Edge Artificial Intelligence : Foundations, Techniques, and Applications

• Autore: Agarwal Preeti
• Pubblicazione: Newark : , : John Wiley & Sons, Incorporated, , 2026; ©2025
• Edizione: 1st ed.
• Descrizione fisica: 1 online resource (647 pages)
• Disciplina: 006.3
• Soggetto topico: Artificial intelligence
• Altri autori: BijalwanAnchit
• Nota di contenuto: Cover -- Series Page -- Title Page -- Copyright Page -- Contents -- Preface -- Part 1: Foundations and Core Concepts of Edge AI -- Chapter 1 Edge AI Demystified: From Its Origins to Future Frontiers -- 1.1 Introduction -- 1.1.1 Edge AI Evolution -- 1.1.2 What is Edge AI, and How Does It Work? -- 1.1.3 Difference Between Edge AI and Cloud AI -- 1.2 Edge AI Ecosystem -- 1.2.1 Hardware Architecture -- 1.2.2 Operating Systems -- 1.2.3 Communication Protocols -- 1.2.4 Computational Paradigms -- 1.2.5 Mechanisms for Security and Data Protection -- 1.2.6 Applications -- 1.3 Benefits of Edge AI -- 1.3.1 Lower Latency and Real-Time Processing -- 1.3.2 Better Privacy and Security of Data -- 1.3.3 Scalability and Resource Efficiency -- 1.3.4 Energy Efficiency -- 1.3.5 Increased Reliability -- 1.3.6 Context-Aware Intelligence -- 1.3.7 Optimization of Bandwidth -- 1.3.8 Versatility Across Industries -- 1.3.9 Democratizing AI -- 1.3.10 Environmental Benefits -- 1.4 Different Deployment Architectures -- 1.4.1 Architecture Types -- 1.5 Hardware and Software Requirements for Edge AI -- 1.5.1 Hardware Requirements for Edge AI -- 1.5.2 Edge AI Software Requirements -- 1.6 Applications of Edge AI -- 1.7 Challenges in Edge AI -- 1.8 Open Research Issues -- 1.9 Future Research Directions for Edge-Driven IoT -- 1.10 Conclusion -- References -- Chapter 2 Optimizing Deep Learning Models for Edge Devices -- 2.1 Introduction -- 2.2 Background Review -- 2.3 Techniques, Algorithms and Frameworks -- 2.3.1 Quantization -- 2.3.2 Pruning -- 2.3.3 Model Optimization for Edge Devices -- 2.3.4 Knowledge Distillation -- 2.3.5 Layer Partitioning -- 2.3.6 DNN Partitioning and Right Sizing -- 2.3.7 Hashing -- 2.3.8 Hybrid Compression Techniques -- 2.3.9 SVD (Singular Value Decomposition) -- 2.3.10 CPU Optimization -- 2.4 Deploying Technology -- 2.5 Experimental Evaluation. ; 2.6 Case Study -- 2.6.1 Smart Cities -- 2.6.2 Health Care and Remote Monitoring -- 2.6.3 Autonomous Driving -- 2.7 Challenges and Future Direction -- 2.8 Conclusion -- References -- Chapter 3 Role of Multi Objective Evolutionary Algorithms in Edge AI System Optimization -- 3.1 Introduction -- 3.2 Multi Objective Optimization in Edge AI -- 3.3 Challenges and Limitations -- 3.4 Future Directions -- 3.5 Conclusion -- References -- Chapter 4 The Convergence of Edge Computing, AI, and Blockchain: Challenges, Opportunities, and Future Prospects -- 4.1 Introduction -- 4.2 Understanding Edge Computing -- 4.3 Understanding Edge AI -- 4.4 Understanding Blockchain Technology -- 4.4.1 Key Features of Blockchain -- 4.4.2 Consensus Mechanisms -- 4.4.3 Blockchain Applications -- 4.4.4 Challenges of Blockchain -- 4.4.5 Future of Blockchain -- 4.5 Convergence of Edge AI and Blockchain -- 4.5.1 Data Privacy and Security -- 4.5.2 Decentralized Intelligence -- 4.5.3 Efficiency and Scalability -- 4.5.4 Transparency -- 4.6 Challenges in Convergence -- 4.7 Applications (IoT, Edge AI, and Blockchain for Sustainable Cities) -- 4.8 Future Prospects -- 4.9 Conclusion -- References -- Chapter 5 Network Optimization in Edge Computing -- 5.1 Introduction -- 5.2 Overview - What is Network Optimization? -- 5.3 Role of Edge Computing in Network Optimization/ Network Fundamentals -- 5.3.1 Reduced Latency -- 5.3.2 Bandwidth Optimization -- 5.3.3 Scalability -- 5.3.4 Enhanced Security and Privacy -- 5.3.5 Cost Efficiency -- 5.4 Challenges -- 5.4.1 Programmability -- 5.4.2 Data Abstraction -- 5.4.3 Service Management -- 5.4.4 Privacy & -- Security -- 5.4.5 Application Distribution -- 5.5 Strategies for Network Optimization -- 5.5.1 Edge Caching -- 5.5.2 Data Locality -- 5.5.3 Advanced Routing Techniques -- 5.6 Software-Defined Networking: Principles and Edge Environment Applications. ; 5.6.1 Principles of SDN -- 5.6.2 SDN in Edge Environments -- 5.7 Network Function Virtualization (NFV) -- 5.7.1 Concepts and Applications in Edge Networks -- 5.7.2 Foundation and Core Principles of NFV -- 5.7.3 Components of NFV Architecture -- 5.7.4 Benefits of NFV -- 5.7.5 Satisfying Network Service Requirements on the Edge in Nearly Real-Time -- 5.7.6 Edge Oriented Network Protocols -- 5.7.7 Enhancements in Edge-Oriented Network Protocols -- 5.8 Application of Edge Computing in Network Optimization: A Comprehensive Overview -- 5.9 Case Study: Edge Computing in Network Optimization for Autonomous Vehicles -- 5.9.1 Edge Computing Deployment Architecture -- 5.9.2 Key Benefits and Outcomes -- 5.9.3 Challenges Encountered -- 5.10 Future Trends in Edge Computing for Network Optimization -- 5.10.1 Integration with 5G Networks -- 5.10.2 Artificial Intelligence at the Edge (Edge AI) -- 5.10.3 Federated Learning and Distributed Computing -- 5.10.4 Edge-to-Cloud Orchestration -- 5.10.5 The Assembled Zone of the Edge with IoT for Smart Cities -- 5.10.6 Energy Efficiency and Sustainability in Edge Computing -- 5.10.7 Security and Privacy on the Edge -- 5.10.8 Network Slicing and Customization with Edge Computing -- 5.11 Conclusion -- References -- Chapter 6 Comparative Analysis of Pruning Conventional Machine Learning or Deep Learning Frameworks Utilizing Discrete Wavelet Transform for Iris Biometrics -- 6.1 Introduction -- 6.2 Literature Review -- 6.3 Background Theories -- 6.3.1 Biometrics and Iris Recognition -- 6.3.2 Deep Learning in Biometrics -- 6.3.3 Discrete Wavelet Transform (DWT) -- 6.3.4 Principal Component Analysis (PCA) -- 6.3.5 Support Vector Machines (SVM) -- 6.4 Methodology -- 6.4.1 Datasets -- 6.4.1.1 IIT Delhi Iris Dataset (IITD) -- 6.4.1.2 MMU Iris Dataset -- 6.4.2 Preprocessing -- 6.4.3 Feature Extraction: CNN and ResNet. ; 6.4.4 Classification -- 6.4.5 Model Evaluation -- 6.4.6 Implementation Details -- 6.5 Results -- 6.5.1 Performance Comparison -- 6.5.2 Classification Report Analysis -- 6.5.3 Confusion Matrix -- 6.5.4 ROC Curve -- 6.6 Problems Faced -- 6.7 Conclusion -- 6.8 Future Scope -- Bibliography -- Chapter 7 Convergence of K8s and Istio Deployment on Mission- Critical Environments -- 7.1 Introduction -- 7.2 Related Work -- 7.3 Requirement Analysis and Proposed HYINKUBIS Architecture Design -- 7.4 Experimental Evaluations -- 7.5 Conclusion -- References -- Part 2: Security, Ethics, and Trust in Edge AI -- Chapter 8 Edge AI Security and Privacy: Threats, Solutions, and Best Practices -- 8.1 Introduction -- 8.1.1 Importance of Security and Privacy in Edge AI -- 8.1.2 Overview of Security and Privacy Issue in Edge AI -- 8.1.3 Types of Security Concerns in Edge Devices -- 8.2 Threats Landscape -- 8.2.1 Physical Tampering -- 8.2.2 Malware and Remote Attack -- 8.2.3 Adversial Attack -- 8.3 Vulnerabilities in Edge Devices -- 8.3.1 Device Level Vulnerabilities -- 8.3.2 Software Level Vulnerabilities -- 8.3.3 Network Level Vulnerabilities -- 8.4 Regulatory and Compliance Issues -- 8.4.1 Overview of Relevant Regulations -- 8.4.2 Compliance Challenges for Edge Devices -- 8.4.3 Best Practices for Compliance -- 8.5 Best Practices for Securing Edge Devices -- 8.5.1 Regular Monitoring and Threat Detection -- 8.5.2 Secure Firmware and Software Updates -- 8.5.2.1 Organizational Protection Schemes -- 8.5.2.2 OTA Updates with Security Layers -- 8.5.3 Role of Cryptographic Methods -- 8.5.4 Minimal Data Exposure: Cleaning and Masking -- 8.5.5 Trusted Hardware: TPMs and Secure Enclaves -- 8.5.6 THASSA -- 8.6 Emerging Trends and Technologies in Edge AI Security -- 8.6.1 Emerging Technologies -- 8.6.2 Anticipated Security Challenges -- 8.6.3 Recommendation for Enhancing Security. ; 8.7 Conclusion -- References -- Chapter 9 Edge AI in Cybersecurity -- 9.1 Introduction to Edge AI in Cybersecurity -- 9.1.1 The Evolution of Cybersecurity Needs -- 9.1.2 Fundamentals of Edge AI -- 9.1.3 Key Components of Edge AI -- 9.1.3.1 Key Features of Hardware Accelerators -- 9.1.3.2 Types of Hardware Accelerators -- 9.1.4 Role of Edge AI in Cybersecurity -- 9.1.5 Cybersecurity Challenges in a Connected World -- 9.1.6 Applications of Edge AI in Cybersecurity -- 9.1.7 Future Directions -- 9.2 Conclusion -- References -- Chapter 10 Database-Guard Artificial Intelligence: Revolutionizing Database Security with Artificial Intelligence -- 10.1 Introduction -- 10.1.1 Problem Statement -- 10.1.2 Objectives -- 10.1.3 Significance of the Study -- 10.2 Background and Literature Review -- 10.2.1 Evolution of Database Security -- 10.2.2 Traditional Database Security Mechanisms and their Limitations -- 10.2.3 Emerging Threats to Database Security -- 10.2.4 AI in Database Security: A Paradigm Shift -- 10.3 DB-GuardIA Architecture and Components -- 10.3.1 Adaptive Threat Detection Layer (ATDL) -- 10.3.1.1 Overview of ATDL -- 10.3.1.2 Key Features of ATDL -- 10.3.1.3 Workflow of ATDL -- 10.3.2 Graph Neural Network-Based Anomaly Detection (GNN-AD) -- 10.3.2.1 Overview of GNN-AD -- 10.3.2.2 Key Features of GNN-AD -- 10.3.2.3 Workflow of GNN-AD -- 10.3.3 AI-Driven Dynamic Encryption Layer (AIDEL) -- 10.3.3.1 Overview of AIDEL -- 10.3.3.2 Key Features of AIDEL -- 10.3.3.3 Workflow of AIDEL -- 10.3.4 Self-Healing Database Layer (SHDL) -- 10.3.4.1 Overview of SHDL -- 10.3.4.2 Key Features of SHDL -- 10.3.4.3 Workflow of SHDL -- 10.3.5 Insider Threat Management Module (ITMM) -- 10.3.5.1 Overview of ITMM -- 10.3.5.2 Key Features of ITMM -- 10.3.5.3 Workflow of ITMM -- 10.3.6 Explainable AI (XAI) Module -- 10.3.6.1 Overview of XAI Module. ; 10.3.6.2 Key Features of XAI Module.
• Sommario/riassunto: Secure your expertise in the next wave of computing with this essential book, which provides a comprehensive guide to Edge AI, detailing its foundational concepts, deployment strategies, and real-world applications for revolutionizing performance and privacy across various industries.
• Titolo autorizzato: Edge Artificial Intelligence
• ISBN: 1-394-35503-3; 1-394-35502-5
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9911040927103321
• Lo trovi qui: Univ. Federico II