Smart Systems for Industrial Applications

C. Venkatesh, PhD is Professor and Principal, Sengunthar Engineering College, India, and has 28 years of teaching experience. He has published 5 patents, about 80 research papers in international journals, and about 70 papers in international and national conferences. N. Rengarajan, PhD is Professor and Principal, Nandha Engineering College, India and has more than three decades of experience. He has published 8 patents, 70 papers in international journals, and 20 papers in national and international conferences. P. Ponmurugan, PhD is an associate professor, Sri Krishna College of Technology, India has almost a decade of experience in academics. He has published 11 patents and about 40 papers in international journals and conferences. He was awarded the “Best Young Engineer” by IEI – Erode Local Centre and “Young Scientist” by the International Association of Research and Developed Organization (IARDO). S. Balamurugan, PhD, SMIEEE and ACM Distinguished Speaker, received his PhD from Anna University, India. He has published 57 books, 300+ international journals/conferences, and 100 patents. He is the Director of the Albert Einstein Engineering and Research Labs. He is also the Vice-Chairman of the Renewable Energy Society of India (RESI). He is serving as a research consultant to many companies, startups, SMEs, and MSMEs. He has received numerous awards for research at national and international levels.

• Preface xvii1 AI-Driven Information and Communication Technologies, Services, and Applications for Next-Generation Healthcare System 1Vijayakumar Ponnusamy, A. Vasuki, J. Christopher Clement and P. Eswaran1.1 Introduction: Overview of Communication Technology and Services for Healthcare 21.2 AI-Driven Communication Technology in Healthcare 61.2.1 Technologies Empowering in Healthcare 61.2.2 AI in Diagnosis 71.2.3 Conversion Protocols 81.2.4 AI in Treatment Assistant 91.2.5 AI in the Monitoring Process 101.2.6 Challenges of AI in Healthcare 101.3 AI-Driven mHealth Communication System and Services 101.3.1 Embedding of Handheld Imaging Platforms With mHealth Devices 121.3.2 The Adaptability of POCUS in Telemedicine 121.4 AI-Driven Body Area Network Communication Technologies and Applications 131.4.1 Features 161.4.2 Communication Architecture of Wireless Body Area Networks 161.4.3 Role of AI in WBAN Architecture 171.4.4 Medical Applications 181.4.5 Nonmedical Applications 181.4.6 Challenges 181.5 AI-Driven IoT Device Communication Technologies and Healthcare Applications 201.5.1 AI’s and IoT’s Role in Healthcare 201.5.2 Creating Efficient Communication Framework for Remote Healthcare Management 211.5.3 Developing Autonomous Capability is Key for Remote Healthcare Management 221.5.4 Enabling Data Privacy and Security in the Field of Remote Healthcare Management 241.6 AI-Driven Augmented and Virtual Reality–Based Communication Technologies and Healthcare Applications 251.6.1 Clinical Applications of Communication-Based AI and Augmented Reality 271.6.2 Surgical Applications of Communication-Based on Artificial Intelligence and Augmented Reality 28References 302 Pneumatic Position Servo System Using Multi-Variable Multi-Objective Genetic Algorithm–Based Fractional-Order PID Controller 33D.Magdalin Mary, V.Vanitha and G.Sophia Jasmine2.1 Introduction 342.2 Pneumatic Servo System 362.3 Existing System Analysis 382.4 Proposed Controller and Its Modeling 402.4.1 Modeling of Fractional-Order PID Controller 402.4.1.1 Fractional-Order Calculus 402.4.1.2 Fractional-Order PID Controller 422.5 Genetic Algorithm 432.5.1 GA Optimization Methodology 432.5.1.1 Initialization 442.5.1.2 Fitness Function 442.5.1.3 Evaluation and Selection 442.5.1.4 Crossover 452.5.1.5 Mutation 452.5.2 GA Parameter Tuning 462.6 Simulation Results and Discussion 472.6.1 MATLAB Genetic Algorithm Tool Box 472.6.2 Simulation Results 472.6.2.1 Reference = 500 (Error) 482.6.2.2 Reference = 500 522.6.2.3 Reference = 1,500 522.6.2.4 Analysis Report 562.7 Hardware Results 562.7.1 Reference = 500 582.7.2 Reference = 1,500 592.8 Conclusion 59References 593 Improved Weighted Distance Hop Hyperbolic Prediction–Based Reliable Data Dissemination (IWDH-HP-RDD) Mechanism for Smart Vehicular Environments 63Sengathir Janakiraman, M. Deva Priya and A. Christy Jeba Malar3.1 Introduction 643.2 Related Work 673.2.1 Extract of the Literature 703.3 Proposed Improved Weighted Distance Hop Hyperbolic Prediction–Based Reliable Data Dissemination (IWDH-HP-RDD) Mechanism for Smart Vehicular Environments 713.4 Simulation Results and Analysis of the Proposed IWDH-HP-RDD Scheme 793.5 Conclusion 89References 904 Remaining Useful Life Prediction of Small and Large Signal Analog Circuits Using Filtering Algorithms 93Sathiyanathan M., Anandhakumar K., Jaganathan S. and Subashkumar C. S.4.1 Introduction 944.2 Literature Survey 954.3 System Architecture 984.4 Remaining Useful Life Prediction 994.4.1 Initialization 994.4.2 Proposal Distribution 1004.4.3 Time Update 1014.4.4 Relative Entropy in Particle Resampling 1014.4.5 RUL Prediction 1024.5 Results and Discussion 1034.6 Conclusion 111References 1115 AI in Healthcare 115S. Menaga and J. Paruvathavardhini5.1 Introduction 1165.1.1 What is Artificial Intelligence? 1175.1.2 Machine Learning – Neural Networks and Deep Learning 1175.1.3 Natural Language Processing 1195.2 Need of AI in Electronic Health Record 1195.2.1 How Does AI/ML Fit Into EHR? 1205.2.2 Natural Language Processing (NLP) 1215.2.3 Data Analytics and Representation 1225.2.4 Predictive Investigation 1225.2.5 Administrative and Security Consistency 1225.3 The Trending Role of AI in Pharmaceutical Development 1235.3.1 Drug Discovery and Design 1245.3.2 Diagnosis of Biomedical and Clinical Data 1255.3.3 Rare Diseases and Epidemic Prediction 1255.3.4 Applications of AI in Pharma 1265.3.5 AI in Marketing 1265.3.6 Review of the Companies That Use AI 1265.4 AI in Surgery 1275.4.1 3D Printing 1275.4.2 Stem Cells 1285.4.3 Patient Care 1285.4.4 Training and Future Surgical Team 1295.5 Artificial Intelligence in Medical Imaging 1315.5.1 In Cardio Vascular Abnormalities 1315.5.2 In Fractures and Musculoskeletal Injuries 1325.5.3 In Neurological Diseases and Thoracic Complications 1335.5.4 In Detecting Cancers 1345.6 AI in Patient Monitoring and Wearable Health Devices 1345.6.1 Monitoring Health Through Wearable’s and Personal Devices 1355.6.2 Making Smartphone Selfies Into Powerful Diagnostic Tools 1365.7 Revolutionizing of AI in Medicinal Decision-Making at the Bedside 1375.8 Future of AI in Healthcare 1375.9 Conclusion 139References 1396 Introduction of Artificial Intelligence 141R. Vishalakshi and S. Mangai6.1 Introduction 1426.1.1 Intelligence 1426.1.2 Types of Intelligence 1436.1.3 A Brief History of Artificial Intelligence From 1923 till 2000 1446.2 Introduction to the Philosophy Behind Artificial Intelligence 1456.2.1 Programming With and Without AI 1476.3 Basic Functions of Artificial Intelligence 1476.3.1 Categories of Artificial Intelligence 1486.3.1.1 Reactive Machines 1486.3.1.2 Limited Memory 1486.3.1.3 Theory of Mind 1496.3.1.4 Self-Awareness 1496.4 Existing Technology and Its Review 1496.4.1 Tesla’s Autopilot 1496.4.2 Boxever 1506.4.3 Fin Gesture 1506.4.4 AI Robot 1526.4.5 Vinci 1536.4.6 AI Glasses 1536.4.7 Affectiva 1536.4.8 AlphaGo Beats 1546.4.9 Cogito 1546.4.10 Siri and Alexa 1556.4.11 Pandora’s 1576.5 Objectives 1576.5.1 Major Goals 1576.5.2 Need for Artificial Intelligence 1586.5.3 Distinction Between Artificial Intelligence and Business Intelligence 1586.6 Significance of the Study 1596.6.1 Segments of Master Frameworks 1606.6.1.1 User Interface 1626.6.1.2 Expert Systems 1636.6.1.3 Inference Engine 1636.6.1.4 Voice Recognition 1646.6.1.5 Robots 1646.7 Discussion 1646.7.1 Artificial Intelligence and Design Practice 1646.8 Applications of AI 1676.8.1 AI Has Been Developing a Huge Number of Tools Necessary to Find a Solution to the Most Challenging Problems in Computer Science 1686.8.2 Future of AI 1686.9 Conclusion 169References 1707 Artificial Intelligence in Healthcare: Algorithms and Decision Support Systems 173S. Palanivel Rajan and M.Paranthaman7.1 Introduction 1737.2 Machine Learning Work Flow and Applications in Healthcare 1767.2.1 Formatting and Cleaning Data 1777.2.2 Supervised and Unsupervised Learning 1787.2.3 Linear Discriminant Analysis 1787.2.4 K-Nearest Neighbor 1797.2.5 K-Means Clustering 1807.2.6 Random Forest 1817.2.7 Decision Tree 1817.2.8 Support Vector Machine 1827.2.9 Artificial Neural Network 1837.2.10 Natural Language Processing 1847.2.11 Deep Learning 1857.2.12 Ensembles 1867.3 Commercial Decision Support Systems Based on AI 1877.3.1 Personal Genome Diagnostics 1887.3.2 Tempus 1887.3.3 iCarbonX—Manage Your Digital Life 1897.3.4 H 2 O.ai 1897.3.5 Google DeepMind 1897.3.6 Buoy Health 1897.3.7 PathAI 1907.3.8 Beth Israel Deaconess Medical Center 1907.3.9 Bioxcel Therapeutics 1907.3.10 Berg 1917.3.11 Enlitic 1917.3.12 Deep Genomics 1917.3.13 Freenome 1927.3.14 CloudMedX 1927.3.15 Proscia 1927.4 Conclusion 193References 1938 Smart Homes and Smart Cities 199C. N. Marimuthu and G. Arthy8.1 Smart Homes 1998.1.1 Introduction 1998.1.2 Evolution of Smart Home 2008.1.3 Smart Home Architecture 2028.1.3.1 Smart Electrical Devices or Smart Plugs 2028.1.3.2 Home Intelligent Terminals or Home Area Networks 2038.1.3.3 Master Network 2038.1.4 Smart Home Technologies 2048.1.5 Smart Grid Technology 2068.1.6 Smart Home Applications 2068.1.6.1 Smart Home in the Healthcare of Elderly People 2068.1.6.2 Smart Home in Education 2078.1.6.3 Smart Lighting 2078.1.6.4 Smart Surveillance 2078.1.7 Advantages and Disadvantages of Smart Homes 2078.2 Smart Cities 2088.2.1 Introduction 2088.2.2 Smart City Framework 2098.2.3 Architecture of Smart Cities 2108.2.4 Components of Smart Cities 2118.2.4.1 Smart Technology 2128.2.4.2 Smart Infrastructure 2128.2.4.3 Smart Mobility 2148.2.4.4 Smart Buildings 2158.2.4.5 Smart Energy 2168.2.4.6 Smart Governance 2178.2.4.7 Smart Healthcare 2188.2.5 Characteristics of Smart Cities 2198.2.6 Challenges in Smart Cities 2218.2.7 Conclusion 222References 2229 Application of AI in Healthcare 225V. Priya and S. Prabu9.1 Introduction 2269.1.1 Supervised Learning Process 2269.1.2 Unsupervised Learning Process 2279.1.3 Semi-Supervised Learning Process 2279.1.4 Reinforcement Learning Process 2279.1.5 Healthcare System Using ml 2289.1.6 Primary Examples of ML’s Implementation in the Healthcare 2289.1.6.1 AI-Assisted Radiology and Pathology 2289.1.6.2 Physical Robots for Surgery Assistance 2299.1.6.3 With the Assistance of AI/ML Techniques, Drug Discovery 2319.1.6.4 Precision Medicine and Preventive Healthcare in the Future 2329.2 Related Works 2329.2.1 In Healthcare, Data Driven AI Models 2329.2.2 Support Vector Machine 2339.2.3 Artificial Neural Networks 2339.2.4 Logistic Regression 2359.2.5 Random Forest 2359.2.6 Discriminant Analysis 2369.2.7 Naïve Bayes 2369.2.8 Natural Language Processing 2369.2.9 Tf-idf 2369.2.10 Word Vectors 2379.2.11 Deep Learning 2379.2.12 Convolutional Neural Network 2379.3 dl Frameworks for Identifying Disease 2409.3.1 TensorFlow 2409.3.2 High Level APIs 2409.3.3 Estimators 2409.3.4 Accelerators 2419.3.5 Low Level APIs 2419.4 Proposed Work 2419.4.1 Application of AI in Finding Heart Disease 2419.4.2 Data Pre-Processing and Classification of Heart Disease 2419.5 Results and Discussions 2449.6 Conclusion 246References 24610 Battery Life and Electric Vehicle Range Prediction 249Ravikrishna S., Subash Kumar C. S. and Sundaram M.10.1 Introduction 25010.2 Different Stages of Electrification of Electric Vehicles 25310.2.1 Starting and Stopping 25310.2.2 Regenerative Braking 25310.2.3 Motor Control 25310.2.4 EV Drive 25410.3 Estimating SoC 25410.3.1 Cell Capacity 25410.3.2 Calendar Life 25510.3.3 Cycling Life 25510.3.4 SoH Based on Capacity Fade 25510.3.5 SoH Based on Power Fade 25510.3.6 Open Circuit Voltage 25510.3.7 Impedance Spectroscopy 25510.3.8 Model-Based Approach 25610.4 Kalman Filter 25710.4.1 Sigma Point Kalman Filter 25710.4.2 Six Step Process 25810.5 Estimating SoH 26010.6 Results and Discussion 26210.7 Conclusion 267References 26711 AI-Driven Healthcare Analysis 269N. Kasthuri and T. Meeradevi11.1 Introduction 27011.2 Literature Review 27111.3 Feature Extraction 27511.3.1 GLCM Feature Descriptors 27511.4 Classifiers 27611.4.1 Stochastic Gradient Descent Classifier 27611.4.2 Naïve Bayes Classifier 27611.4.3 K-Nearest Neighbor Classifier 27711.4.4 Support Vector Machine Classifier 27711.4.5 Random Forest Classifier 27811.4.6 Working of Random Forest Algorithm 27811.4.7 Convolutional Neural Network 27811.4.7.1 Activation Function 28111.4.7.2 Pooling Layer 28111.4.7.3 Fully Connected Layer (FC) 28111.5 Results and Conclusion 28211.5.1 5,000 Images 28211.5.2 10,000 Images 283References 28412 A Novel Technique for Continuous Monitoring of Fuel Adulteration 287Rajalakshmy P., Varun R., Subha Hency Jose P. and Rajasekaran K.12.1 Introduction 28812.1.1 Literature Review 28912.1.2 Overview 29012.1.3 Objective 29012.2 Existing Method 29012.2.1 Module-1 Water 29112.2.2 Module-2 Petrol 29312.2.3 Petrol Density Measurement 29312.2.4 Block Diagram 29312.2.5 Components of the System 29412.2.5.1 Pressure Instrument 29412.2.5.2 Sensor 29412.2.6 Personal Computer 29512.2.7 Petrol Density Measurement Instrument Setup 29512.2.7.1 Setup 1 29612.2.7.2 Setup 2 29812.2.7.3 Setup 3 29812.2.7.4 Setup 4 29812.2.7.5 Final Setup 29812.3 Interfacing MPX2010DP with INA 114 29912.3.1 I2C Bus Configuration for Honeywell Sensor 29912.3.2 Pressure and Temperature Output Through I2C 30012.4 Results and Discussion 30212.5 Conclusion 303References 30413 Improved Merkle Hash and Trapdoor Function–Based Secure Mutual Authentication (IMH-TF-SMA) Mechanism for Securing Smart Home Environment 307M. Deva Priya, Sengathir Janakiraman and A. Christy Jeba Malar13.1 Introduction 30813.2 Related Work 31013.3 Proposed Improved Merkle Hash and Trapdoor Function– Based Secure Mutual Authentication (IMH-TF-SMA) Mechanism for Securing Smart Home Environment 31613.3.1 Threat Model 31713.3.2 IMH-TF-SMA Mechanism 31713.3.2.1 Phase of Initialization 32013.3.2.2 Phase of Addressing 32013.3.2.3 Phase of Registration 32013.3.2.4 Phase of Login Authentication 32113.3.2.5 Phase of Session Agreement 32113.4 Results and Discussion 32513.5 Conclusion 330References 33014 Smart Sensing Technology 333S. Palanivel Rajan and T. Abirami14.1 Introduction 33314.1.1 Sensor 33314.1.1.1 Real-Time Example of Sensor 33414.1.1.2 Definition of Sensors 33514.1.1.3 Characteristics of Sensors 33514.1.1.4 Classification of Sensors 33614.1.1.5 Types of Sensors 33614.1.2 IoT (Internet of Things) 34014.1.2.1 Trends and Characteristics 34014.1.2.2 Definition 34014.1.2.3 Flow Chart of IoT 34114.1.2.4 IoT Phases 34114.1.2.5 Phase Chart 34214.1.2.6 IoT Protocol 34214.1.3 Wpan 34314.1.3.1 IEEE 802.15.1 Overview 34414.1.3.2 Bluetooth 34414.1.3.3 History of Bluetooth 34414.1.3.4 How Bluetooth Works 34514.1.3.5 Bluetooth Specifications 34514.1.3.6 Advantages of Bluetooth Technology 34614.1.3.7 Applications 34714.1.4 Zigbee (IEEE 802.15.4) 34814.1.4.1 Introduction 34814.1.4.2 Architecture of Zigbee 34914.1.4.3 Zigbee Devices 35114.1.4.4 Operating Modes of Zigbee 35114.1.4.5 Zigbee Topologies 35214.1.4.6 Applications of Zigbee Technology 35314.1.5 Wlan 35314.1.5.1 Introduction 35314.1.5.2 Advantages of WLANs 35514.1.5.3 Drawbacks of WLAN 35514.1.6 Gsm 35614.1.6.1 Introduction 35614.1.6.2 Composition of GSM Networks 35614.1.6.3 Security 35814.1.7 Smart Sensor 35814.1.7.1 Development History of Smart Sensors 35814.1.7.2 Internal Parts of Smart Transmitter 35914.1.7.3 Applications 36114.1.8 Conclusion 365References 365Index 367