2049.1.1.1 Medical IoT Communication Network 2049.2 Medical IoT Application Domains 2099.2.1 Smart Doctor 2099.2.2 Smart Medical Practitioner 2099.2.3 Smart Technology 2099.2.4 Smart Receptionist 2109.2.5 Disaster Response Systems (DRS) 2109.3 Medical IoT Concerns 2109.3.1 Security Concerns 2119.3.2 Privacy Concerns 2129.3.3 Trust Concerns 2129.4 Need for Security in Medical IoT 2129.5 Components for Enhancing Data Security in Medical IoT 2149.5.1 Confidentiality 2149.5.2 Integrity 2149.5.3 Authentication 2159.5.4 Non-Repudiation 2159.5.5 Privacy 2159.6 Vulnerabilities in Medical IoT Environment 2159.6.1 Patient Privacy Protection 2159.6.2 Patient Safety 2169.6.3 Unauthorized Access 2169.6.4 Medical IoT Security Constraints 2179.7 Solutions for IoT Healthcare Cyber-Security 2189.7.1 Architecture of the Smart Healthcare System 2189.7.1.1 Data Perception Layer 2189.7.1.2 Data Communication Layer 2199.7.1.3 Data Storage Layer 2199.7.1.4 Data Application Layer 2199.8 Execution of Trusted Environment 2209.8.1 Root of Trust Security Services 2209.8.2 Chain of Trust Security Services 2229.9 Patient Registration Using Medical IoT Devices 2239.9.1 Encryption 2249.9.2 Key Generation 2259.9.3 Security by Isolation 2259.9.4 Virtualization 2259.10 Trusted Communication Using Block Chain 2299.10.1 Record Creation Using IoT Gateways 2299.10.2 Accessibility to Patient Medical History 2309.10.3 Patient Enquiry With Hospital Authority 2309.10.4 Block Chain Based IoT System Architecture 2319.10.4.1 First Layer 2319.10.4.2 Second Layer 2319.10.4.3 Third Layer 2329.11 Conclusion 232References 23310 Efficient Data Transmission and Remote Monitoring System for IoT Applications 235Laith Farhan, Firas MaanAbdulsattar, Laith Alzubaidi, Mohammed A. Fadhel, Banu ÇalýþUslu and Muthana Al-Amidie10.1 Introduction 23610.2 Network Configuration 23610.2.1 Message Queuing Telemetry Transport (MQTT) Protocol 23810.2.2 Embedded Database SQLite 24210.2.3 Eclipse Paho Library 24210.2.4 Raspberry Pi Single Board Computer 24210.2.5 Custard Pi Add-On Board 24310.2.6 Pressure Transmitter (Type 663) 24410.3 Data Filtering and Predicting Processes 24510.3.1 Filtering Process 24510.3.2 Predicting Process 24610.3.3 Remote Monitoring Systems 24810.4 Experimental Setup 24910.4.1 Implementation Using Python 25110.4.1.1 Prerequisites 25110.4.2 Monitoring Data 25110.4.3 Experimental Results 25510.4.3.1 IoT Device Results 25510.4.3.2 Traditional Network Results 25710.5 Conclusion 261References 26111 IoT in Current Times and its Prospective Advancements 265T. Venkat Narayana Rao, Abhishek Duggirala, Muralidhar Kurni and Syed Tabassum Sultana11.1 Introduction 26611.1.1 Introduction to Industry 4.0 26611.1.2 Introduction to IoT 26611.1.3 Introduction to IIoT 26711.2 How IIoT Advances Industrial Engineering in Industry 4.0 Era 26711.3 IoT and its Current Applications 26811.3.1 Home Automation 26811.3.2 Wearables 26911.3.3 Connected Cars 26911.3.4 Smart Grid 26911.4 Application Areas of IIoT 27011.4.1 IIoT in Healthcare 27011.4.2 IIoT in Mining 27011.4.3 IIoT in Agriculture 27111.4.4 IIoT in Aerospace 27111.4.5 IIoT in Smart Cities 27211.4.6 IIoT in Supply Chain Management 27211.5 Challenges of Existing Systems 27211.5.1 Security 27211.5.2 Integration 27311.5.3 Connectivity Issues 27311.6 Future Advancements 27311.6.1 Data Analytics in IoT 27411.6.2 Edge Computing 27411.6.3 Secured IoT Through Blockchain 27411.6.4 A Fusion of AR and IoT 27511.6.5 Accelerating IoT Through 5G 27511.7 Case Study of DeWalt 27511.8 Conclusion 276References 27612 Reliance on Artificial Intelligence, Machine Learning and Deep Learning in the Era of Industry 4.0 281T. Venkat Narayana Rao, Akhila Gaddam, Muralidhar Kurni and K. Saritha12.1 Introduction to Artificial Intelligence 28212.1.1 History of AI 28212.1.2 Views of AI 28212.1.3 Types of AI 28312.1.4 Intelligent Agents 28412.2 AI and its Related Fields 28612.3 What is Industry 4.0? 28912.4 Industrial Revolutions 28912.4.1 First Industrial Revolution (1765) 29012.4.2 Second Industrial Revolution (1870) 29012.4.3 Third Industrial Revolution (1969) 29012.4.4 Fourth Industrial Revolution 29112.5 Reasons for Shifting Towards Industry 4.0 29112.6 Role of AI in Industry 4.0 29212.7 Role of ML in Industry 4.0 29212.8 Role of Deep Learning in Industry 4.0 29312.9 Applications of AI, ML, and DL in Industry 4.0 29412.10 Challenges 29512.11 Top Companies That Use AI to Augment Manufacturing Processes in the Era of Industry 4.0 29612.12 Conclusion 297References 29713 The Implementation of AI and AI-Empowered Imaging System to Fight Against COVID-19—A Review 301Sanjay Chakraborty and Lopamudra Dey13.1 Introduction 30213.2 AI-Assisted Methods 30413.2.1 AI-Driven Tools to Diagnose COVID-19 and Drug Discovery 30413.2.2 AI-Empowered Image Processing to Diagnosis 30613.3 Optimistic Treatments and Cures 30713.4 Challenges and Future Research Issues 30813.5 Conclusion 308References 30914 Implementation of Machine Learning Techniques for the Analysis of Transmission Dynamics of COVID-19 313C. Vijayalakshmi and S. Bangusha Devi14.1 Introduction 31414.2 Data Analysis 31514.3 Methodology 31514.3.1 Linear Regression Model 31514.3.2 Time Series Model 31814.4 Results and Discussions 32014.4.1 Model Estimation and Studying its Adequacy 32314.4.2 Regression Model for Daily New Cases and New Deaths 33014.5 Conclusions 348References 348Index 351

SK Hafizul Islam received his PhD degree in Computer Science and Engineering in 2013 from the Indian Institute of Technology [IIT (ISM)] Dhanbad, Jharkhand, India. He is an assistant professor in the Department of Computer Science and Engineering, Indian Institute of Information Technology Kalyani (IIIT Kalyani), West Bengal, India. He has authored or coauthored 110 research papers in journals and conference proceedings.Debabrata Samanta is an assistant professor in the Department of Computer Science, CHRIST (Deemed to be University), Bangalore, India. He obtained his PhD in Computer Science and Engg. from the National Institute of Technology, Durgapur, India, in the area of SAR Image Processing. He is the owner of 17 Indian patents and has authored and coauthored more than 135 research papers in international journals.

• Preface xviiAcknowledgments xxiii1 Machine Learning Technologies in IoT EEG-Based Healthcare Prediction 1Karthikeyan M.P., Krishnaveni K. and Muthumani N.1.1 Introduction 21.1.1 Descriptive Analytics 31.1.2 Analytical Methods 31.1.3 Predictive Analysis 41.1.4 Behavioral Analysis 41.1.5 Data Interpretation 41.1.6 Classification 41.2 Related Works 71.3 Problem Definition 91.4 Research Methodology 91.4.1 Components Used 101.4.2 Specifications and Description About Components 101.4.2.1 Arduino 101.4.2.2 EEG Sensor—Mindwave Mobile Headset 111.4.2.3 Raspberry pi 121.4.2.4 Working 131.4.3 Cloud Feature Extraction 131.4.4 Feature Optimization 141.4.5 Classification and Validation 151.5 Result and Discussion 161.5.1 Result 161.5.2 Discussion 231.6 Conclusion 271.6.1 Future Scope 27References 282 Smart Health Application for Remote Tracking of Ambulatory Patients 33Shariq Aziz Butt, Muhammad Waqas Anjum, Syed Areeb Hassan, Arindam Garai and Edeh Michael Onyema2.1 Introduction 342.2 Literature Work 342.3 Smart Computing for Smart Health for Ambulatory Patients 352.4 Challenges With Smart Health 362.4.1 Emergency Support 362.4.2 The Issue With Chronic Disease Monitoring 382.4.3 An Issue With the Tele-Medication 382.4.4 Mobility of Doctor 402.4.5 Application User Interface Issue 402.5 Security Threats 412.5.1 Identity Privacy 412.5.2 Query Privacy 422.5.3 Location of Privacy 422.5.4 Footprint Privacy and Owner Privacy 432.6 Applications of Fuzzy Set Theory in Healthcare and Medical Problems 432.7 Conclusion 51References 513 Data-Driven Decision Making in IoT Healthcare Systems—COVID-19: A Case Study 57Saroja S., Haseena S. and Blessa Binolin Pepsi M.3.1 Introduction 583.1.1 Pre-Processing 593.1.2 Classification Algorithms 603.1.2.1 Dummy Classifier 603.1.2.2 Support Vector Machine (SVM) 603.1.2.3 Gradient Boosting 613.1.2.4 Random Forest 623.1.2.5 Ada Boost 633.2 Experimental Analysis 633.3 Multi-Criteria Decision Making (MCDM) Procedure 633.3.1 Simple Multi Attribute Rating Technique (SMART) 643.3.1.1 COVID-19 Disease Classification Using SMART 643.3.2 Weighted Product Model (WPM) 663.3.2.1 COVID-19 Disease Classification Using WPM 663.3.3 Method for Order Preference by Similarity to the Ideal Solution (TOPSIS) 673.3.3.1 COVID-19 Disease Classification Using TOPSIS 683.4 Conclusion 69References 694 Touch and Voice-Assisted Multilingual Communication Prototype for ICU Patients Specific to COVID-19 71B. Rajesh Kanna and C.Vijayalakshmi4.1 Introduction and Motivation 724.1.1 Existing Interaction Approaches and Technology 734.1.2 Challenges and Gaps 744.2 Proposed Prototype of Touch and Voice-Assisted Multilingual Communication 754.3 A Sample Case Study 824.4 Conclusion 82References 845 Cloud-Assisted IoT System for Epidemic Disease Detection and Spread Monitoring 87Himadri Nath Saha, Reek Roy and Sumanta Chakraborty5.1 Introduction 885.2 Background & Related Works 925.3 Proposed Model 985.3.1 ThinkSpeak 1005.3.2 Blood Oxygen Saturation (SpO2) 1005.3.3 Blood Pressure (BP) 1015.3.4 Electrocardiogram (ECG) 1015.3.5 Body Temperature (BT) 1025.3.6 Respiration Rate (RR) 1025.3.7 Environmental Parameters 1035.4 Methodology 1035.5 Performance Analysis 1105.6 Future Research Direction 1115.7 Conclusion 112References 1136 Impact of Healthcare 4.0 Technologies for Future Capacity Building to Control Epidemic Diseases 115Himadri Nath Saha, Sumanta Chakraborty, Sourav Paul, Rajdeep Ghosh and Dipanwita Chakraborty Bhattacharya6.1 Introduction 1166.2 Background and Related Works 1206.3 System Design and Architecture 1286.4 Methodology 1316.5 Performance Analysis 1386.6 Future Research Direction 1386.7 Conclusion 139References 1397 Security and Privacy of IoT Devices in Healthcare Systems 143Himadri Nath Saha and Subhradip Debnath7.1 Introduction 1447.2 Background and Related Works 1457.3 Proposed System Design and Architecture 1477.3.1 Modules 1487.3.1.1 Wireless Body Area Network 1487.3.1.2 Centralized Network Coordinator 1497.3.1.3 Local Server 1497.3.1.4 Cloud Server 1507.3.1.5 Dedicated Network Connection 1517.4 Methodology 1517.5 Performance Analysis 1607.6 Future Research Direction 1617.7 Conclusion 163References 1648 An IoT-Based Diet Monitoring Healthcare System for Women 167Suganyadevi S., Shamia D. and Balasamy K.8.1 Introduction 1688.2 Background 1778.2.1 Food Consumption 1778.2.2 Food Consumption Monitoring 1788.2.3 Health Monitoring Methods Using Physical Methodology 1798.2.3.1 Traditional Form of Self-Report 1798.2.3.2 Self-Reporting Methodology Through Smart Phones 1798.2.3.3 Food Frequency Questionnaire 1798.2.4 Methods for Health Tracking Using Automated Approach 1808.2.4.1 Pressure Process 1808.2.4.2 Surveillance Video Method 1808.2.4.3 Method of Doppler Sensing 1808.3 Necessity of Wearable Approach? 1818.4 Different Approaches for Wearable Sensing 1818.4.1 Approach of Acoustics 1828.4.1.1 Detection of Chewing 1828.4.1.2 Detection of Swallowing 1838.4.1.3 Shared Chewing/Swallowing Discovery 1838.5 Description of the Methodology 1848.6 Description of Various Components Used 1858.6.1 Sensors 1858.6.1.1 Sensors for Cardio-Vascular Monitoring 1858.6.1.2 Sensors for Activity Monitoring 1868.6.1.3 Sensors for Body Temperature Monitoring 1878.6.1.4 Sensor for Galvanic Skin Response (GSR) Monitoring 1888.6.1.5 Sensor for Monitoring the Blood Oxygen Saturation (SpO2 ) 1898.7 Strategy of Communication for Wearable Systems 1898.8 Conclusion 192References 1949 A Secure Framework for Protecting Clinical Data in Medical IoT Environment 203Balasamy K., Krishnaraj N., Ramprasath J. and Ramprakash P.9.1 Introduction 2039.1.1 Medical IoT Background & Perspective 2049.1.1.1 Medical IoT Communication Network 2049.2 Medical IoT Application Domains 2099.2.1 Smart Doctor 2099.2.2 Smart Medical Practitioner 2099.2.3 Smart Technology 2099.2.4 Smart Receptionist 2109.2.5 Disaster Response Systems (DRS) 2109.3 Medical IoT Concerns 2109.3.1 Security Concerns 2119.3.2 Privacy Concerns 2129.3.3 Trust Concerns 2129.4 Need for Security in Medical IoT 2129.5 Components for Enhancing Data Security in Medical IoT 2149.5.1 Confidentiality 2149.5.2 Integrity 2149.5.3 Authentication 2159.5.4 Non-Repudiation 2159.5.5 Privacy 2159.6 Vulnerabilities in Medical IoT Environment 2159.6.1 Patient Privacy Protection 2159.6.2 Patient Safety 2169.6.3 Unauthorized Access 2169.6.4 Medical IoT Security Constraints 2179.7 Solutions for IoT Healthcare Cyber-Security 2189.7.1 Architecture of the Smart Healthcare System 2189.7.1.1 Data Perception Layer 2189.7.1.2 Data Communication Layer 2199.7.1.3 Data Storage Layer 2199.7.1.4 Data Application Layer 2199.8 Execution of Trusted Environment 2209.8.1 Root of Trust Security Services 2209.8.2 Chain of Trust Security Services 2229.9 Patient Registration Using Medical IoT Devices 2239.9.1 Encryption 2249.9.2 Key Generation 2259.9.3 Security by Isolation 2259.9.4 Virtualization 2259.10 Trusted Communication Using Block Chain 2299.10.1 Record Creation Using IoT Gateways 2299.10.2 Accessibility to Patient Medical History 2309.10.3 Patient Enquiry With Hospital Authority 2309.10.4 Block Chain Based IoT System Architecture 2319.10.4.1 First Layer 2319.10.4.2 Second Layer 2319.10.4.3 Third Layer 2329.11 Conclusion 232References 23310 Efficient Data Transmission and Remote Monitoring System for IoT Applications 235Laith Farhan, Firas MaanAbdulsattar, Laith Alzubaidi, Mohammed A. Fadhel, Banu ÇalýþUslu and Muthana Al-Amidie10.1 Introduction 23610.2 Network Configuration 23610.2.1 Message Queuing Telemetry Transport (MQTT) Protocol 23810.2.2 Embedded Database SQLite 24210.2.3 Eclipse Paho Library 24210.2.4 Raspberry Pi Single Board Computer 24210.2.5 Custard Pi Add-On Board 24310.2.6 Pressure Transmitter (Type 663) 24410.3 Data Filtering and Predicting Processes 24510.3.1 Filtering Process 24510.3.2 Predicting Process 24610.3.3 Remote Monitoring Systems 24810.4 Experimental Setup 24910.4.1 Implementation Using Python 25110.4.1.1 Prerequisites 25110.4.2 Monitoring Data 25110.4.3 Experimental Results 25510.4.3.1 IoT Device Results 25510.4.3.2 Traditional Network Results 25710.5 Conclusion 261References 26111 IoT in Current Times and its Prospective Advancements 265T. Venkat Narayana Rao, Abhishek Duggirala, Muralidhar Kurni and Syed Tabassum Sultana11.1 Introduction 26611.1.1 Introduction to Industry 4.0 26611.1.2 Introduction to IoT 26611.1.3 Introduction to IIoT 26711.2 How IIoT Advances Industrial Engineering in Industry 4.0 Era 26711.3 IoT and its Current Applications 26811.3.1 Home Automation 26811.3.2 Wearables 26911.3.3 Connected Cars 26911.3.4 Smart Grid 26911.4 Application Areas of IIoT 27011.4.1 IIoT in Healthcare 27011.4.2 IIoT in Mining 27011.4.3 IIoT in Agriculture 27111.4.4 IIoT in Aerospace 27111.4.5 IIoT in Smart Cities 27211.4.6 IIoT in Supply Chain Management 27211.5 Challenges of Existing Systems 27211.5.1 Security 27211.5.2 Integration 27311.5.3 Connectivity Issues 27311.6 Future Advancements 27311.6.1 Data Analytics in IoT 27411.6.2 Edge Computing 27411.6.3 Secured IoT Through Blockchain 27411.6.4 A Fusion of AR and IoT 27511.6.5 Accelerating IoT Through 5G 27511.7 Case Study of DeWalt 27511.8 Conclusion 276References 27612 Reliance on Artificial Intelligence, Machine Learning and Deep Learning in the Era of Industry 4.0 281T. Venkat Narayana Rao, Akhila Gaddam, Muralidhar Kurni and K. Saritha12.1 Introduction to Artificial Intelligence 28212.1.1 History of AI 28212.1.2 Views of AI 28212.1.3 Types of AI 28312.1.4 Intelligent Agents 28412.2 AI and its Related Fields 28612.3 What is Industry 4.0? 28912.4 Industrial Revolutions 28912.4.1 First Industrial Revolution (1765) 29012.4.2 Second Industrial Revolution (1870) 29012.4.3 Third Industrial Revolution (1969) 29012.4.4 Fourth Industrial Revolution 29112.5 Reasons for Shifting Towards Industry 4.0 29112.6 Role of AI in Industry 4.0 29212.7 Role of ML in Industry 4.0 29212.8 Role of Deep Learning in Industry 4.0 29312.9 Applications of AI, ML, and DL in Industry 4.0 29412.10 Challenges 29512.11 Top Companies That Use AI to Augment Manufacturing Processes in the Era of Industry 4.0 29612.12 Conclusion 297References 29713 The Implementation of AI and AI-Empowered Imaging System to Fight Against COVID-19—A Review 301Sanjay Chakraborty and Lopamudra Dey13.1 Introduction 30213.2 AI-Assisted Methods 30413.2.1 AI-Driven Tools to Diagnose COVID-19 and Drug Discovery 30413.2.2 AI-Empowered Image Processing to Diagnosis 30613.3 Optimistic Treatments and Cures 30713.4 Challenges and Future Research Issues 30813.5 Conclusion 308References 30914 Implementation of Machine Learning Techniques for the Analysis of Transmission Dynamics of COVID-19 313C. Vijayalakshmi and S. Bangusha Devi14.1 Introduction 31414.2 Data Analysis 31514.3 Methodology 31514.3.1 Linear Regression Model 31514.3.2 Time Series Model 31814.4 Results and Discussions 32014.4.1 Model Estimation and Studying its Adequacy 32314.4.2 Regression Model for Daily New Cases and New Deaths 33014.5 Conclusions 348References 348Index 351