Machine Learning and Cognitive Computing for Mobile Communications and Wireless Networks

Krishna Kant Singh is an Associate Professor in Electronics and Communications Engineering in KIET Group of Institutions, Ghaziabad, India. Dr. Singh has acquired BTech, MTech, and PhD (IIT Roorkee) in the area of machine learning and remote sensing. He has authored more than 50 technical books and research papers in international conferences and SCIE journals. Akansha Singh is an Associate Professor in Department of Computer Science Engineering in Amity University, Noida, India. Dr. Singh has acquired BTech, MTech, and PhD (IIT Roorkee) in the area of neural network and remote sensing. She has authored more than 40 technical books and research papers in international conferences and SCIE journals. Her area of interest includes Mobile Computing, Artificial Intelligence, Machine Learning, Digital Image Processing. Korhan Cengiz received his PhD in Electronics Engineering from Kadir Has University, Istanbul, Turkey, in 2016. He has served as keynote speakers at many conferences. His research interests include wireless sensor networks, routing protocols, wireless communications, 5G systems, statistical signal processing, and spatial modulation. Dac-Nhuong Le has a MSc and PhD in computer science from Vietnam National University, Vietnam in 2009 and 2015, respectively. He is Associate Professor in Computer Science, Deputy-Head of Faculty of Information Technology, Haiphong University, Vietnam. He has a total academic teaching experience of 12+ years with many publications in reputed international conferences, journals and online book chapters. His area of research includes: evaluation computing and approximate algorithms, network communication, security and vulnerability, network performance analysis and simulation, cloud computing, IoT and image processing in biomedical.

• Preface xiii1 Machine Learning Architecture and Framework 1Nilanjana Pradhan and Ajay Shankar Singh1.1 Introduction 21.2 Machine Learning Algorithms 31.2.1 Regression 31.2.2 Linear Regression 41.2.3 Support Vector Machine 41.2.4 Linear Classifiers 51.2.5 SVM Applications 81.2.6 Naïve Bayes Classification 81.2.7 Random Forest 91.2.8 K-Nearest Neighbor (KNN) 91.2.9 Principal Component Analysis (PCA) 91.2.10 K-Means Clustering 101.3 Business Use Cases 101.4 ML Architecture Data Acquisition 141.5 Latest Application of Machine Learning 151.5.1 Image Identification 161.5.2 Sentiment Analysis 161.5.3 News Classification 161.5.4 Spam Filtering and Email Classification 171.5.5 Speech Recognition 171.5.6 Detection of Cyber Crime 171.5.7 Classification 171.5.8 Author Identification and Prediction 181.5.9 Services of Social Media 181.5.10 Medical Services 181.5.11 Recommendation for Products and Services 181.5.11.1 Machine Learning in Education 191.5.11.2 Machine Learning in Search Engine 191.5.11.3 Machine Learning in Digital Marketing 191.5.11.4 Machine Learning in Healthcare 191.6 Future of Machine Learning 201.7 Conclusion 22References 232 Cognitive Computing: Architecture, Technologies and Intelligent Applications 25Nilanjana Pradhan, Ajay Shankar Singh and Akansha Singh2.1 Introduction 262.1 The Components of a Cognitive Computing System 272.3 Subjective Computing Versus Computerized Reasoning 282.4 Cognitive Architectures 292.5 Subjective Architectures and HCI 312.6 Cognitive Design and Evaluation 322.6.1 Architectures Conceived in the 1940s Can’t Handle the Data of 2020 412.7 Cognitive Technology Mines Wealth in Masses of Information 412.7.1 Technology is Only as Strong as Its Flexible, Secure Foundation 422.8 Cognitive Computing: Overview 432.9 The Future of Cognitive Computing 47References 493 Deep Reinforcement Learning for Wireless Network 51Bharti Sharma, R.K Saini, Akansha Singh and Krishna Kant Singh3.1 Introduction 513.2 Related Work 543.3 Machine Learning to Deep Learning 553.3.1 Advance Machine Learning Techniques 563.3.1.1 Deep Learning 563.3.2 Deep Reinforcement Learning (DRL) 573.3.2.1 Q-Learning 583.3.2.2 Multi-Armed Bandit Learning (MABL) 583.3.2.3 Actor–Critic Learning (ACL) 583.3.2.4 Joint Utility and Strategy Estimation Based Learning 593.4 Applications of Machine Learning Models in Wireless Communication 593.4.1 Regression, KNN and SVM Models for Wireless 603.4.2 Bayesian Learning for Cognitive Radio 603.4.3 Deep Learning in Wireless Network 613.4.4 Deep Reinforcement Learning in Wireless Network 623.4.5 Traffic Engineering and Routing 633.4.6 Resource Sharing and Scheduling 643.4.7 Power Control and Data Collection 643.5 Conclusion 65References 664 Cognitive Computing for Smart Communication 73Poonam Sharma, Akansha Singh and Aman Jatain4.1 Introduction 744.2 Cognitive Computing Evolution 754.3 Characteristics of Cognitive Computing 764.4 Basic Architecture 774.4.1 Cognitive Computing and Communication 774.5 Resource Management Based on Cognitive Radios 784.6 Designing 5G Smart Communication with Cognitive Computing and AI 804.6.1 Physical Layer Design Based on Reinforcement Learning 824.7 Advanced Wireless Signal Processing Based on Deep Learning 844.7.1 Modulation 854.7.2 Deep Learning for Channel Decoding 864.7.3 Detection Using Deep Learning 874.8 Applications of Cognition-Based Wireless Communication 874.8.1 Smart Surveillance Networks for Public Safety 884.8.2 Cognitive Health Care Systems 884.9 Conclusion 89References 895 Spectrum Sensing and Allocation Schemes for Cognitive Radio 91Amrita Rai, Amit Sehgal, T.L. Singal and Rajeev Agrawal5.1 Foundation and Principle of Cognitive Radio 925.2 Spectrum Sensing for Cognitive Radio Networks 945.3 Classification of Spectrum Sensing Techniques 955.4 Energy Detection 975.5 Matched Filter Detection 1005.6 Cyclo-Stationary Detection 1035.7 Euclidean Distance-Based Detection 1075.8 Spectrum Allocation for Cognitive Radio Networks 1085.9 Challenges in Spectrum Allocation 1185.9.1 Spectrum and Network Heterogeneity 1195.9.2 Issues and Challenges 1205.10 Future Scope in Spectrum Allocation 122References 1236 Significance of Wireless Technology in Internet of Things (IoT) 131Ashish Tripathi, Arun Kumar Singh, Pushpa Choudhary, Prem Chand Vashist and K. K. Mishra6.1 Introduction 1326.1.1 Internet of Things: A Historical Background 1336.1.2 Internet of Things: Overview, Definition, and Understanding 1336.1.3 Internet of Things: Existing and Future Scopes 1356.2 Overview of the Hardware Components of IoT 1366.2.1 IoT Hardware Components: Development Boards/Platforms 1366.2.1.1 Arduino 1366.2.1.2 Raspberry Pi 1376.2.1.3 BeagleBone 1376.2.2 IoT Hardware Components: Transducer 1386.2.2.1 Sensors 1386.2.2.2 Actuators 1386.3 Wireless Technology in IoT 1396.3.1 Topology 1396.3.1.1 Mesh Topology 1406.3.1.2 Star Topology 1416.3.1.3 Point-to-Point Topology 1416.3.2 IoT Networks 1426.3.2.1 Nano Network 1426.3.2.2 Near-Field Communication (NFC) Network 1436.3.2.3 Body Area Network (BAN) 1436.3.2.4 Personal Area Network (PAN) 1436.3.2.5 Local Area Network (LAN) 1436.3.2.6 Campus/Corporate Area Network (CAN) 1436.3.2.7 Metropolitan Area Network (MAN) 1446.3.2.8 Wide Area Network (WAN) 1446.3.3 IoT Connections 1446.3.3.1 Device-to-Device (D2D)/Machine-to-Machine (M2M) 1446.3.3.2 Machine-to-Gateway/Router (M2G/R) 1456.3.3.3 Gateway/Router-to-Data System (G/R2DS) 1456.3.3.4 Data System to Data System (DS2DS) 1456.3.4 IoT Protocols/Standards 1456.3.4.1 Network Protocols for IoT 1466.3.4.2 Data Protocols for IoT 1486.4 Conclusion 150References 1507 Architectures and Protocols for Next-Generation Cognitive Networking 155R. Ganesh Babu, V. Amudha and P. Karthika7.1 Introduction 1567.1.1 Primary Network (Licensed Network) 1567.1.2 CR Network (Unlicensed Network) 1577.2 Cognitive Radio Network Technologies and Applications 1597.2.1 Classes of CR 1597.2.2 Next Generation (xG) of CR Applications 1627.3 Cognitive Computing: Architecture, Technologies, and Intelligent Applications 1637.3.1 CR Physical Architecture 1637.4 Functionalities of CR in NeXt Generation (xG) Networks 1647.5 Spectrum Sensing 1657.5.1 Spectrum Decision 1657.5.2 Spectrum Mobility 1657.5.3 CR Network Functions 1667.6 Cognitive Computing for Smart Communications 1677.6.1 CR Technologies 1677.7 Spectrum Allocation in Cognitive Radio 1697.8 Cooperative and Cognitive Network 1737.8.1 Cooperative Centralized Coordinated 1737.8.2 Cooperative Decentralized (Distributed) Coordinated and Uncoordinated 176References 1768 Analysis of Peak-to-Average Power Ratio in OFDM Systems Using Cognitive Radio Technology 179Udayakumar Easwaran, Poongodi Palaniswamy and Vetrivelan Ponnusamy8.1 Introduction 1808.2 OFDM Systems 1818.3 Peak-to-Average Power Ratio 1838.4 Cognitive Radio (CR) 1848.5 Related Works 1868.6 Neural Network System Model 1938.7 Complexity Examination 1948.8 PAPR and BER Examination 1958.9 Performance Evaluation 1968.10 Results and Discussions 1968.11 Conclusion 200References 2009 A Threshold-Based Optimization Energy-Efficient Routing Technique in Heterogeneous Wireless Sensor Networks 203Samayveer Singh9.1 Introduction 2049.2 Literature Review 2059.3 System Model 2079.3.1 Four-Level Heterogeneous Network Model 2089.3.2 Energy Dissipation Radio Model 2109.4 Proposed Work 2119.4.1 Optimum Cluster Head Election of the Proposed Protocol 2119.4.2 Information Congregation and Communication Process Based on Chaining System for Intra and Inter‑Cluster Communication 2149.4.3 The Complete Working Process of the Proposed Method 2149.5 Simulation Results and Discussions 2169.5.1 Network Lifetime and Stability Period 2179.5.2 Network Outstanding Energy 2199.5.3 Throughput 2199.5.4 Comparative Analysis of the Level-4 Network Protocols 2229.6 Conclusion 222References 22310 Efficacy of Big Data Application in Smart Cities 225Sudipta Sahana, Dharmpal Singh and Pranati Rakshit10.1 Introduction 22610.1.1 Characteristics of Big Data 22710.1.1.1 Velocity 22710.1.1.2 Volume 22710.1.1.3 Value 22810.1.1.4 Variety 22810.1.1.5 Veracity 22810.1.2 Definition of Smart Cities 22810.2 Types of Data in Big Data 22910.2.1 Structured Data 22910.2.2 Unstructured Data 23010.2.3 Semi-Structured Data 23010.3 Big Data Technologies 23110.3.1 Apache Hadoop 23110.3.2 HDFS 23110.3.3 Spark 23210.3.4 Microsoft HDInsight 23210.3.5 NoSQL 23310.3.6 Hive 23310.3.7 Sqoop 23410.3.8 R 23510.3.9 Data Lakes 23510.4 Data Source for Big Data 23510.4.1 Media 23610.4.2 Cloud 23610.4.3 The Web 23610.4.4 IOT 23610.4.5 Databases as a Big Data Source 23710.4.6 Hidden Big Data Sources 23710.4.6.1 Email 23710.4.6.2 Social Media 23810.4.6.3 Open Data 23810.4.6.4 Sensor Data 23810.4.7 Application-Oriented Big Data Source for a Smart City 23810.4.7.1 Healthcare 23810.4.7.2 Transportation 23910.4.7.3 Education 24010.5 Components of a Smart City 24110.5.1 Smart Infrastructure 24110.5.1.1 Intelligent Lighting 24110.5.1.2 Modern Parking Systems 24110.5.1.3 Associated Charging Points 24210.5.2 Smart Buildings and Belongings 24210.5.2.1 Safety and Security Systems 24210.5.2.2 Smart Sprinkler Systems for Gardens 24210.5.2.3 Smart Heating and Ventilation 24210.5.3 Smart Industrial Environment 24310.5.4 Smart City Services 24310.5.4.1 Smart Stalls 24310.5.4.2 Monitoring of Risky Areas 24410.5.4.3 Public Safety 24410.5.4.4 Fire/Explosion Management 24410.5.4.5 Automatic Health-Care Delivery 24410.5.5 Smart Energy Management 24410.5.5.1 Smart Grid 24510.5.5.2 Intelligent Meters 24510.5.6 Smart Water Management 24510.5.7 Smart Waste Management 24510.6 Challenge and Solution of Big Data for Smart City 24610.6.1 Challenge in Big Data for Smart City 24610.6.1.1 Data Integration 24610.6.1.2 Security and Privacy 24610.6.1.3 Data Analytics 24710.6.2 Solution of Challenge Smart City 24710.6.2.1 Conquering Difficulties with Enactment 24710.6.2.2 Making People Smarter—Education for Everyone 24810.7 Conclusion 248References 249Index 251