Data-centric AI

Integrated Computation and Communications for Extended Reality

AvConghao Zhou,Jie Gao

Inbunden, Engelska, 2026

Del i serien Wireless Networks

1 461 kr

Kommande

Beskrivning

This book explores how integrated computation and communication can be achieved to support scalable and user-centric Extended Reality (XR) service provisions. Leveraging the digital twin technique as a key enabler, this book aims to introduce a novel data-centric AI framework to support XR from the perspective of communication and networking. Specifically, the authors present architectural designs and algorithmic solutions of data-centric AI that support the cross-layer and intelligent collection, processing, and analysis of XR user data, thereby enabling user-centric service provision. The book presents a digital twin-based framework that encompasses conceptual architecture, workflow, and operation functions to support diverse XR modules involving both communication and computation. In addition, the book explores the role of data-centric AI in XR resource provisioning, with a particular focus on how data-centric AI enhances both the quality and quantity of data available for AI model training and decision-making. Various learning paradigms, including supervised learning and reinforcement learning, are examined to demonstrate how AI enhances the efficiency and adaptability of resource management

Produktinformation

Utgivningsdatum:2026-10-14
Mått:155 x 235 x undefined mm
Format:Inbunden
Språk:Engelska
Serie:Wireless Networks
Antal sidor:188
Förlag:Springer Nature Switzerland AG
ISBN:9783032274861

Utforska kategorier

Mer om författaren

Dr. Conghao Zhou is currently a full professor at the School of Telecommunications Engineering, Xidian University, China. He received his Ph.D. degree in Electrical and Computer Engineering from the University of Waterloo ON, Canada. His research interests include AI for networking, immersive communications, and space-air-ground integrated networks. Dr. Zhou received the IEEE GLOBECOM'24 Best Paper Award and the IEEE WCSP'25 Best Paper Award. He served as a guest editor for IEEE Journal on Miniaturization for Air and Space Systems and MDPI Remote Sensing, and TPC members of many conferences, including IEEE ICC, ICCC, and VTC.Dr. Jie Gao is currently an Assistant Professor in the School of Information Technology at Carleton University. His research focuses on machine learning for communications and networking, digital twins, and other emerging technologies for 6G. Dr. Gao is the recipient of the IEEE VTS OJVT Best Paper Award 2025 and the IEEE Best Land Transportation Paper Award (2024). He has served as a Publicity Co-Chair for IEEE VTC2025-Fall and IEEE MetaCom 2023, a Publication Co-Chair for ACM/IEEE IoTDI 2022, and as a co-chair for multiple tracks, symposia, and workshops at international conferences since 2021.Dr. Xuemin (Sherman) Shen received the Ph.D. degree in electrical engineering from Rutgers University, New Brunswick, NJ, USA, in 1990. He is a University Professor with the Department of Electrical and Computer Engineering, University of Waterloo, Canada. His research focuses on network resource management, wireless network security, Internet of Things, AI for networks, and vehicular networks. Dr. Shen is a registered Professional Engineer of Ontario, Canada, an Engineering Institute of Canada Fellow, a Canadian Academy of Engineering Fellow, a Royal Society of Canada Fellow, a Chinese Academy of Engineering Foreign Member, and an International Fellow of Engineering Academy of Japan. He is also a Distinguished Lecturer of the IEEE Vehicular Technology Society and Communications Society.

Innehållsförteckning

Introduction.- Reshaping Reality.- Challenges for Networks.- Digital Twin for Data-centric AI.- Communication Service Provision for Device Pose Tracking in XR.- Communication-adaptive Physical Environment Mapping in XR.- Data-centric Reinforcement Learning-based Approach.- Multi-tier Computing for Virtual Content Delivery in XR.- Virtual Content Delivery in XR.- Network Planning.- Data-centric Meta Learning-based Approach.- Future Directions.- Conclusion.