Smart Sensor Networks Using AI for Industry 4.0: Applications and New Opportunities (Advances in Intelligent Decision-Making, Systems Engineering, and Project Management)

Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
About the Editors
Contributors
Chapter 1: Optimization of Wireless Sensor Networks using Bio-Inspired Algorithm
	1.1 Introduction
	1.2 Literature Review
	1.3 Genetic Algorithm (GA)
		1.3.1 Roulette Wheel
		1.3.2 Probability of Crossover (P c)
		1.3.3 Probability of Mutation (P m)
		1.3.4 Elitism
	1.4 Ant Colony Optimization (ACO)
		1.4.1 Mathematical Model of ACO
	1.5 Particle Swarm Optimization Algorithm (PSO)
		1.5.1 Mathematical Model of PSO
	1.6 Implementation of Genetic Algorithm in a WSN
		1.6.1 Simulation Results
	1.7 Implementation of Ant Colony Optimization Algorithm in a WSN
		1.7.1 Simulation Result
	1.8 Implementation of Particle Swarm Optimization Algorithm in a WSN
		1.8.1 Simulation Result
	1.9 Comparative Analysis
	1.10 Conclusion and Future Work
	References
Chapter 2: An Improved Genetic Algorithm with Haar Lifting for Optimal Sensor Deployment in Target Covers Based Wireless Sensor Networks
	2.1 Introduction
	2.2 Related Works
	2.3 Problem Formulation
	2.4 Haar Lifting Scheme
	2.5 GA-2D Haar Lifting Optimal Sensor Placement
	2.6 Simulation Results
	2.7 Conclusion
	References
Chapter 3: Lifetime Enhancement of Wireless Sensor Network Using Artificial Intelligence Techniques
	3.1 Introduction
	3.2 Issues in Wireless Sensor Network
	3.3 Factors Deciding WSN Lifetime
	3.4 Artificial Intelligence Technique
		3.4.1 Why AI Is Required in WSN
	3.5 WSN Lifetime Enhancement Using AI
		3.5.1 Data Aggregation Using AI
		3.5.2 Coverage and Connectivity Determination Using AI
		3.5.3 Node Localization Using AI
		3.5.4 Routing Using AI
		3.5.5 Scheduling Using AI
		3.5.6 Node Deployment Using AI
	3.6 Conclusion
	References
Chapter 4: Research Issues of Information Security Using Blockchain Technique in Multiple Media WSNs: A Communication Technique Perceptive
	4.1 Introduction: Background and Driving Forces
	4.2 Background and Motivation
	4.3 Application of Blockchain-Based WSN Communication
		4.3.1 RFID-Based Food Supply Chain
		4.3.2 Underwater Sensor Network Security
		4.3.3 Telecom Roaming, Fraud, and Overage Management
	4.4 Blockchain Key Characteristics
	4.5 Need of Blockchain for Developing Countries
	4.6 Real Life Uses of Blockchain
		4.6.1 Blockchain for Humanities Aid
		4.6.2 Bitcoin Cryptocurrency
		4.6.3 Incent Customer Retention
	4.8 Conclusion
		4.7 Disadvantages of Blockchain
	References
Chapter 5: Modified Artificial Fish Swarm Optimization Based Clustering in Wireless Sensor Network
	5.1 Introduction
	5.2 Related Work
	5.3 Proposed Methodology
		5.3.1 Clustering the Sensor Node
			5.3.1.1 Weighted k-Means Clustering Algorithm
		5.3.2 Cluster Head Selection
			5.3.2.1 Modified Artificial Fish Swarm Algorithm (MAFS)
				5.3.2.1.1 Initialization
				5.3.2.1.2 Oppositional Behavior
					5.3.2.1.2.1 Prey Behavior
					5.3.2.1.2.2 Swarm Behavior
					5.3.2.1.2.3 Follow Behavior
					5.3.2.1.2.4 Termination Criteria
	5.4 Performance Metrics
		5.4.1 End-to-End Delay
		5.4.2 Throughput
		5.4.3 Network Lifetime
	5.5 Comparative Analysis
		5.5.1 Performance Evaluation
	5.6 Conclusion
	References
Chapter 6: Survey: Data Prediction Model in Wireless Sensor Networks Using Machine Learning and Optimization Methods
	6.1 Introduction
	6.2 Machine Learning (ML) Algorithms
	6.3 Data Prediction Models in WSN
		6.3.1 PCA
		6.3.2 ARIMA Prediction Model
		6.3.3 Multiple Linear Regression Models
		6.3.4 Support Vector Machine
		6.3.5 Ensemble Methods
		6.3.6 Artificial Neural Network (ANN)
		6.3.7 Multilayer Perceptron (MLP)
		6.3.8 Long Short Term Memory (LSTM)
	6.4 Hybrid Models
		6.4.1 PSO-SVM
		6.4.2 FFA-RF Model
		6.4.3 HHO-ANN
	6.5 Conclusion
	Acknowledgments
	References
Chapter 7: Strategic Sink Mobility Based on Particle Swarm Optimization in Wireless Sensor Network
	7.1 Introduction
		7.1.1 Contributions
	7.2 Related Work
	7.3 The Operation of Proposed Work
		7.3.1 System Consideration of Proposed Work
			7.3.1.1 Network Model Assumptions Considered for Proposed Work
	7.4 Simulation Setting Scenario
		7.4.1 Simulation Parameters Values
		7.4.2 Result and Analysis
	7.5 Conclusion and Future Scope
	References
Chapter 8: A Study on Outlier Detection Techniques for Wireless Sensor Network with CNN Approach
	8.1 Introduction: Wireless Sensor Networks (WSN)
		8.1.1 Application of WSN
		8.1.2 WSN Design Challenges
	8.2 Outliers
		8.2.1 Definitions of Outliers
		8.2.2 Types of Outliers
		8.2.3 Sources of Outliers
		8.2.4 Degree of Being an Outlier
		8.2.5 Dimension of Outliers
		8.2.6 Data Correlation
		8.2.7 Architectural Structure
		8.2.8 Issues of Outlier Detection
		8.2.9 Use of Outlier Detection in WSN
	8.3 Outlier Detection Methods
		8.3.1 Statistical-Based Approach
			8.3.1.1 Kernel-Based Approach
			8.3.1.2 Nearest Neighbor-Based Approach
		8.3.2 Clustering-Based Approach
		8.3.3 Classification-Based Approach
		8.3.4 Spectral Decomposition-Based Approach
		8.3.5 Artificial Intelligence-Based Approach
	8.4 Outlier Detection Using CNN
		8.4.1 Proposed Approach
		8.4.2 Experimental Setup
		8.4.3 Evaluation Metric
	8.5 Conclusion
	References
Chapter 9: NEECH: A Novel Energy-Efficient Cluster Head Selecting Protocol in a Wireless Sensor Network
	9.1 Introduction
		9.1.1 Major Contributions
	9.2 Related Work
	9.3 Working of NEECH
		9.3.1 Network Assumptions for NEECH
		9.3.2 Radio Energy Consumption Model
		9.3.3 Operation Steps of NEECH
	9.4 Results and Discussion
		9.4.1 Performance Metrics
	9.5 Conclusion
	References
Chapter 10: An Efficient Model for Toxic Gas Detection and Monitoring Using Cloud and Sensor Network
	10.1 Introduction
	10.2 Literature Review
	10.3 Proposed Gas Detection and Monitoring Model
	10.4 Proposed Gas Detection Algorithm
	10.5 Implementation
		10.5.1 Booting the Raspberry Pi
		10.5.2 Securing All Hardware Connections
		10.5.3 Importing Sensor Data onto the Cloud Platform
		10.5.4 Enabling Twillio
		10.5.5 Creating an Application
	10.6 Results
	10.7 Conclusion
	References
Chapter 11: Particle Swarm Intelligence-Based Localization Algorithms in Wireless Sensor Networks
	11.1 Introduction
		11.1.1 Objectives of the Chapter
		11.1.2 Scope of the Chapter
	11.2 Existing Localization Algorithms
	11.3 Cooperative Distributive Particle Swarm Optimization (CDPSO)
		11.3.1 Simulation and Results Analysis
			11.3.1.1 Simulation Setup
			11.3.1.2 Results Analysis
		11.3.2 PSO Assisted AKF Algorithm
		11.3.3 Simulation and Results
		11.3.4 CDPSO Localized Routing with Optimum References
		11.3.5 Simulation Results and Analysis
		11.3.6 Location Tracking of Patients Using PSO-AKF
		11.3.7 Simulation Results and Analysis
	11.4 Conclusion
	References
Chapter 12: A Review on Defense Strategy Security Mechanism for Sensor Network
	12.1 Introduction
	12.2 Game Theory in Wireless Sensor Networks
		12.2.1 Classification of Games
			12.2.1.1 Noncooperative Games
			12.2.1.2 Cooperative Games
			12.2.1.3 Cooperation Enforcement Games
			12.2.1.4 Other Classification
	12.3 Security Defense Strategy Attack Graph
		12.3.1 Game Theory for Sybil Attack
		12.3.2 Defense Strategy for Denial of Service (DDoS)
		12.3.3 Defense Mechanisms of Transport/Network Layer
			12.3.3.1 Source-Based Mechanism
			12.3.3.2 Routing Defense Mechanism Game Theory for Sensor
	12.4 Open Issues and Challenges
	12.5 Conclusion
	References
Chapter 13: Securing Wireless Multimedia Objects Through Machine Learning Techniques in Wireless Sensor Networks
	13.1 Introduction: Wireless Network
		13.1.1 Wireless Sensor Network
		13.1.2 Objectives of Wireless Sensor Network (WSN)
			13.1.2.1 Coverage
			13.1.2.2 Differentiated Detection Levels
			13.1.2.3 Network Connectivity
			13.1.2.4 Network Life Span
			13.1.2.5 Data Fidelity
			13.1.2.6 Energy Efficiency
			13.1.2.7 Imperfection Tolerance and Load Balancing
		13.1.3 WSN Relevance
			13.1.3.1 Armed Forces Applications
		13.1.4 WSN Features
			13.1.4.1 Power Efficiency in Wireless Sensor Networks
			13.1.4.2 WSN Scalability
			13.1.4.3 WSNs Responsiveness
			13.1.4.4 Steadfastness in Wireless Sensor Networks
			13.1.4.5 WSN Mobility
		13.1.5 SN Categories
			13.1.5.1 Ground-Based WSNs
			13.1.5.2 Underground-Based WSNs
			13.1.5.3 Underwater Based WSNs
			13.1.5.4 Multimedia WSNs (M-WSNs)
		13.1.6 Unauthorized Access Point Detection in WSNs
			13.1.6.1 Fake Access Point
			13.1.6.2 Rogue Access Point
		13.1.7 Wireless Multimedia Sensor Networks
		13.1.8 Literature Survey
		13.1.9 Paradigms of Intelligent Authentication for Efficient Multimedia Security
			13.1.9.1 Parametric Learning Methods
			13.1.9.2 Nonparametric Learning Methods
			13.1.9.3 Supervised Learning Algorithms
		13.1.10 Unsupervised Learning Algorithms
			13.1.10.1 Reinforcement Learning Algorithms
	13.2 Implementation of Machine Learning Algorithms in Multimedia Security
		13.2.1 Supervised Learning Algorithm
		13.2.2 Reinforcement Learning Algorithm
		13.2.3 Unsupervised Learning Algorithm
	13.3 Issues Related to the Present Approaches
		13.3.1 Inconsistency
		13.3.2 Obscurity in Pre-Designing
		13.3.3 Uninterrupted Security to Genuine Components
		13.3.4 Uninterrupted Security to Genuine Components: Time-Divergent Features
		13.3.5 Dealing with Varied Network
		13.3.6 Incorporating Authentication Protocols
	13.4 Conclusion
	References
Chapter 14: Low Power Communication in Wireless Sensor Networks and IoT
	14.1 Introduction
	14.2 Long Range Communication (LoRa)
	14.3 Zigbee
	14.4 IPv6 Low Power Personal Area Network (6LoWPAN)
	14.5 Narrow Band Internet of Things (NBIoT)
	14.6 SIGFOX
	14.7 Conclusion
	Acknowledgment
	References
Chapter 15: Localization Using Bat Algorithm in Wireless Sensor Network
	15.1 Introduction
		15.1.1 Problem Statement
		15.1.2 Major Contributions
	15.2 Literature Work
		15.2.1 Bat Algorithm
	15.3 Operational Functioning of LBA
		15.3.1 Network Model
		15.3.2 Simulation Parameters
	15.4 Results and Discussion: Performance Evaluating Metrics
	15.5 Summary
	15.6 Conclusion
	References
Index