Note: Cover -- Half Title -- Series Information -- Title Page -- Copyright Page -- Table of Contents -- Preface -- Editors -- Abbreviations -- Part I Computational Intelligence: Edge AI Services -- Chapter 1 Edge Computational Intelligence: Fundamentals, Trends, and Applications -- 1.1 Introduction -- 1.2 Mainframe-Based Computing Model -- 1.3 PC File Server-Based Computing Model -- 1.4 C/S Architecture-Based Computing Model -- 1.5 Web and B/S Architecture-Based Computing Model -- 1.6 Mobile Devices-Centric Computing Model -- 1.7 Technologies-Based Computing Model -- 1.8 End-Edge-Cloud Computing Model -- 1.9 EC Trends -- 1.9.1 Heterogeneous Computing -- 1.9.2 Edge Intelligence (EI) -- 1.9.3 Edge Cloud Interface -- 1.9.4 5G + Edge Computing -- 1.10 EC Applications in Industry -- 1.10.1 Cloud Service Provider-Based Model -- 1.10.2 Site Facility Edge Service -- 1.10.3 Fixed Operator-Enabled EC Services -- 1.10.4 Mobile Operator-Centric EC Services -- 1.10.5 EC as a Self-Organizing Network -- 1.10.6 Near End Computing Services -- 1.11 Intelligent Edge (IE) and Edge Intelligence (EI) -- 1.11.1 Cost -- 1.11.2 Latency -- 1.11.3 Reliability -- 1.11.4 Privacy -- 1.12 Edge Computing -- 1.13 Edge AI & -- Its Need -- 1.14 Maturation of Neural Networks -- 1.15 Advancements in Computer Infrastructure -- 1.15.1 Use of IoT Devices -- 1.15.2 AI at the Edge: Requirement -- 1.15.3 Benefits of Cloud Computing and Edge Computing -- 1.16 Working of Edge AI -- 1.17 Advantages of Edge AI -- 1.17.1 Intelligence -- 1.17.2 Real-Time -- 1.17.3 Inexpensive -- 1.17.4 Improved Privacy -- 1.17.5 Abundancy -- 1.17.6 Persistency -- 1.17.7 Edge AI Future -- 1.18 Representative Applications of Edge AI -- 1.18.1 Smart Energy Forecasting -- 1.18.2 Predictive Analysis and Maintenance -- 1.18.3 AI-Driven Devices in Healthcare -- 1.18.4 Intelligent Virtual Assistants. , 1.18.5 Cloudlet and Micro-Data Centers -- 1.19 Fog Computing -- 1.20 Mobile Edge Computing -- 1.21 EC Terminologies -- 1.22 End-Edge-Cloud Computing -- 1.23 Hardware for EC -- 1.24 AI Hardware for EC -- 1.24.1 GPU-Enabled Hardware -- 1.24.2 Field Programmable Gate Array (FPGA)-Enabled Hardware [33, 34] -- 1.24.3 Integrated Circuit (ASIC)-Based Hardware -- 1.24.4 Potential of Integrated Commodities for Edge Nodes -- 1.25 EC Frameworks -- 1.25.1 Design Goals -- 1.25.2 End Users -- 1.25.3 Up-Scaling -- 1.25.4 System Characteristics -- 1.25.5 Application Environments -- 1.26 Edge Virtualization -- 1.26.1 Virtualization Strategies -- 1.26.2 Virtualizing Network -- 1.26.3 Network Slicing -- 1.26.4 Value Scenarios (VS) -- 1.26.5 Smart Parks -- 1.27 Video Surveillance -- 1.28 Industrial Internet of Things (IIoT) -- 1.29 Conclusion -- References -- Chapter 2 Securing IoT Services Using Artificial Intelligence in Edge Computing -- 2.1 Introduction -- 2.2 Conception and Depictions -- 2.2.1 IoT Service -- 2.2.2 Edge Computing -- 2.3 Framework of IoT Service With EC -- 2.3.1 Layer of Device -- 2.3.2 Layer of Network -- 2.3.3 Layer of Edge -- 2.3.4 Layer of Cloud -- 2.4 Privacy Maintenance With AI for Edge-Enabled IoT Services -- 2.4.1 Traditional Encryption Methods -- 2.4.1.1 Anonymization -- 2.4.1.2 Cryptographic Method -- 2.4.1.3 Data Obfuscation -- 2.4.2 AI-Based Privacy-Preserving Methods in ENs -- 2.4.2.1 CNN-Based Privacy Preservation -- 2.4.2.2 Privacy Preservation Using DNNs -- 2.5 Edge-Enabled IoT Services With AI and Blockchain -- 2.5.1 Blockchain for IoT Services' Security -- 2.5.1.1 Authentication Management and Access Control -- 2.5.1.2 Reliability and Confidentiality of Data -- 2.5.2 Blockchain for Edge-Enabled IoT Data Sharing -- 2.5.3 Blockchain for Edge-Enabled IoT Services' Efficiency -- 2.6 Challenges and Issues. , 2.6.1 Schemes Based On ML Security -- 2.6.2 Adopt ML in Blockchain Technology -- 2.7 Conclusions -- References -- Chapter 3 Computational-Based Edge AI Services and Challenges -- 3.1 Introduction -- 3.2 Background -- 3.3 Edge AI Services -- 3.3.1 Edge AI Services in Healthcare -- 3.3.2 Edge AI in Retail Industry -- 3.3.3 Role of Edge AI in Manufacturing Industry -- 3.3.4 Role of Edge AI in Transportation and Traffic Management -- 3.4 Edge Computing and AI Algorithms -- 3.4.1 Traditional Machine Learning -- 3.4.2 Deep Learning Algorithms -- 3.4.3 Reinforcement and Deep Reinforcement Learning -- 3.4.4 Evolutionary Algorithms -- 3.5 Challenges in Implementing Edge AI -- 3.6 Conclusion -- References -- Part II Computational Intelligence: Edge AI Security and Privacy -- Chapter 4 Security and Privacy in Edge AI: Challenges and Concerns -- 4.1 Introduction -- 4.1.1 IoT Service -- 4.1.2 IoT Architecture -- 4.1.2.1 Components of IoT Architecture -- 4.1.2.2 Layers of IoT Architecture -- 4.1.2.3 IoT Services -- 4.2 Edge Computing (EC) -- 4.3 EC in Consonance With IoT Devices -- 4.4 Edge AI -- 4.4.1 Definition -- 4.4.2 Traditional Intelligence Vs. Edge Intelligence -- 4.4.3 Need of Edge AI -- 4.4.4 Reasons for Deploying AI at the Edge -- 4.4.5 Pros of Edge AI -- 4.4.6 Working of Edge AI Technology -- 4.5 Edge AI Compared to Edge Computing -- 4.6 Security and Privacy Concerns for Edge AI -- 4.6.1 AI and Edge Computing Security -- 4.6.2 Integration of Edge Computing With AI -- 4.6.3 Security Risks of Edge Computing -- 4.6.3.1 Security in Edge Computing -- 4.6.3.2 Advantages of Security in Edge Computing -- 4.6.3.3 Security Strategies for Edge Computing -- 4.6.3.4 Edge Security Best Practices -- 4.6.3.5 Edge Security Vendors and Products -- 4.7 IoT Service Architecture With Edge Computing -- 4.7.1 Device Layer -- 4.7.2 Network Layer -- 4.7.3 Edge Layer. , 4.7.4 Cloud Layer -- 4.8 AI-Assisted Privacy Preservation for Edge-Enabled IoT Services -- 4.8.1 Traditional Encryption Methods -- 4.8.1.1 Anonymization -- 4.8.1.2 Cryptographic Method -- 4.8.1.3 Data Obfuscation -- 4.8.2 ENs With Lightweight AI Privacy-Preserving Methods -- 4.8.2.1 Role of CNNs in Privacy Preservation -- 4.8.2.2 Role of DNNs in Privacy Preservation -- 4.9 Edge-Enabled IoT Services By AI-Powered Blockchain -- 4.9.1 Role of Blockchain for Maintaining the Security of IoT Services -- 4.9.1.1 Access Control and Authentication Management -- 4.9.1.2 Confidentiality and Reliability of Data -- 4.9.2 Blockchain's Role in Edge-Enabled IoT Data Sharing -- 4.9.3 Enhancing Efficiency of Edge-Enabled IoT Services With Blockchain -- 4.10 Challenges and Concerns -- 4.10.1 Security Schemes Based On ML -- 4.10.1.1 High Cost of Communication and Computation -- 4.10.1.2 Security Techniques for Backup -- 4.10.2 Integration of ML and Blockchain Technology -- 4.11 Conclusion -- References -- Chapter 5 A Study of an Edge Computing-Enabled Metaverse Ecosystem -- 5.1 Introduction -- 5.1.1 Metaverse -- 5.1.2 Edge Computing -- 5.1.3 Edge Computing and Metaverse -- 5.1.3 Metaverse and Traditional Cloud-Based Platform -- 5.1.4 Edge Computing in the Metaverse -- 5.1.5 Use of Edge Computing By Prominent Leaders in Gaming Market -- 5.2 Relevance -- 5.3 Architectural Framework of an Edge Computing-Enabled -- 5.4 Edge Computing Case Studies in the Metaverse -- 5.5 Challenges for Edge Computing-Enabled Metaverse -- 5.5.1 Synchronization Challenges -- 5.5.2 Load Balancing -- 5.5.3 Network Complexities -- 5.5.4 Data Privacy and Security -- 5.5.5 Interoperability -- 5.5.6 Resource Constraints -- 5.5.7 Scalability -- 5.6 Conclusion -- References -- Chapter 6 Sustainable Communication-Efficient Edge AI: Algorithms and Systems -- 6.1 Introduction -- 6.1.1 Edge Devices. , 6.1.2 Cloud Computing -- 6.1.3 Challenges to Cloud Computing -- 6.1.4 Challenges Before Cloud Computing for Building Edge Computing -- 6.1.5 Edge Computing -- 6.1.6 Artificial Intelligence -- 6.1.7 Edge Computing With AI -- 6.1.8 Edge AI -- 6.2.1 Need of Edge AI -- 6.2.2 Advantages of Edge AI -- 6.2.3 How Does Edge AI Technology Work? -- 6.2.4 Edge AI Architecture -- 6.3 Communication-Efficient Edge AI: Algorithms and Systems -- 6.3.1 Communications-Efficient Algorithms for Edge AI -- 6.3.1.1 Federated Learning -- 6.3.1.2 Centralized Federated Learning -- 6.3.1.3 Centralized Federated Learning Design -- 6.4 Centralized Federated Learning Pseudo Code -- 6.4.1 Decentralized Federated Learning -- 6.4.2 Heterogeneous Dederated Learning -- 6.4.3 Quantization -- 6.4.4 Pruning -- 6.4.4.1 Design of Pruning -- 6.4.4.2 Pruning Techniques -- 6.4.4.5 Edge Intelligence Network -- 6.4.4.5 Edge-To-Edge Communication -- References -- Part III Computational Intelligence: Edge Computing and AI Applications -- Chapter 7 Machine Learning-Based Hybrid Technique for Securing Edge Computing -- 7.1 Introduction -- 7.2 Literature Review -- 7.2.1 Static Analysis Based On Malware Detection -- 7.2.2 Dynamic Analysis Based On Malware Detection -- 7.2.3 Hybrid Malware Analysis Techniques -- 7.3 Proposed Hybrid Malware Analysis -- 7.3.1 HybriDroid Architecture -- 7.3.2 Classifier Training for HybriDroid and CHybriDroid -- 7.4 Experimental Results -- 7.4.1 Data Set -- 7.4.2 Feature Selection -- 7.4.3 Feature Ranking -- 7.4.4 Result Discussion -- 7.4.5 Prediction Model Overhead -- 7.4.6 Analysis -- 7.5 Conclusion and Future Work -- References -- Chapter 8 A Study of Secure Deployment of Mobile Services in Edge Computing -- 8.1 Introduction -- 8.1.1 MEC Service Deployment -- 8.1.2 Computation Offloading -- 8.1.3 Data Placement -- 8.2 Basic Concepts and Definitions. , 8.2.1 Service Deployment.