Artificial Intelligent Techniques for Wireless Communication and Networking (2022) [Kanthavel et al] []

Cover
Half-Title Page
Series Page
Title Page
Copyright Page
Contents
Preface
1 Comprehensive and Self-Contained Introduction to Deep Reinforcement Learning
	1.1 Introduction
	1.2 Comprehensive Study
		1.2.1 Introduction
		1.2.2 Framework
		1.2.3 Choice of the Learning Algorithm and Function Approximator Selection
			1.2.3.1 Auxiliary Tasks
			1.2.3.2 Modifying the Objective Function
	1.3 Deep Reinforcement Learning: Value-Based and Policy-Based Learning
		1.3.1 Value-Based Method
		1.3.2 Policy-Based Method
	1.4 Applications and Challenges of Applying Reinforcement Learning to Real-World
		1.4.1 Applications
		1.4.2 Challenges
	1.5 Conclusion
	References
2 Impact of AI in 5G Wireless Technologies and Communication Systems
	2.1 Introduction
	2.2 Integrated Services of AI in 5G and 5G in AI
		2.2.1 5G Services in AI
			2.2.1.1 Next-Generation Edge Convergence With AI Systems on Chip
			2.2.1.2 Massive Device Concurrency Replenishing AI Data Lakes in Real Time
			2.2.1.3 Ultra-Fast, High-Volume Streaming for Low-Latency AI
		2.2.2 AI Services in 5G
			2.2.2.1 Distributed AI
			2.2.2.2 AI for IT Operations (AIOps)
			2.2.2.3 Network Slicing
		2.2.3 Evolution With AI in the 5G Era
			2.2.3.1 Agile Network Construction
			2.2.3.2 Intelligent Operations and Management
			2.2.3.3 Smart Operations
	2.3 Artificial Intelligence and 5G in the Industrial Space
	2.4 Future Research and Challenges of Artificial Intelligence in the Mobile Networks
		2.4.1 Research Directions
			2.4.1.1 AI Is Being Adopted Into Mobile Networks by Communication Service Provider Now
			2.4.1.2 AI and Customer Experience
			2.4.1.3 Recouping the Network Investments That 5G Demands
			2.4.1.4 Data Challenges Presented by Artificial Intelligence Adoption
			2.4.1.5 Network Intelligence and Automation
		2.4.2 Challenges to a 5G-Powered AI Network
			2.4.2.1 Dealing With Interference
			2.4.2.2 Dealing With Latency
			2.4.2.3 Solving Latency
	2.5 Conclusion
	References
3 Artificial Intelligence Revolution in Logistics and Supply Chain Management
	3.1 Introduction
	3.2 Theory—AI in Logistics and Supply Chain Market
		3.2.1 AI Impacts
		3.2.2 Revolutionizing Global Market
		3.2.3 Role of AI
		3.2.4 AI Trends in Logistics
			3.2.4.1 Anticipatory Logistics
			3.2.4.2 Self-Learning Systems
		3.2.5 AI Trends in Supply Chain
	3.3 Factors to Propel Business Into the Future Harnessing Automation
		3.3.1 Logistics
			3.3.1.1 Predictive Capabilities
			3.3.1.2 Robotics
			3.3.1.3 Big Data
			3.3.1.4 Computer Vision
			3.3.1.5 Autonomous Vehicles
		3.3.2 Supply Chain
			3.3.2.1 Bolstering Planning & Scheduling Activities
			3.3.2.2 Intelligent Decision-Making
			3.3.2.3 End-End Visibility
			3.3.2.4 Actionable Analytical Insights
			3.3.2.5 Inventory and Demand Management
			3.3.2.6 Boosting Operational Efficiencies
	3.4 Conclusion
	References
4 An Empirical Study of Crop Yield Prediction Using Reinforcement Learning
	4.1 Introduction
	4.2 An Overview of Reinforcement Learning in Agriculture
		4.2.1 Reinforcement Terminology and Definitions
		4.2.2 Review on Agricultural Reinforcement Learning
	4.3 Reinforcement Learning Startups for Crop Prediction
		4.3.1 Need for Crop Prediction
		4.3.2 Reinforcement Learning Impacts on Agriculture
		4.3.3 Deep Q Networks for Crop Prediction
	4.4 Conclusion
	References
5 Cost Optimization for Inventory Management in Blockchain and Cloud
	5.1 Introduction
	5.2 Blockchain: The Future of Inventory Management
		5.2.1 Issues Faced in Inventory Management
		5.2.2 Inventory Management Scenario
		5.2.3 A Primer on Blockchain Technology
		5.2.4 Blockchain for Proactive Inventory Management
	5.3 Cost Optimization for Blockchain Inventory Management in Cloud
		5.3.1 Optimizing Blockchain Inventory Management
		5.3.2 Best Practices of Blockchain Inventory Cost Optimization in Cloud
			5.3.2.1 Criticality Analysis
			5.3.2.2 Demand Forecasting
			5.3.2.3 Lead Time Forecasting
			5.3.2.4 Issue Size Forecasting
			5.3.2.5 Economic Modeling
			5.3.2.6 Optimization of Reordering Parameters
			5.3.2.7 Exception Management
			5.3.2.8 Inventory Segmentation
			5.3.2.9 Spares Risk Assessment
			5.3.2.10 Spares Pooling
			5.3.2.11 Knowledge Capture
			5.3.2.12 Reporting Inventory
	5.4 Cost Reduction Strategies in Blockchain Inventory Management in Cloud
		5.4.1 Reduce Useless Inventory
		5.4.2 Let Experts Manage Inventory (VMI)
		5.4.3 Develop Relationships With Suppliers
		5.4.4 Install Industrial Vending Machines
		5.4.5 Order Smaller, More Frequently
	5.5 Conclusion
	References
6 Review of Deep Learning Architectures Used for Identification and Classification of Plant Leaf Diseases
	6.1 Introduction
	6.2 Literature Review
	6.3 Proposed Idea
	6.4 Reference Gap
	6.5 Conclusion
	References
7 Generating Art and Music Using Deep Neural Networks
	7.1 Introduction
		7.1.1 Traditional Approach
		7.1.2 Modern Computing Approach
	7.2 Related Works
		7.2.1 Feeling Investigation on Social Media
	7.3 System Architecture
		7.3.1 Art Module
		7.3.2 Music Module
	7.4 System Development
		7.4.1 Upload Module
		7.4.2 Conversion Module
		7.4.3 Transformation Module
		7.4.4 Loading Dataset Module
		7.4.5 Optimizing Module
			7.4.5.1 Calculating Loss Function
		Lcontent(c,x) & Lstyle(s,x)
	7.5 Algorithm-LSTM
	7.6 Result
		7.6.1 Sample Input and Output
	7.7 Conclusions
	References
8 Deep Learning Era for Future 6G Wireless Communications—Theory, Applications, and Challenges
	8.1 Introduction
	8.2 Study of Wireless Technology
		8.2.1 Overview
		8.2.2 Background Study
		8.2.3 6G Wireless Technology
		8.2.4 Influence of AI in 6G Wireless Communication
	8.3 Deep Learning Enabled 6G Wireless Communication
		8.3.1 Deep Learning Techniques for 6G Networks
		8.3.2 Predicted Services in the 6G Era
			8.3.2.1 Internet-of-(Every)Thing
			8.3.2.2 Connected Vehicles
			8.3.2.3 Smart Cities
			8.3.2.4 Robotics and Industry
	8.4 Applications and Future Research Directions
	Conclusion
	References
9 Robust Cooperative Spectrum Sensing Techniques for a Practical Framework Employing Cognitive Radios in 5G Networks
	9.1 Introduction
	9.2 Spectrum Sensing in Cognitive Radio Networks
	9.3 Collaborative Spectrum Sensing for Opportunistic Access in Fading Environments
	9.4 Cooperative Sensing Among Cognitive Radios
	9.5 Cluster-Based Cooperative Spectrum Sensing for Cognitive Radio Systems
	9.6 Spectrum Agile Radios: Utilization and Sensing Architectures
	9. 7 Some Fundamental Limits on Cognitive Radio
	9.8 Cooperative Strategies and Capacity Theorems for Relay Networks
	9.9 Research Challenges in Cooperative Communication
	9.10 Conclusion
	References
10 Natural Language Processing
	10.1 Introduction
	10.2 Conclusions
	References
11 Class Level Multi-Feature Semantic Similarity-Based Efficient Multimedia Big Data Retrieval
	11.1 Introduction
	11.2 Literature Review
	11.3 Class Level Semantic Similarity-Based Retrieval
	11.4 Results and Discussion
		11.4.1 Performance Analysis vs Number of Classes
		11.4.2 Performance Analysis vs. Number of Terms/Relations
	Conclusion
	References
12 Supervised Learning Approaches for Underwater Scalar Sensory Data Modeling With Diurnal Changes
	12.1 Introduction
	12.2 Literature Survey
		12.2.1 Underwater Channel Models
	12.3 Proposed Work
		12.3.1 Statistical Analysis Using Software Tools
	12.4 Results
		12.4.1 Statistical Works
			12.4.1.1 Auto Correlation and Partial Auto Correlation Analysis of Depth and Temperature
		12.4.2 Attenuation Results
	12.5 Conclusion and Future Work
	References
13 Multi-Layer UAV Ad Hoc Network Architecture, Protocol and Simulation
	13.1 Introduction
		13.1.1 Flying Ad Hoc Networks (FANETs)
		13.1.2 Multi-Layer-Based UAVs Ad Hoc Network
	13.2 Background
	13.3 Issues and Gap Identified
	13.4 Main Focus of the Chapter
	13.5 Mobility
		13.5.1 Mobility Model
		13.5.2 Reference-Point-Group Mobility Model (RPGM)
		13.5.3 Spatial Dependency-Based Mobility Model
			13.5.3.1 Degree of Spatial-Dependency
	13.6 Routing Protocol
		13.6.1 Data-Centric-Routing-Protocol (DCRP)
	13.7 High Altitude Platforms (HAPs)
		13.7.1 Characteristics of HAP
		13.7.2 Advantages of HAPs
	13.8 Connectivity Graph Metrics
		13.8.1 Link Changes Counts
		13.8.2 Link Duration
		13.8.3 Path-Availability
	13.9 Aerial Vehicle Network Simulator (AVENs)
	13.10 Conclusion
	References
14 Artificial Intelligence in Logistics and Supply Chain
	14.1 Introduction to Logistics and Supply Chain
		Agriculture
		Manufacturing
		Artificial Intelligence (AI) Tools
		Transportation
		14.1.1 Elements of Supply Chain Network
		14.1.2 Supply Chain Performances and Costing
			14.1.2.1 Performance Measure
			14.1.2.2 Procurement Cost
			14.1.2.3 Transportation Cost
			14.1.2.4 Inventory Cost
	14.2 Recent Research Avenues in Supply Chain
		14.2.1 Vendor Selection
		14.2.2 Transportation
		14.2.3 Inventory Routing
		14.2.4 Agent-Based Modeling
		14.2.5 Reverse Logistics
	14.3 Importance and Impact of AI
		14.3.1 Benefits
		14.3.2 Challenges
			14.3.2.1 Supply Chain Risk Estimation
			14.3.2.2 Green Supply Chain (GSC)
	14.4 Research Gap of AI-Based Supply Chain
		14.4.1 Healthcare
			14.4.1.1 Pharmaceutical
			14.4.1.2 Medical Devices
			14.4.1.3 Fast Moving Consumer Goods
		14.4.2 Networked Manufacturing
		14.4.3 Humanitarian Supply Chain Network
	Conclusion
	References
15 Hereditary Factor-Based MultiFeatured Algorithm for Early Diabetes Detection Using Machine Learning
	15.1 Introduction
		15.1.1 Role of Data Mining Tools in Healthcare for Predicting Various Diseases
	15.2 Literature Review
	15.3 Objectives of the Proposed System
	15.4 Proposed System
	15.5 HIVE and R as Evaluation Tools
	15.6 Decision Trees
	15.7 Results and Discussions
	15.8 Conclusion
	References
16 Adaptive and Intelligent Opportunistic Routing Using Enhanced Feedback Mechanism
	16.1 Introduction
	16.2 Related Study
	16.3 System Model
		16.3.1 Dividing Packets Into Blocks
		16.3.2 Packet Transmission
		16.3.3 Feedback
	16.4 Experiments and Results
	16.5 Conclusion
	References
17 Enabling Artificial Intelligence and Cyber Security in Smart Manufacturing
	17.1 Introduction
	17.2 New Development of Artificial Intelligence
	17.3 Artificial Intelligence Facilitates the Development of Intelligent Manufacturing
	17.4 Current Status and Problems of Green Manufacturing
		17.4.1 Green Manufacturing
		17.4.2 Current Status and Major Problems
			17.4.2.1 Isolation of Information Among Multiple Fields
			17.4.2.2 Diverse Information Types and Different Kinds of Data
			Lack of a Process-Safety-Oriented Decision-Making System
			Lack of Early Warning and Risk Tracing Systems
	17.5 Artificial Intelligence for Green Manufacturing
		17.5.1 Information Integration via Knowledge Graphs
			17.5.1.1 Process-Safety Information Extraction
			17.5.1.2 Process-Safety Knowledge Fusion
			17.5.1.3 Process-Safety Knowledge Processing
		17.5.2 Risk Assessment and Decision-Making Using Bayesian Networks
		17.5.3 Incident Early Warning Based on Deep Learning
	17.6 Detailed Description of Common Encryption Algorithms
		17.6.1 Triple DES (3DES)—(Triple Data Encryption Standard)
	17.7 Current and Future Works
	17.8 Conclusion
	References
18 Deep Learning in 5G Networks
	18.1 5G Networks
	18.2 Artificial Intelligence and 5G Networks
	18.3 Deep Learning in 5G Networks
	Conclusion
	References
19 EIDR Umpiring Security Models for Wireless Sensor Networks
	19.1 Introduction
	19.2 A Review of Various Routing Protocols
		19.2.1 Trust-Based Routing Protocols
		19.2.2 Intrusion Detection System
		19.2.3 The Network Layer Routing Protocols
			19.2.3.1 WRP
			19.2.3.2 AODV
			19.2.3.3 LEACH Protocols
	19.3 Scope of Chapter
		19.3.1 Objective
		19.3.2 Contributions
		19.3.3 Performance Evaluations
	19.4 Conclusions and Future Work
	References
20 Artificial Intelligence in Wireless Communication
	20.1 Introduction
	20.2 Artificial Intelligence: A Grand Jewel Mine
	20.3 Wireless Communication: An Overview
	20.4 Wireless Revolution
	20.5 The Present Times
	20.6 Artificial Intelligence in Wireless Communication
		20.6.1 How the Two Worlds Collided
		20.6.2 Cognitive Radios
	20.7 Artificial Neural Network
	20.8 The Deployment of 5G
	20.9 Looking Into the Features of 5G
	20.10 AI and the Internet of Things (IoT)
	20.11 Artificial Intelligence in Software-Defined Networks (SDN)
	20.12 Artificial Intelligence in Network Function Virtualization
	20.13 Conclusion
	References
Index
Also of Interest