Intelligent Communication Networks : Research and Applications / edited by Rajarshi Mahapatra, Siddhartha Bhattacharyya, and Avishek Nag.

Format:

Book

Contributor:

Mahapatra, Rajarshi, editor.

Bhattacharyya, Siddhartha, editor.

Nag, Avishek, editor.

Language:

English

Subjects (All):

Telecommunication systems--Technological innovations.

Telecommunication systems.

Artificial intelligence--Engineering applications.

Artificial intelligence.

Physical Description:

1 online resource (257 pages)

Edition:

First edition.

Place of Publication:

Boca Raton, FL : CRC Press, [2024]

Summary:

The text presents the basic understanding of the machine learning algorithms used for communication networks in a single volume. It will serve as an ideal reference text for senior undergraduate, graduate students, and academic researchers in diverse engineering domains including electrical, electronics and communication, computer.

Contents:

Cover

Half Title

Title Page

Copyright Page

Dedication

Table of Contents

Preface

Editors

Contributors

Chapter 1: Various Deep Learning-based Resource Allocation Techniques in Wireless Communication System

1.1 The Next-Generation Wireless Communication Systems

1.2 Machine Learning Algorithms

1.2.1 Deep Neural Networks

1.2.2 Deep Reinforcement Learning

1.2.3 Centralized Learning

1.2.4 Distributed Learning

1.2.5 Federated Learning

1.2.6 Deep Learning in Resource Allocation

1.3 Heterogeneous Network

1.4 Reinforcement Learning

1.5 Federated Learning

1.6 Federated Deep Reinforcement Learning in Resource Allocation

1.6.1 Overview of Federated Deep Reinforcement Learning (FDRL) in Resource Allocation

1.6.2 Applying Federated Deep Reinforcement Learning in Resource Allocation

1.6.2.1 Challenges and Advantages

References

Chapter 2: Federated Deep Reinforcement Learning-based Resource Allocation in Heterogeneous Networks

2.1 Introduction

2.1.1 Supervised Learning-based Resource Allocation

2.1.2 Unsupervised Learning-based Resource Allocation

2.1.3 Learning Assisted Optimization for Resource Allocation

2.1.4 Deep Reinforcement Learning for Resource Allocation

2.1.4.1 Deep Q-Networks

2.1.4.2 Deep Deterministic Policy Gradient

2.1.5 Federated Learning-based Resource Allocation

2.2 Reinforcement Learning in Resource Allocation

2.3 Aim of the Chapter

2.4 System Model

2.5 Proposed Federated-DRL Algorithm

2.6 Simulation Results

2.6.1 Spectral Efficiency Performance

2.6.2 Timing and Complexity Analysis

2.7 Summary

Chapter 3: A Comprehensive Overview of Internet of Nano-Things (IoNT) in the Next-Generation Heterogeneous Networks: Deployment Aspects, Applications, and Challenges

3.1 Introduction.

3.2 Comparison to Other Studies

3.2.1 5G and IoNT

3.2.2 IoNT Characteristics and Architecture

3.2.2.1 IoNT Characteristics

3.2.2.2 IoNT Architecture

3.2.3 IoNT-Enabling Technologies

3.2.4 IoNT Applications

3.2.5 IoNT Network Architecture and Standards

3.2.5.1 Physical Layer

3.2.5.2 Link Layer

3.2.5.3 Network Layer

3.2.5.4 Upper Layers

3.2.5.5 Standards

3.2.6 Big Data Analytics, Cloud Computing, and Fog Computing in Support of the IoNT

3.2.6.1 Big Data Analytics in Support of the IoNT

3.2.6.2 Cloud Computing in Support of the IoNT

3.2.6.3 Fog Computing in Support of the IoNT

3.2.7 Deployment Aspects of the IoNT

3.2.7.1 Random vs. Deterministic

3.2.7.2 Static vs. Dynamic

3.2.8 Open Research Issues and Future Challenges

3.2.8.1 Architecture and Protocols

3.2.8.2 Reliability

3.2.8.3 Throughput

3.2.8.4 Lifetime

3.2.8.5 Data Collection and Routing Technology

3.2.8.6 Security and Privacy

3.2.8.7 Service Discovery

3.2.8.8 Context Awareness

3.3 Conclusion

Chapter 4: Emerging World of the Metaverse: An Indian Perspective

4.1 Introduction

4.2 Internet of Things and Virtual Reality

4.3 Emergence of the Metaverse

4.4 Network and Communication in the Metaverse

4.4.1 Building Smart Cities with the Metaverse

4.4.2 Industry 4.0 and Digital Twin

4.5 Socialization in the Metaverse

4.6 The Metaverse in India

4.7 Technological Limitations

4.8 Data Safety and Security

4.9 Dilemmas and Conundrum of the Metaverse

4.10 Future of the Metaverse

4.10.1 Metaverse for Business Ideas

4.10.2 Customer User Engagement

4.10.3 Legal Framework in the Metaverse

4.11 Conclusion

Chapter 5: Intelligent Optical Networks: Challenges, Opportunities, and Applications

5.1 Introduction.

5.2 Overview of Intelligent Optical Networks

5.2.1 Evolution of Optical Network Transmission Technology

5.2.2 Optical Network Functionality

5.2.3 Categories of Optical Networks

5.2.4 Classification of Machine Learning

5.2.4.1 Supervised Learning

5.2.4.2 Unsupervised Learning

5.2.4.3 Reinforcement Learning

5.2.5 Techniques for Generation of Data and Modeling Images

5.2.6 Metrics-Classification Metrics, Regression Metrics, and Rand and Jaccard Indices

5.3 Challenges and Opportunities in Intelligent Optical Networks

5.3.1 Challenges in Intelligent Optical Networks

5.3.2 Opportunities in Intelligent Optical Networks

5.4 Applications in Intelligent Optical Networks

5.4.1 Artificial Intelligence in Optical Networks

5.4.2 Machine Learning in Optical Networks

5.4.2.1 ML Approaches to Physical Layer Applications

5.4.2.2 ML Approaches to Network Layer Applications

5.4.3 Big Data Analytics in Optical Networks

5.5 Various Simulation Tools for Intelligent Optical Networks

5.5.1 Simulation Study

5.5.2 Result and Inferences

5.6 Conclusion

Acknowledgement

Chapter 6: Machine Learning for Non-Orthogonal Multiple Access

6.1 Introduction: Background and Driving Forces

6.2 PD NOMA

6.3 CR NOMA

6.4 Multi-Carrier NOMA

6.5 Cooperative NOMA

6.5.1 Employing Dedicated Relays

6.6 Millimeter Wave NOMA

6.7 Detection in NOMA: From SIC to Deep Learning

6.8 Practical Implementation of NOMA

6.8.1 Modulation and Coding for NOMA

6.8.2 Imperfect CSI

6.9 NOMA with Machine Learning

6.9.1 Different Aspect of ML in NOMA Networks

6.10 Future Challenges

6.10.1 NOMA with Heterogeneous Networks

6.10.2 NOMA with Simultaneous Wireless Information and Power Transfer (SWIPT)

6.10.3 NOMA with Visible Light Communication (VLC)

6.11 Conclusions

References.

Chapter 7: Compensating Inbound Signal Strength for Radio-Controlled Mobile Robots Using ANFIS

7.1 Introduction

7.2 Using Fuzzy Logic to Create Telecommunication Systems

7.3 The ANFIS Method

7.4 Training a Neuro-Fuzzy System Based on the Area Difference Method

7.5 Aggregation of Output Values

7.6 Conclusions

Acknowledgment

Author Contributions

Chapter 8: Optimizing Wireless Sensor Networks Using Machine Learning

8.1 Introduction

8.2 Sensor Network

8.2.1 Types of WSN

8.2.2 Applications of WSN

8.2.3 Challenges in WSN and Design Objectives

8.3 Machine Learning (ML)

8.3.1 Supervised Machine Learning

8.3.2 Unsupervised Learning

8.3.2.1 Clustering

8.3.2.2 Dimension Reduction

8.3.3 Reinforcement Learning

8.3.4 Deep Learning

8.4 ML for Optimizing WSNs

8.4.1 Security

8.4.1.1 Anomaly Detection

8.4.1.2 Intrusion Detection

8.4.2 Routing

8.4.3 Data Aggregation

8.4.4 Coverage and Connectivity

8.4.5 Localization

8.4.6 Quality of Service (QoS)

8.4.7 Energy Harvesting

8.4.8 Congestion Control

8.4.9 Challenges of ML for WSN

8.5 ML in WSN Applications

8.6 Conclusions

Chapter 9: Machine Learning-Assisted Interference Management in the 6G UAV Networks with Soft Frequency Reuse

9.1 Introduction

9.2 Related Works

9.3 UAV-Assisted Wireless Networks

9.4 Soft Frequency Reuse in UAV-Assisted Networks

9.5 Proposed Machine Learning Model

9.6 Simulation Results and Analysis

9.7 Conclusions

Chapter 10: Computational Intelligence in Communication Networks: Classification, Clustering, Reinforcement Learning, Deep Learning

10.1 Introduction

10.1.1 Neural Networks

10.1.2 Fuzzy Systems

10.1.3 Evolutionary Computation

10.2 Differences Between Computational Intelligence and Artificial Intelligence.

10.3 Details of Computational Intelligence

10.3.1 Branches of Computational Intelligence

10.3.2 Principles of CI and Application

10.3.2.1 Fuzzy Logic

10.3.2.2 Neural Networks

10.3.2.3 Evolutionary Computation

10.3.2.4 Natural Language Processing

10.3.2.5 Probabilistic Methods

10.3.3 Implementation of CI

10.3.3.1 Using a Mobile Phone as an Example

10.4 Computational Intelligence in Communication Network

10.5 Conclusion

Index.

Notes:

Includes bibliographical references and index.

Description based on publisher supplied metadata and other sources.

Description based on print version record.

ISBN:

9781040032466

104003246X

9781040032381

1040032389

9781003303114

1003303110

OCLC:

1430661173