Edge Computational Intelligence for AI-Enabled IoT Systems

Edge computational intelligence is an interface between edge computing and artificial intelligence (AI) technologies. This interfacing represents a paradigm shift in the world of work by enabling a broad application areas and customer-friendly solutions. Edge computational intelligence technologies are just in their infancy. Edge Computational Intelligence for AI-Enabled IoT Systems looks at the trends and advances in edge computing and edge AI, the services rendered by them, related security and privacy issues, training algorithms, architectures, and sustainable AI-enabled IoT systems. Together, these technologies benefit from ultra-low latency, faster response times, lower bandwidth costs and resilience from network failure, and the book explains the advantages of systems and applications using intelligent IoT devices that are at the edge of a network and close to users. It explains how to make most of edge and cloud computing as complementary technologies or used in isolation for extensive and widespread applications. The advancement in IoT devices, networking facilities, parallel computation and 5G, and robust infrastructure for generalized machine learning have made it possible to employ edge computational intelligence in diverse areas and in diverse ways. The book begins with chapters that cover Edge AI services on offer as compared to conventional systems. These are followed by chapters that discuss security and privacy issues encountered during the implementation and execution of edge AI and computing services The book concludes with chapters looking at applications spread across different areas of edge AI and edge computing and also at the role of computational intelligence in AI-driven IoT systems.

Shrikaant Kulkarni has 37 years of teaching and research experience at both undergraduate and postgraduate levels. Presently he is a Professor in the Department of Civil Engineering, Padm. Dr. V. B. Kolte College of Engineering, Malkapur, India. He has published over 60 research papers in national and international journals and conferences Jaiprakash Narain Dwivedi is currently working as an Associate Professor, ECE Department, University Institute of Engineering, Chandigarh University, Mohali, Punjab, India. His interest in research includes machine learning, artificial neural network, pattern recognition, classification, CNN, DNN, deep learning and signal processing. Dinda Pramanta is an Assistant Professor and a committee member of Mathematical-Data Science-AI Educational Program on Kyushu Institute of Information Sciences from 2021. His research interests include spiking neural networks, hardware, and AI for educational purposes. Yuichiro Tanaka is an Assistant Professor with Research Center for Neuromorphic AI Hardware, Kyushu Institute of Technology, Japan. His research interests include soft computing, neural networks, hardware, and home service robots. He is a member of IEEE and JNNS.

I. Computational Intelligence: Edge AI Services 1. Edge Computational Intelligence: Fundamentals, Trends, and Applications 2. Securing IoT Services Using Artificial Intelligence in Edge Computing 3. Computational-Based Edge AI Services and Challenges II. Computational Intelligence: Edge AI security and Privacy 4. Security and Privacy in Edge AI: Challenges and Concerns 5. A Study of Edge Computing-Enabled Metaverse Ecosystem 6. Sustainable Communication-Efficient Edge AI: Algorithms and Systems III. Computational Intelligence: Edge Computing and AI Applications 7. Machine Learning-Based Hybrid Technique for Securing Edge Computing 8. A Study of Secure Deployment of Mobile Services in Edge Computing 9. AI-Enabled Novel Applications in Edge Computing for IoT Services 10. Application of Edge AI in Biomedicine IV. Computational Intelligence: IoT Systems 11. Artificial Intelligence and Soft Computing-Driven Evolutionary Computation Algorithms for Solving Unconstrained Nonlinear Problems 12. UAV-Enabled Mobile Edge Computing for IoT Applications 13. Internet of Things Enabled Software-Defined Networks 14. Smart and Sustainable Energy-Efficient Wireless Sensor Network: Design and Techniques