Swarm Intelligence Optimization: Algorithms and Applications

Resource optimization has always been a thrust area of research, and as the Internet of Things (IoT) is the most talked about topic of the current era of technology, it has become the need of the hour. Therefore, the idea behind this book was to simplify the journey of those who aspire to understand resource optimization in the IoT. To this end, included in this book are various real-time/offline applications and algorithms/case studies in the fields of engineering, computer science, information security, and cloud computing, along with the modern tools and various technologies used in systems, leaving the reader with a high level of understanding of various techniques and algorithms used in resource optimization.

Table of Contents:
Preface xv 1 A Fundamental Overview of Different Algorithms and Performance Optimization for Swarm Intelligence 1 Manju Payal, Abhishek Kumar and Vicente García Díaz 1.1 Introduction 1 1.2 Methodology of SI Framework 3 1.3 Composing With SI 7 1.4 Algorithms of the SI 7 1.5 Conclusion 18 References 18 2 Introduction to IoT With Swarm Intelligence 21 Anant Mishra and Jafar Tahir 2.1 Introduction 21 2.1.1 Literature Overview 22 2.2 Programming 22 2.2.1 Basic Programming 22 2.2.2 Prototyping 22 2.3 Data Generation 23 2.3.1 From Where the Data Comes? 23 2.3.2 Challenges of Excess Data 24 2.3.3 Where We Store Generated Data? 24 2.3.4 Cloud Computing and Fog Computing 25 2.4 Automation 26 2.4.1 What is Automation? 26 2.4.2 How Automation is Being Used? 26 2.5 Security of the Generated Data 30 2.5.1 Why We Need Security in Our Data? 30 2.5.2 What Types of Data is Being Generated? 31 2.5.3 Protecting Different Sector Working on the Principle of IoT 32 2.6 Swarm Intelligence 33 2.6.1 What is Swarm Intelligence? 33 2.6.2 Classification of Swarm Intelligence 33 2.6.3 Properties of a Swarm Intelligence System 34 2.7 Scope in Educational and Professional Sector 36 2.8 Conclusion 37 References 38 3 Perspectives and Foundations of Swarm Intelligence and its Application 41 Rashmi Agrawal 3.1 Introduction 41 3.2 Behavioral Phenomena of Living Beings and Inspired Algorithms 42 3.2.1 Bee Foraging 42 3.2.2 ABC Algorithm 43 3.2.3 Mating and Marriage 43 3.2.4 MBO Algorithm 44 3.2.5 Coakroach Behavior 44 3.3 Roach Infestation Optimization 45 3.3.1 Lampyridae Bioluminescence 45 3.3.2 GSO Algorithm 46 3.4 Conclusion 46 References 47 4 Implication of IoT Components and Energy Management Monitoring 49 Shweta Sharma, Praveen Kumar Kotturu and Prafful Chandra Narooka 4.1 Introduction 49 4.2 IoT Components 53 4.3 IoT Energy Management 56 4.4 Implication of Energy Measurement for Monitoring 57 4.5 Execution of Industrial Energy Monitoring 58 4.6 Information Collection 59 4.7 Vitality Profiles Analysis 59 4.8 IoT-Based Smart Energy Management System 61 4.9 Smart Energy Management System 61 4.10 IoT-Based System for Intelligent Energy Management in Buildings 62 4.11 Smart Home for Energy Management Using IoT 62 References 64 5 Distinct Algorithms for Swarm Intelligence in IoT 67 Trapty Agarwal, Gurjot Singh, Subham Pradhan and Vikash Verma 5.1 Introduction 67 5.2 Swarm Bird–Based Algorithms for IoT 68 5.2.1 Particle Swarm Optimization (PSO) 68 5.2.1.1 Statistical Analysis 68 5.2.1.2 Algorithm 68 5.2.1.3 Applications 69 5.2.2 Cuckoo Search Algorithm 69 5.2.2.1 Statistical Analysis 69 5.2.2.2 Algorithm 70 5.2.2.3 Applications 70 5.2.3 Bat Algorithm 71 5.2.3.1 Statistical Analysis 71 5.2.3.2 Algorithm 71 5.2.3.3 Applications 72 5.3 Swarm Insect–Based Algorithm for IoT 72 5.3.1 Ant Colony Optimization 72 5.3.1.1 Flowchart 73 5.3.1.2 Applications 73 5.3.2 Artificial Bee Colony 74 5.3.2.1 Flowchart 75 5.3.2.2 Applications 75 5.3.3 Honey-Bee Mating Optimization 75 5.3.3.1 Flowchart 76 5.3.3.2 Application 77 5.3.4 Firefly Algorithm 77 5.3.4.1 Flowchart 78 5.3.4.2 Application 78 5.3.5 Glowworm Swarm Optimization 78 5.3.5.1 Statistical Analysis 79 5.3.5.2 Flowchart 79 5.3.5.3 Application 80 References 80 6 Swarm Intelligence for Data Management and Mining Technologies to Manage and Analyze Data in IoT 83 Kashinath Chandelkar 6.1 Introduction 83 6.2 Content Management System 84 6.3 Data Management and Mining 85 6.3.1 Data Life Cycle 86 6.3.2 Knowledge Discovery in Database 87 6.3.3 Data Mining vs. Data Warehousing 88 6.3.4 Data Mining Techniques 88 6.3.5 Data Mining Technologies 92 6.3.6 Issues in Data Mining 93 6.4 Introduction to Internet of Things 94 6.5 Swarm Intelligence Techniques 94 6.5.1 Ant Colony Optimization 95 6.5.2 Particle Swarm Optimization 95 6.5.3 Differential Evolution 96 6.5.4 Standard Firefly Algorithm 96 6.5.5 Artificial Bee Colony 97 6.6 Chapter Summary 98 References 98 7 Healthcare Data Analytics Using Swarm Intelligence 101 Palvadi Srinivas Kumar, Pooja Dixit and N. Gayathri 7.1 Introduction 101 7.1.1 Definition 103 7.2 Intelligent Agent 103 7.3 Background and Usage of AI Over Healthcare Domain 104 7.4 Application of AI Techniques in Healthcare 105 7.5 Benefits of Artificial Intelligence 106 7.6 Swarm Intelligence Model 107 7.7 Swarm Intelligence Capabilities 108 7.8 How the Swarm AI Technology Works 109 7.9 Swarm Algorithm 110 7.10 Ant Colony Optimization Algorithm 110 7.11 Particle Swarm Optimization 112 7.12 Concepts for Swarm Intelligence Algorithms 113 7.13 How Swarm AI is Useful in Healthcare 114 7.14 Benefits of Swarm AI 115 7.15 Impact of Swarm-Based Medicine 116 7.16 SI Limitations 117 7.17 Future of Swarm AI 118 7.18 Issues and Challenges 119 7.19 Conclusion 120 References 120 8 Swarm Intelligence for Group Objects in Wireless Sensor Networks 123 Kapil Chauhan and Pramod Singh Rathore 8.1 Introduction 123 8.2 Algorithm 127 8.3 Mechanism and Rationale of the Work 130 8.3.1 Related Work 131 8.4 Network Energy Model 132 8.4.1 Network Model 132 8.5 PSO Grouping Issue 132 8.6 Proposed Method 133 8.6.1 Grouping Phase 133 8.6.2 Proposed Validation Record 133 8.6.3 Data Transmission Stage 133 8.7 Bunch Hub Refreshing Calculation Dependent on an Improved PSO 133 8.8 Other SI Models 134 8.9 An Automatic Clustering Algorithm Based on PSO 135 8.10 Steering Rule Based on Informed Algorithm 136 8.11 Routing Protocols Based on Meta-Heuristic Algorithm 137 8.12 Routing Protocols for Avoiding Energy Holes 138 8.13 System Model 138 8.13.1 Network Model 138 8.13.2 Power Model 139 References 139 9 Swam Intelligence–Based Resources Optimization and Analyses and Managing Data in IoT With Data Mining Technologies 143 Pooja Dixit, Palvadi Srinivas Kumar and N. Gayathri 9.1 Introduction 143 9.1.1 Swarm Intelligence 143 9.1.1.1 Swarm Biological Collective Behavior 145 9.1.1.2 Swarm With Artificial Intelligence Model 147 9.1.1.3 Birds in Nature 150 9.1.1.4 Swarm with IoT 153 9.2 IoT With Data Mining 153 9.2.1 Data from IoT 154 9.2.1.1 Data Mining for IoT 154 9.2.2 Data Mining With KDD 157 9.2.3 PSO With Data Mining 159 9.3 ACO and Data Mining 161 9.4 Challenges for ACO-Based Data Mining 162 References 162 10 Data Management and Mining Technologies to Manage and Analyze Data in IoT 165 Shweta Sharma, Satya Murthy Sasubilli and Kunal Bhargava 10.1 Introduction 165 10.2 Data Management 166 10.3 Data Lifecycle of IoT 167 10.4 Procedures to Implement IoT Data Management 171 10.5 Industrial Data Lifecycle 173 10.6 Industrial Data Management Framework of IoT 174 10.6.1 Physical Layer 174 10.6.2 Correspondence Layer 175 10.6.3 Middleware Layer 175 10.7 Data Mining 175 10.7.1 Functionalities of Data Mining 179 10.7.2 Classification 180 10.8 Clustering 182 10.9 Affiliation Analysis 182 10.10 Time Series Analysis 183 References 185 11 Swarm Intelligence for Data Management and Mining Technologies to Manage and Analyze Data in IoT 189 Kapil Chauhan and Vishal Dutt 11.1 Introduction 190 11.2 Information Mining Functionalities 192 11.2.1 Classification 192 11.2.2 Clustering 192 11.3 Data Mining Using Ant Colony Optimization 193 11.3.1 Enormous Information Investigation 194 11.3.2 Data Grouping 195 11.4 Computing With Ant-Based 196 11.4.1 Biological Background 196 11.5 Related Work 197 11.6 Contributions 198 11.7 SI in Enormous Information Examination 198 11.7.1 Handling Enormous Measure of Information 199 11.7.2 Handling Multidimensional Information 199 11.8 Requirements and Characteristics of IoT Data 200 11.8.1 IoT Quick and Gushing Information 200 11.8.2 IoT Big Information 200 11.9 Conclusion 201 References 202 12 Swarm Intelligence–Based Energy-Efficient Clustering Algorithms for WSN: Overview of Algorithms, Analysis, and Applications 207 Devika G., Ramesh D. and Asha Gowda Karegowda 12.1 Introduction 208 12.1.1 Scope of Work 209 12.1.2 Related Works 209 12.1.3 Challenges in WSNs 210 12.1.4 Major Highlights of the Chapter 213 12.2 SI-Based Clustering Techniques 213 12.2.1 Growth of SI Algorithms and Characteristics 214 12.2.2 Typical SI-Based Clustering Algorithms 219 12.2.3 Comparison of SI Algorithms and Applications 219 12.3 WSN SI Clustering Applications 219 12.3.1 WSN Services 233 12.3.2 Clustering Objectives for WSN Applications 233 12.3.3 SI Algorithms for WSN: Overview 234 12.3.4 The Commonly Applied SI-Based WSN Clusterings 235 12.3.4.1 ACO-Based WSN Clustering 235 12.3.4.2 PSO-Based WSN Clustering 237 12.3.4.3 ABC-Based WSN Clustering 240 12.3.4.4 CS Cuckoo–Based WSN Clustering 241 12.3.4.5 Other SI Technique-Based WSN Clustering 242 12.4 Challenges and Future Direction 246 12.5 Conclusions 247 References 253 13 Swarm Intelligence for Clustering in Wireless Sensor Networks 263 Preeti Sethi 13.1 Introduction 263 13.2 Clustering in Wireless Sensor Networks 264 13.3 Use of Swarm Intelligence for Clustering in WSN 266 13.3.1 Mobile Agents: Properties and Behavior 266 13.3.2 Benefits of Using Mobile Agents 267 13.3.3 Swarm Intelligence–Based Clustering Approach 268 13.4 Conclusion 272 References 272 14 Swarm Intelligence for Clustering in Wi-Fi Networks 275 Astha Parihar and Ramkishore Kuchana 14.1 Introduction 275 14.1.1 Wi-Fi Networks 275 14.1.2 Wi-Fi Networks Clustering 277 14.2 Power Conscious Fuzzy Clustering Algorithm (PCFCA) 278 14.2.1 Adequate Cluster Head Selection in PCFCA 278 14.2.2 Creation of Clusters 279 14.2.3 Execution Assessment of PCFCA 282 14.3 Vitality Collecting in Remote Sensor Systems 282 14.3.1 Power Utilization 283 14.3.2 Production of Energy 283 14.3.3 Power Cost 284 14.3.4 Performance Representation of EEHC 284 14.4 Adequate Power Circular Clustering Algorithm (APRC) 284 14.4.1 Case-Based Clustering in Wi-Fi Networks 284 14.4.2 Circular Clustering Outlook 284 14.4.3 Performance Representation of APRC 285 14.5 Modifying Scattered Clustering Algorithm (MSCA) 286 14.5.1 Equivalence Estimation in Data Sensing 286 14.5.2 Steps in Modifying Scattered Clustering Algorithm (MSCA) 286 14.5.3 Performance Evaluation of MSCA 287 14.6 Conclusion 288 References 288 15 Support Vector in Healthcare Using SVM/PSO in Various Domains: A Review 291 Vishal Dutt, Pramod Singh Rathore and Kapil Chauhan 15.1 Introduction 291 15.2 The Fundamental PSO 292 15.2.1 Algorithm for PSO 293 15.3 The Support Vector 293 15.3.1 SVM in Regression 299 15.3.2 SVM in Clustering 300 15.3.3 Partition Clustering 301 15.3.4 Hierarchical Clustering 301 15.3.5 Density-Based Clustering 302 15.3.6 PSO in Clustering 303 15.4 Conclusion 304 References 304 16 IoT-Based Healthcare System to Monitor the Sensor’s Data of MWBAN 309 Rani Kumari and ParmaNand 16.1 Introduction 310 16.1.1 Combination of AI and IoT in Real Activities 310 16.2 Related Work 311 16.3 Proposed System 312 16.3.1 AI and IoT in Medical Field 312 16.3.2 IoT Features in Healthcare 313 16.3.2.1 Wearable Sensing Devices With Physical Interface for Real World 313 16.3.2.2 Input Through Organized Information to the Sensors 313 16.3.2.3 Small Sensor Devices for Input and Output 314 16.3.2.4 Interaction With Human Associated Devices 314 16.3.2.5 To Control Physical Activity and Decision 314 16.3.3 Approach for Sensor’s Status of Patient 315 16.4 System Model 315 16.4.1 Solution Based on Heuristic Iterative Method 317 16.5 Challenges of Cyber Security in Healthcare With IoT 320 16.6 Conclusion 321 References 321 17 Effectiveness of Swarm Intelligence for Handling Fault-Tolerant Routing Problem in IoT 325 Arpit Kumar Sharma, Kishan Kanhaiya and Jaisika Talwar 17.1 Introduction 325 17.1.1 Meaning of Swarm and Swarm Intelligence 326 17.1.2 Stability 327 17.1.3 Technologies of Swarm 328 17.2 Applications of Swarm Intelligence 328 17.2.1 Flight of Birds Elaborations 329 17.2.2 Honey Bees Elaborations 329 17.3 Swarm Intelligence in IoT 330 17.3.1 Applications 331 17.3.2 Human Beings vs. Swarm 332 17.3.3 Use of Swarms in Engineering 332 17.4 Innovations Based on Swarm Intelligence 333 17.4.1 Fault Tolerance in IoT 334 17.5 Energy-Based Model 335 17.5.1 Basic Approach of Fault Tolerance With Its Network Architecture 335 17.5.2 Problem of Fault Tolerance Using Different Algorithms 337 17.6 Conclusion 340 References 340 18 Smart Epilepsy Detection System Using Hybrid ANN-PSO Network 343 Jagriti Saini and Maitreyee Dutta 18.1 Introduction 343 18.2 Materials and Methods 345 18.2.1 Experimental Data 345 18.2.2 Data Pre-Processing 345 18.2.3 Feature Extraction 346 18.2.4 Relevance of Extracted Features 346 18.3 Proposed Epilepsy Detection System 349 18.4 Experimental Results of ANN-Based System 350 18.5 MSE Reduction Using Optimization Techniques 351 18.6 Hybrid ANN-PSO System for Epilepsy Detection 353 18.7 Conclusion 355 References 356 Index 359

About the Author :
Abhishek Kumar gained his PhD in computer science from the University of Madras, India in 2019. He is assistant professor at Chitkara University and has more than 80 publications in peer-reviewed international and national journals, books & conferences His research interests include artificial intelligence, image processing, computer vision, data mining and machine learning. Pramod Singh Rathore has a MTech in Computer Science & Engineering from the Government Engineering College Ajmer, Rajasthan Technical University, Kota India, where he is now an assistant professor. He has more than 60 papers, chapters, and a book to his credit and his research interests are in networking cloud and IoT. Vicente García Díaz obtained his PhD in Computer Science in 2011 at the University of Oviedo, Spain where he is now an associate professor in the School of Computer Science. He has published more than 100 publications and his research interests include domain-specific languages, e-learning, decision support systems. Rashmi Agrawal obtained her PhD in Computer Applications in 2016 from Manav Rachna International University Faridabad, India, where she is now a professor in the Department of Computer Applications. Her research area includes data mining and artificial intelligence and she has published more than 65 publications to her credit.