TY  - BOOK
AU  - Benedict,Shajulin
ED  - Institute of Physics (Great Britain),
TI  - Edge intelligence: deep learning-enabled edge computing 
T2  - [IOP release $release]
SN  - 9780750355933
AV  - QA76.583 .B464 2024eb
PY  - 2024///]
CY  - Bristol [England] (Temple Circus, Temple Way, Bristol BS1 6HG, UK)
PB  - IOP Publishing
KW  - Edge computing
KW  - Artificial intelligence
KW  - bicssc
KW  - COMPUTERS / Artificial Intelligence / General
KW  - bisacsh
N1  - "Version: 20240601"--Title page verso; Includes bibliographical references; part I. Introduction. 1. Edge intelligence -- 1.1. Edge computing -- 1.2. History of edge computing -- 1.3. Edge intelligence -- 1.4. Advantages : edge intelligence -- 1.5. Challenges : edge intelligence -- 1.6. Applications -- 1.7. The need for this book -- 1.8. Potential readers -- 1.9. Organization of the book; 2. Edge computing architectures -- 2.1. Internet of Things -- 2.2. IoT-enabled components -- 2.3. Learning techniques : machine learning -- 2.4. Learning techniques : deep learning -- 2.5. Edge-AI architectures -- 2.6. Conclusion; 3. Edge OS and programming models -- 3.1. Operating systems -- 3.2. Objectives of OS in edge devices (Edge OS) -- 3.3. Taxonomy of OS : toward edge -- 3.4. Edge OS : examples -- 3.5. Process states in edge-OS -- 3.6. FreeRTOS : OS for embedded devices -- 3.7. Conclusion; part II. Learning techniques. 4. Edge intelligence : learning techniques -- 4.1. Edge intelligence : a need -- 4.2. Federated learning -- 4.3. DNN splitting -- 4.4. Transfer learning -- 4.5. Gossip learning -- 4.6. Conclusion; 5. Inference/prediction techniques -- 5.1. Learning stages -- 5.2. Inference knowledge levels -- 5.3. Distributed inferences -- 5.4. Distributed inferences : implementation strategies -- 5.5. Interactive versus batched inferences -- 5.6. Partitioning distributed inferences -- 5.7. Accelerating distributed inferences : strategies -- 5.8. Conclusion; 6. Edge resources and accelerators -- 6.1. Edge resources : basics -- 6.2. Micro-controller-level devices : an edge? -- 6.3. Micro-processor-level devices : general purpose -- 6.4. GPUs, TPUs, and FPGAs : special purpose -- 6.5. SoC, SoM, system-on-board -- 6.6. Edge accelerators -- 6.7. Commercial edge accelerators -- 6.8. Examples and use-cases -- 6.9. Conclusion; 7. Performance analysis of edge-enabled applications -- 7.1. Performance concerns -- 7.2. Model-specific performance concerns -- 7.3. Architecture-specific performance concerns -- 7.4. Algorithm-specific performance concerns -- 7.5. Data-specific performance concerns -- 7.6. Performance monitoring : a need -- 7.7. Performance monitoring : metrics -- 7.8. Energy-efficiency methods -- 7.9. Carbon efficiency methods -- 7.10. Workload scheduling and performance impacts -- 7.11. Performance monitoring tools -- 7.12. Cloud/fog/edge-level performance monitoring -- 7.13. Conclusion; 8. Security in edge-AI systems -- 8.1. Existing security challenges -- 8.2. Security attacks in edge-AI -- 8.3. Data-specific vulnerabilities -- 8.4. Security architectures in edge-AI -- 8.5. Preventing security breaches : strategies -- 8.6. Tools and solutions -- 8.7. Conclusion; part III. Tools and solutions. 9. Frameworks : edge-AI platforms -- 9.1. Essential characteristics -- 9.2. Types of framework -- 9.3. Resource-allocation frameworks -- 9.4. Cloud-specific frameworks -- 9.5. Application-specific frameworks -- 9.6. Distributed federated learning frameworks -- 9.7. Conclusion; 10. Orchestration platforms : computing continuum -- 10.1. Orchestration and integration -- 10.2. Algorithmic/application orchestration -- 10.3. Workload orchestration -- 10.4. Hierarchical versus non-hierarchical orchestration -- 10.5. Adaptiveness in orchestration -- 10.6. Automation in orchestration -- 10.7. Metric-oriented orchestration -- 10.8. Orchestration frameworks -- 10.9. Integration platforms; part IV. Applications. 11. Edge-AI applications -- 11.1. Applications -- 11.2. Edge-AI for healthcare -- 11.3. Industrial applications using edge-AI -- 11.4. Edge-AI for agriculture -- 11.5. Edge-AI for forensics -- 11.6. Edge-AI for mobility/logistics -- 11.7. Conclusion; 12. Business opportunities using edge-AI -- 12.1. Digital business -- 12.2. Economic impacting factors -- 12.3. Business opportunities : edge-AI platforms -- 12.4. Cost models -- 12.5. Economic simulators for FaaS implementation -- 12.6. Conclusion; 13. Challenges and future directions -- 13.1. Edge-AI challenges; Full-text restricted to subscribers or individual document purchasers; Academic and commercial researchers; Also available in print
N2  - Edge Intelligence: deep learning-enabled edge computing is a book that targets researchers and practitioners who are interested in applying intelligence without compromising data privacy. The book reveals the existing edge-AI techniques and forecasts future edge-AI integration methods. The book delves into edge computing architectures after describing relevant basic technologies such as IoT, cloud computing, and other security-related architectures. The book starts with an explanation of all relevant basic technologies. It offers a smooth transition from the basics to insightful practical sessions for practitioners. The ideas of providing innovative ideas and applications in the later part of the book can enthuse researchers and developers to engage themselves in innovating newer products with the application of edge intelligence. Part of IOP Series in Next Generation Computing
UR  - https://iopscience.iop.org/book/mono/978-0-7503-5593-3
ER  -