Nature Inspired Computing for Wireless Sensor Networks (eBook)

Preface 6
Objective of the Book 6
Organization of the Book 6
Part I: Bio-inspired Optimization (Chaps. 2–6) 7
Part II: Swarm Optimization (Chaps. 7–9) 8
Part III: Multi-objective Optimization (Chaps. 10–14) 8
List of Reviewers 10
Contents 12
About the Editors 14
Bio-inspired Optimization 34
2 A GA-Based Fault-Aware Routing Algorithm for Wireless Sensor Networks 35
1 Introduction 35
2 Related Work 38
3 System Model and Terminologies 39
4 Proposed Algorithm 41
4.1 Information Sharing Phase 42
4.2 Network Setup Phase 42
4.3 Steady Phase 48
5 Simulation Results 48
5.1 Simulation Setup 48
5.2 Evaluation of Experimental Results 48
6 Conclusion 50
References 51
3 GA-Based Fault Diagnosis Technique for Enhancing Network Lifetime of Wireless Sensor Network 53
1 Introduction 53
1.1 Issues 53
1.2 Challenges 54
2 Fault, Errors and Failures 55
2.1 Types of Fault 56
2.2 Fault Diagnosis 56
3 Related Work 57
4 Proposed Method 58
5 Performance Evaluation 63
6 Conclusion 67
References 68
4 A GA-Based Intelligent Traffic Management Technique for Wireless Body Area Sensor Networks 71
1 Introduction 71
2 Literature Review 72
3 Proposed Method 75
4 Performance Evaluation 85
5 Conclusion 86
References 87
5 Fault Diagnosis in Wireless Sensor Networks Using a Neural Network Constructed by Deep Learning Technique 90
1 Introduction 90
2 Related Work 92
2.1 Statistical Test-Based Intermittent Fault Diagnosis 92
2.2 Soft Computing and Neural Network Approach for Fault Diagnosis 93
3 System Model 95
3.1 Assumptions 95
3.2 Sensor Network Model 96
3.3 Fault Model 96
3.4 Modelling of Sensor Data 97
4 Problem Formulation 98
5 Feature Selection 99
5.1 Mean 99
5.2 Standard Deviation (SD) 100
5.3 Skewness and Kurtosis 100
5.4 Mean Absolute Deviation (MAD) 101
5.5 Extracting the Features From Sensor Data—An Example 101
6 Neural Network with Deep Learning Algorithms For Intermittent Fault Detection of Sensor Nodes 103
6.1 Basic Neural Network Design 104
7 Results and Discussions 107
8 Conclusion 111
References 111
6 Immune Inspired Fault Diagnosis in Wireless Sensor Network 115
1 Introduction 115
1.1 Motivation 117
1.2 Contribution 118
2 Biological Immune System: An Overview 118
3 AIS Approaches for Fault Diagnosis in WSN 122
4 Applications of AIS Algorithms 123
5 Conclusion 126
References 126
Swarm Optimization 129
7 Intelligent Routing in Wireless Sensor Network Based on African Buffalo Optimization 130
1 Introduction 130
2 Related Work 132
3 Preliminary: African Buffalo Optimization 135
3.1 The Component View of the ABO 136
3.2 African Buffalo Optimization: The Algorithm 138
3.3 Merits of ABO Algorithm 138
3.4 Application of ABO Algorithm 139
4 Proposed Method 140
4.1 Problem Formulation 142
5 Performance Evaluation 144
5.1 Variation of Iterations 146
5.2 Unique Variation of Iterations 150
6 Conclusion 150
References 151
8 On the Development of Energy-Efficient Distributed Source Localization Algorithm in Wireless Sensor Networks Using Modified Swarm Intelligence 154
1 Introduction 154
2 Related Works 156
3 Maximum-Likelihood DOA Estimation of Narrow-Band Far-Field Signal 157
3.1 Formulation of ML-DOA Estimation Problem 158
4 Distributed DOA Estimation 159
4.1 Local Cost Function for DOA Estimation 160
4.2 Distributed DOA Estimation Using Local ML Functions 161
5 Diffusion Particle Swarm Optimization (DPSO) 164
6 Diffusion PSO Algorithm for ML-DOA Estimation in Sensor Network 166
6.1 Performance Measure 167
6.2 Example 169
7 Clustering-Based Distributed DOA Estimation in Wireless Sensor Networks 174
7.1 Clustering-Based Distributed DOA Estimation 175
8 Conclusion 180
9 Future Direction 181
References 182
9 Quasi-oppositional Harmony Search Algorithm Approach for Ad Hoc and Sensor Networks 185
1 Introduction 185
2 Need of Optimization 187
2.1 Basic HSA 187
2.2 Improved HSA 190
2.3 Opposition-Based Learning 190
2.4 Quasi-Opposition-Based Learning: A Concept 192
3 Optimization Techniques Applied in WSN 199
4 Performance Evaluation 201
5 Conclusion 201
Appendix 203
Parameters of QOHS 203
References 203
Multi-objective Optimization 205
10 A Comprehensive Survey of Intelligent-Based Hierarchical Routing Protocols for Wireless Sensor Networks 206
1 Introduction 206
2 Taxonomy Metrics 209
2.1 WSN Types 209
2.2 Node Deployment 211
2.3 Control Manner 211
2.4 Network Architecture 212
2.5 Clustering Attributes 212
2.6 Protocol Operation 213
2.7 Path Establishment 213
2.8 Communication Paradigm 214
2.9 Radio Model 214
2.10 Protocol Objectives 215
2.11 Applications 215
3 Intelligent-Based Hierarchical Routing Protocols 216
3.1 Particle Swarm Optimization-Based Hierarchical Routing Protocols 216
3.2 Genetic Algorithm-Based Hierarchical Routing Protocols 236
3.3 Fuzzy Logic-Based Hierarchical Routing Protocols 242
3.4 Ant Colony Optimization-Based Hierarchical Routing Protocols 245
3.5 Artificial Immune Algorithm-Based Hierarchical Routing Protocols 247
4 Comparison and Discussion 250
5 Conclusion and Future Directions 262
References 263
11 Qualitative Survey on Sensor Node Deployment, Load Balancing and Energy Utilization in Sensor Network 267
1 Introduction 267
2 Overview of Sensor Node Deployment 268
2.1 IPP Based Approach for Ensuring Coverage 269
2.2 PSO Based Node Deployment 271
2.3 ACO in Node Deployment and Load Balancing 276
2.4 Honey Bee Optimization in Sensor Deployment 278
3 Load Balancing in Sensor Network 280
4 Conclusion 283
References 284
12 Bio-inspired Algorithm for Multi-objective Optimization in Wireless Sensor Network 286
1 Introduction 286
2 Review of Bio-Inspired Algorithms 291
2.1 Ant Colony Optimization (ACO) 291
2.2 Artificial Bee Colony (ABC) 291
2.3 Bat Algorithm (BA) 292
2.4 Biogeography-Based Optimization (BBO) 292
2.5 Cat Swarm Optimization (CSO) 293
2.6 Cuckoo Search Algorithm 293
2.7 Chicken Swarm Optimization Algorithm (CSOA) 293
2.8 Elephant Herding Optimization (EHO) 293
2.9 Fish Swarm Optimization Algorithm (FSOA) 294
2.10 Grey Wolf Optimization (GWO) 294
2.11 Glowworm Swarm Optimization (GSO) 294
2.12 Moth Flame Optimization (MFO) Algorithm 295
2.13 Particle Swarm Optimization (PSO) 295
2.14 Whale Optimization Algorithm (WOA) 296
3 Domains of Applications 296
4 Application of Bio-Inspired Algorithms in Different Areas of Wireless Sensor Network 298
5 Challenges and Key Issues of Bio-Inspired Computing 301
6 Bio-Inspired Computation and Its Future 301
7 Conclusion 303
References 303
13 TLBO Based Cluster-Head Selection for Multi-objective Optimization in Wireless Sensor Networks 309
1 Introduction 309
2 Literature Review 311
3 Preliminary: Teaching-Learning-Based Optimization (TLBO) 315
3.1 Teacher Phase 315
3.2 Learner Phase 315
4 Proposed Method 316
4.1 Network Model 316
4.2 Parameter Formulation 317
4.3 TLBO Formulation 317
5 Conclusion 322
References 322
14 Nature-Inspired Algorithms for Reliable, Low-Latency Communication in Wireless Sensor Networks for Pervasive Healthcare Applications 326
1 Introduction 326
2 Literature Survey 328
3 Wireless Sensor Network Architecture 330
4 Routing Protocols for WSN in Healthcare 332
4.1 Deadline Classification 333
4.2 Architecture Design Objectives 333
5 Nature-Inspired Routing Protocols 334
5.1 Particle Swarm Optimization 335
5.2 Ant Colony Optimization 337
5.3 Artificial Immune System 339
5.4 Plant Biology-Inspired Framework for WSN 340
6 Conclusions 342
References 344