Preface xix 1 Internet of Robotic Things: A New Architecture and Platform 1V. Vijayalakshmi, S. Vimal and M. Saravanan 1.1 Introduction 2 1.1.1 Architecture 3 1.1.1.1 Achievability of the Proposed Architecture 6 1.1.1.2 Qualities of IoRT Architecture 6 1.1.1.3 Reasonable Existing Robots for IoRT Architecture 8 1.2 Platforms 9 1.2.1 Cloud Robotics Platforms 9 1.2.2 IoRT Platform 10 1.2.3 Design a Platform 11 1.2.4 The Main Components of the Proposed Approach 11 1.2.5 IoRT Platform Design 12 1.2.6 Interconnection Design 15 1.2.7 Research Methodology 17 1.2.8 Advancement Process—Systems Thinking 17 1.2.8.1 Development Process 17 1.2.9 Trial Setup-to Confirm the Functionalities 18 1.3 Conclusion 20 1.4 Future Work 21 References 21 2 Brain–Computer Interface Using Electroencephalographic Signals for the Internet of Robotic Things 27R. Raja Sudharsan and J. Deny 2.1 Introduction 28 2.2 Electroencephalography Signal Acquisition Methods 30 2.2.1 Invasive Method 31 2.2.2 Non-Invasive Method 32 2.3 Electroencephalography Signal-Based BCI 32 2.3.1 Prefrontal Cortex in Controlling Concentration Strength 33 2.3.2 Neurosky Mind-Wave Mobile 34 2.3.2.1 Electroencephalography Signal Processing Devices 34 2.3.3 Electromyography Signal Extraction of Features and Its Signal Classifications 37 2.4 IoRT-Based Hardware for BCI 40 2.5 Software Setup for IoRT 40 2.6 Results and Discussions 42 2.7 Conclusion 47 References 48 3 Automated Verification and Validation of IoRT Systems 55S.V. Gayetri Devi and C. Nalini 3.1 Introduction 56 3.1.1 Automating V&V—An Important Key to Success 58 3.2 Program Analysis of IoRT Applications 59 3.2.1 Need for Program Analysis 59 3.2.2 Aspects to Consider in Program Analysis of IoRT Systems 59 3.3 Formal Verification of IoRT Systems 61 3.3.1 Automated Model Checking 61 3.3.2 The Model Checking Process 62 3.3.2.1 PRISM 65 3.3.2.2 UPPAAL 66 3.3.2.3 SPIN Model Checker 67 3.3.3 Automated Theorem Prover 69 3.3.3.1 ALT-ERGO 70 3.3.4 Static Analysis 71 3.3.4.1 CODESONAR 72 3.4 Validation of IoRT Systems 73 3.4.1 IoRT Testing Methods 79 3.4.2 Design of IoRT Test 80 3.5 Automated Validation 80 3.5.1 Use of Service Visualization 82 3.5.2 Steps for Automated Validation of IoRT Systems 82 3.5.3 Choice of Appropriate Tool for Automated Validation 84 3.5.4 IoRT Systems Open Source Automated Validation Tools 85 3.5.5 Some of Significant Open Source Test Automation Frameworks 86 3.5.6 Finally IoRT Security Testing 86 3.5.7 Prevalent Approaches for Security Validation 87 3.5.8 IoRT Security Tools 87 References 88 4 Light Fidelity (Li-Fi) Technology: The Future Man–Machine–Machine Interaction Medium 91J.M. Gnanasekar and T. Veeramakali 4.1 Introduction 92 4.1.1 Need for Li-Fi 94 4.2 Literature Survey 94 4.2.1 An Overview on Man-to-Machine Interaction System 95 4.2.2 Review on Machine to Machine (M2M) Interaction 96 4.2.2.1 System Model 97 4.3 Light Fidelity Technology 98 4.3.1 Modulation Techniques Supporting Li-Fi 99 4.3.1.1 Single Carrier Modulation (SCM) 100 4.3.1.2 Multi Carrier Modulation 100 4.3.1.3 Li-Fi Specific Modulation 101 4.3.2 Components of Li-Fi 102 4.3.2.1 Light Emitting Diode (LED) 102 4.3.2.2 Photodiode 103 4.3.2.3 Transmitter Block 103 4.3.2.4 Receiver Block 104 4.4 Li-Fi Applications in Real Word Scenario 105 4.4.1 Indoor Navigation System for Blind People 105 4.4.2 Vehicle to Vehicle Communication 106 4.4.3 Li-Fi in Hospital 107 4.4.4 Li-Fi Applications for Pharmacies and the Pharmaceutical Industry 109 4.4.5 Li-Fi in Workplace 110 4.5 Conclusion 111 References 111 5 Healthcare Management-Predictive Analysis (IoRT) 113L. Mary Gladence, V. Maria Anu and Y. Bevish Jinila 5.1 Introduction 114 5.1.1 Naive Bayes Classifier Prediction for SPAM 115 5.1.2 Internet of Robotic Things (IoRT) 115 5.2 Related Work 116 5.3 Fuzzy Time Interval Sequential Pattern (FTISPAM) 117 5.3.1 FTI SPAM Using GA Algorithm 118 5.3.1.1 Chromosome Generation 119 5.3.1.2 Fitness Function 120 5.3.1.3 Crossover 120 5.3.1.4 Mutation 121 5.3.1.5 Termination 121 5.3.2 Patterns Matching Using SCI 121 5.3.3 Pattern Classification Based on SCI Value 122 5.3.4 Significant Pattern Evaluation 123 5.4 Detection of Congestive Heart Failure Using Automatic Classifier 124 5.4.1 Analyzing the Dataset 125 5.4.2 Data Collection 126 5.4.2.1 Long-Term HRV Measures 127 5.4.2.2 Attribute Selection 128 5.4.3 Automatic Classifier—Belief Network 128 5.5 Experimental Analysis 130 5.6 Conclusion 132 References 134 6 Multimodal Context-Sensitive Human Communication Interaction System Using Artificial Intelligence-Based Human-Centered Computing 137S. Murugan, R. Manikandan and Ambeshwar Kumar 6.1 Introduction 138 6.2 Literature Survey 141 6.3 Proposed Model 145 6.3.1 Multimodal Data 145 6.3.2 Dimensionality Reduction 146 6.3.3 Principal Component Analysis 147 6.3.4 Reduce the Number of Dimensions 148 6.3.5 CNN 148 6.3.6 CNN Layers 149 6.3.6.1 Convolution Layers 149 6.3.6.2 Padding Layer 150 6.3.6.3 Pooling/Subsampling Layers 150 6.3.6.4 Nonlinear Layers 151 6.3.7 ReLU 151 6.3.7.1 Fully Connected Layers 152 6.3.7.2 Activation Layer 152 6.3.8 LSTM 152 6.3.9 Weighted Combination of Networks 153 6.4 Experimental Results 155 6.4.1 Accuracy 155 6.4.2 Sensibility 156 6.4.3 Specificity 156 6.4.4 A Predictive Positive Value (PPV) 156 6.4.5 Negative Predictive Value (NPV) 156 6.5 Conclusion 159 6.6 Future Scope 159 References 160 7 AI, Planning and Control Algorithms for IoRT Systems 163T.R. Thamizhvani, R.J. Hemalatha, R. Chandrasekaran and A. Josephin Arockia Dhivya 7.1 Introduction 164 7.2 General Architecture of IoRT 167 7.2.1 Hardware Layer 168 7.2.2 Network Layer 168 7.2.3 Internet Layer 168 7.2.4 Infrastructure Layer 168 7.2.5 Application Layer 169 7.3 Artificial Intelligence in IoRT Systems 170 7.3.1 Technologies of Robotic Things 170 7.3.2 Artificial Intelligence in IoRT 172 7.4 Control Algorithms and Procedures for IoRT Systems 180 7.4.1 Adaptation of IoRT Technologies 183 7.4.2 Multi-Robotic Technologies 186 7.5 Application of IoRT in Different Fields 187 References 190 8 Enhancements in Communication Protocols That Powered IoRT 193T. Anusha and M. Pushpalatha 8.1 Introduction 194 8.2 IoRT Communication Architecture 194 8.2.1 Robots and Things 196 8.2.2 Wireless Link Layer 197 8.2.3 Networking Layer 197 8.2.4 Communication Layer 198 ­­8.2.5 Application Layer 198 8.3 Bridging Robotics and IoT 198 8.4 Robot as a Node in IoT 200 8.4.1 Enhancements in Low Power WPANs 200 8.4.1.1 Enhancements in IEEE 802.15.4 200 8.4.1.2 Enhancements in Bluetooth 201 8.4.1.3 Network Layer Protocols 202 8.4.2 Enhancements in Low Power WLANs 203 8.4.2.1 Enhancements in IEEE 802.11 203 8.4.3 Enhancements in Low Power WWANs 204 8.4.3.1 LoRaWAN 205 8.4.3.2 5G 205 8.5 Robots as Edge Device in IoT 206 8.5.1 Constrained RESTful Environments (CoRE) 206 8.5.2 The Constrained Application Protocol (CoAP) 207 8.5.2.1 Latest in CoAP 207 8.5.3 The MQTT-SN Protocol 207 8.5.4 The Data Distribution Service (DDS) 208 8.5.5 Data Formats 209 8.6 Challenges and Research Solutions 209 8.7 Open Platforms for IoRT Applications 210 8.8 Industrial Drive for Interoperability 212 8.8.1 The Zigbee Alliance 212 8.8.2 The Thread Group 213 8.8.3 The WiFi Alliance 213 8.8.4 The LoRa Alliance 214 8.9 Conclusion 214 References 215 9 Real Time Hazardous Gas Classification and Management System Using Artificial Neural Networks 219R. Anitha, S. Anusooya, V. Jean Shilpa and Mohamed Hishaam 9.1 Introduction 220 9.2 Existing Methodology 220 9.3 Proposed Methodology 221 9.4 Hardware & Software Requirements 223 9.4.1 Hardware Requirements 223 9.4.1.1 Gas Sensors Employed in Hazardous Detection 223 9.4.1.2 NI Wireless Sensor Node 3202 226 9.4.1.3 NI WSN gateway (NI 9795) 228 9.4.1.4 COMPACT RIO (NI-9082) 229 9.5 Experimental Setup 232 9.5.1 Data Set Preparation 233 9.5.2 Artificial Neural Network Model Creation 236 9.6 Results and Discussion 240 9.7 Conclusion and Future Work 243 References 244 10 Hierarchical Elitism GSO Algorithm For Pattern Recognition 245Ilavazhagi Bala S. and Latha Parthiban 10.1 Introduction 246 10.2 Related Works 247 10.3 Methodology 248 10.3.1 Additive Kuan Speckle Noise Filtering Model 249 10.3.2 Hierarchical Elitism Gene GSO of MNN in Pattern Recognition 251 10.4 Experimental Setup 255 10.5 Discussion 255 10.5.1 Scenario 1: Computational Time 256 10.5.2 Scenario 2: Computational Complexity 257 10.5.3 Scenario 3: Pattern Recognition Accuracy 258 10.6 Conclusion 260 References 260 11 Multidimensional Survey of Machine Learning Application in IoT (Internet of Things) 263Anurag Sinha and Pooja Jha 11.1 Machine Learning—An Introduction 264 11.1.1 Classification of Machine Learning 265 11.2 Internet of Things 267 11.3 ML in IoT 268 11.3.1 Overview 268 11.4 Literature Review 270 11.5 Different Machine Learning Algorithm 271 11.5.1 Bayesian Measurements 271 11.5.2 K-Nearest Neighbors (k-NN) 272 11.5.3 Neural Network 272 11.5.4 Decision Tree (DT) 272 11.5.5 Principal Component Analysis (PCA) t 273 11.5.6 K-Mean Calculations 273 11.5.7 Strength Teaching 273 11.6 Internet of Things in Different Frameworks 273 11.6.1 Computing Framework 274 11.6.1.1 Fog Calculation 274 11.6.1.2 Estimation Edge 275 11.6.1.3 Distributed Computing 275 11.6.1.4 Circulated Figuring 276 11.7 Smart Cities 276 11.7.1 Use Case 277 11.7.1.1 Insightful Vitality 277 11.7.1.2 Brilliant Portability 277 11.7.1.3 Urban Arranging 278 11.7.2 Attributes of the Smart City 278 11.8 Smart Transportation 279 11.8.1 Machine Learning and IoT in Smart Transportation 280 11.8.2 Markov Model 283 11.8.3 Decision Structures 284 11.9 Application of Research 285 11.9.1 In Energy 285 11.9.2 In Routing 285 11.9.3 In Living 286 11.9.4 Application in Industry 287 11.10 Machine Learning for IoT Security 290 11.10.1 Used Machine Learning Algorithms 291 11.10.2 Intrusion Detection 293 11.10.3 Authentication 294 11.11 Conclusion 294 References 295 12 IoT-Based Bias Analysis in Acoustic Feedback Using Time-Variant Adaptive Algorithm in Hearing Aids 301G. Jayanthi and Latha Parthiban 12.1 Introduction 302 12.2 Existence of Acoustic Feedback 303 12.2.1 Causes of Acoustic Feedback 303 12.2.2 Amplification of Feedback Process 304 12.3 Analysis of Acoustic Feedback 304 12.3.1 Frequency Analysis Using Impulse Response 305 12.3.2 Feedback Analysis Using Phase Difference 306 12.4 Filtering of Signals 310 12.4.1 Digital Filters 310 12.4.2 Adaptive Filters 311 12.4.2.1 Order of Adaptive Filters 311 12.4.2.2 Filter Coefficients in Adaptive Filters 311 12.4.3 Adaptive Feedback Cancellation 312 12.4.3.1 Non-Continuous Adaptation 312 12.4.3.2 Continuous Adaptation 314 12.4.4 Estimation of Acoustic Feedback 315 12.4.5 Analysis of Acoustic Feedback Signal 317 12.4.5.1 Forward Path of the Signal 317 12.4.5.2 Feedback Path of the Signal 317 12.4.5.3 Bias Identification 319 12.5 Adaptive Algorithms 320 12.5.1 Step-Size Algorithms 321 12.5.1.1 Fixed Step-Size 322 12.5.1.2 Variable Step-Size 323 12.6 Simulation 325 12.6.1 Training of Adaptive Filter for Removal of Acoustic Feedback 325 12.6.2 Testing of Adaptive Filter 326 12.6.2.1 Subjective and Objective Evaluation Using KEMAR 326 12.6.2.2 Experimental Setup Using Manikin Channel 327 12.7 Performance Evaluation 328 12.8 Conclusions 333 References 334 13 Internet of Things Platform for Smart Farming 337R. Anandan, Deepak B.S., G. Suseendran and Noor Zaman Jhanjhi 13.1 Introduction 337 13.2 History 338 13.3 Electronic Terminologies 339 13.3.1 Input and Output Devices 339 13.3.2 GPIO 340 13.3.3 ADC 340 13.3.4 Communication Protocols 340 13.3.4.1 UART 340 13.3.4.2 I2C 340 13.3.4.3 SPI 341 13.4 IoT Cloud Architecture 341 13.4.1 Communication From User to Cloud Platform 342 13.4.2 Communication From Cloud Platform To IoT Device 342 13.5 Components of IoT 343 13.5.1 Real-Time Analytics 343 13.5.1.1 Understanding Driving Styles 343 13.5.1.2 Creating Driver Segmentation 344 13.5.1.3 Identifying Risky Neighbors 344 13.5.1.4 Creating Risk Profiles 344 13.5.1.5 Comparing Microsegments 344 13.5.2 Machine Learning 344 13.5.2.1 Understanding the Farm 345 13.5.2.2 Creating Farm Segmentation 345 13.5.2.3 Identifying Risky Factors 346 13.5.2.4 Creating Risk Profiles 346 13.5.2.5 Comparing Microsegments 346 13.5.3 Sensors 346 13.5.3.1 Temperature Sensor 347 13.5.3.2 Water Quality Sensor 347 13.5.3.3 Humidity Sensor 347 13.5.3.4 Light Dependent Resistor 347 13.5.4 Embedded Systems 349 13.6 IoT-Based Crop Management System 350 13.6.1 Temperature and Humidity Management System 350 13.6.1.1 Project Circuit 351 13.6.1.2 Connections 353 13.6.1.3 Program 356 13.6.2 Water Quality Monitoring System 361 13.6.2.1 Dissolved Oxygen Monitoring System 361 13.6.2.2 pH Monitoring System 363 13.6.3 Light Intensity Monitoring System 364 13.6.3.1 Project Circuit 365 13.6.3.2 Connections 365 13.6.3.3 Program Code 366 13.7 Future Prospects 367 13.8 Conclusion 368 References 369 14 Scrutinizing the Level of Awareness on Green Computing Practices in Combating Covid-19 at Institute of Health Science-Gaborone 371Ishmael Gala and Srinath Doss 14.1 Introduction 372 14.1.1 Institute of Health Science-Gaborone 373 14.1.2 Research Objectives 374 14.1.3 Green Computing 374 14.1.4 Covid-19 375 14.1.5 The Necessity of Green Computing in Combating Covid-19 376 14.1.6 Green Computing Awareness 379 14.1.7 Knowledge 380 14.1.8 Attitude 381 14.1.9 Behavior 381 14.2 Research Methodology 381 14.2.1 Target Population 382 14.2.2 Sample Frame 382 14.2.3 Questionnaire as a Data Collection Instrument 383 14.2.4 Validity and Reliability 383 14.3 Analysis of Data and Presentation 383 14.3.1 Demographics: Gender and Age 384 14.3.2 How Effective is Green Computing Policies in Combating Covid-19 at Institute of Health Science-Gaborone? 386 14.3.3 What are Green Computing Practices Among Users at Gaborone Institute of Health Science? 388 14.3.4 What is the Role of Green Computing Training in Combating Covid-19 at Institute of Health Science-Gaborone? 388 14.3.5 What is the Likelihood of Threats Associated With a Lack of Awareness on Green Computing Practices While Combating Covid-19? 390 14.3.6 What is the Level of User Conduct, Awareness and Attitude With Regard to Awareness on Green Computing Practices at Institute of Health Science-Gaborone? 391 14.4 Recommendations 393 14.4.1 Green Computing Policy 393 14.4.2 Risk Assessment 394 14.4.3 Green Computing Awareness Training 394 14.4.4 Compliance 394 14.5 Conclusion 394 References 395 15 Detailed Analysis of Medical IoT Using Wireless Body Sensor Network and Application of IoT in Healthcare 401Anurag Sinha and Shubham Singh 15.1 Introduction 402 15.2 History of IoT 403 15.3 Internet of Objects 405 15.3.1 Definitions 405 15.3.2 Internet of Things (IoT): Data Flow 406 15.3.3 Structure of IoT—Enabling Technologies 406 15.4 Applications of IoT 407 15.5 IoT in Healthcare of Human Beings 407 15.5.1 Remote Healthcare—Telemedicine 408 15.5.2 Telemedicine System—Overview 408 15.6 Telemedicine Through a Speech-Based Query System 409 15.6.1 Outpatient Monitoring 410 15.6.2 Telemedicine Umbrella Service 410 15.6.3 Advantages of the Telemedicine Service 411 15.6.4 Some Examples of IoT in the Health Sector 411 15.7 Conclusion 412 15.8 Sensors 412 15.8.1 Classification of Sensors 413 15.8.2 Commonly Used Sensors in BSNs 415 15.8.2.1 Accelerometer 417 15.8.2.2 ECG Sensors 418 15.8.2.3 Pressure Sensors 419 15.8.2.4 Respiration Sensors 420 15.9 Design of Sensor Nodes 420 15.9.1 Energy Control 421 15.9.2 Fault Diagnosis 422 15.9.3 Reduction of Sensor Nodes 422 15.10 Applications of BSNs 423 15.11 Conclusions 423 15.12 Introduction 424 15.12.1 From WBANs to BBNs 425 15.12.2 Overview of WBAN 425 15.12.3 Architecture 426 15.12.4 Standards 427 15.12.5 Applications 427 15.13 Body-to-Body Network Concept 428 15.14 Conclusions 429 References 430 16 DCMM: A Data Capture and Risk Management for Wireless Sensing Using IoT Platform 435Siripuri Kiran, Bandi Krishna, Janga Vijaykumar and Sridhar manda 16.1 Introduction 436 16.2 Background 438 16.2.1 Internet of Things 438 16.2.2 Middleware Data Acquisition 438 16.2.3 Context Acquisition 439 16.3 Architecture 439 16.3.1 Proposed Architecture 439 16.3.1.1 Protocol Adaption 441 16.3.1.2 Device Management 443 16.3.1.3 Data Handler 445 16.4 Implementation 446 16.4.1 Requirement and Functionality 446 16.4.1.1 Requirement 446 16.4.1.2 Functionalities 447 16.4.2 Adopted Technologies 448 16.4.2.1 Middleware Software 448 16.4.2.2 Usability Dependency 449 16.4.2.3 Sensor Node Software 449 16.4.2.4 Hardware Technology 450 16.4.2.5 Sensors 451 16.4.3 Details of IoT Hub 452 16.4.3.1 Data Poster 452 16.4.3.2 Data Management 452 16.4.3.3 Data Listener 453 16.4.3.4 Models 454 16.5 Results and Discussions 454 16.6 Conclusion 460 References 461 Index 463

A unique book explaining how perception, location, communication, cognition, computation, networking, propulsion, integration of federated Internet of Robotic Things (IoRT) and digital platforms are important components of new-generation IoRT applications through continuous, real-time interaction with the world. The 16 chapters in this book discuss new architectures, networking paradigms, trustworthy structures, and platforms for the integration of applications across various business and industrial domains that are needed for the emergence of intelligent things (static or mobile) in collaborative autonomous fleets. These new apps speed up the progress of paradigms of autonomous system design and the proliferation of the Internet of Robotic Things (IoRT). Collaborative robotic things can communicate with other things in the IoRT, learn independently, interact securely with the world, people, and other things, and acquire characteristics that make them self-maintaining, self-aware, self-healing, and fail-safe operational. Due to the ubiquitous nature of collaborative robotic things, the IoRT, which binds together the sensors and the objects of robotic things, is gaining popularity. Therefore, the information contained in this book will provide readers with a better understanding of this interdisciplinary field. Audience Researchers in various fields including computer science, IoT, artificial intelligence, machine learning, and big data analytics.