Fog-enabled intelligent IoT systems / Yang Yang, Xiliang Luo, Xiaoli Chu, Ming-Tuo Zhou.

Unlimited

Authorized users

Can lend chapters, not whole ebooks

Fog-enabled intelligent IoT systems / Yang Yang, Xiliang Luo, Xiaoli Chu, Ming-Tuo Zhou.

9783030231859 (electronic book)
3030231852 (electronic book)
9783030231842

https://doi.org/10.1007/978-3-030-23185-9
https://doi.org/10.1007/978-3-030-23

Cham : Springer, [2020]

©2020

English

1 online resource : illustrations

10.1007/978-3-030-23185-9 doi
10.1007/978-3-030-23

QA76.585 .Y36 2020eb

004.67/82

This book first provides a comprehensive review of state-of-the-art IoT technologies and applications in different industrial sectors and public services. The authors give in-depth analyses of fog computing architecture and key technologies that fulfill the challenging requirements of enabling computing services anywhere along the cloud-to-thing continuum. Further, in order to make IoT systems more intelligent and more efficient, two fog-enabled frameworks with detailed technical approaches are proposed for realistic application scenarios with no or limited priori domain knowledge, i.e. physical laws, system statuses, operation principles and execution rules. Based on these fog-enabled frameworks, a series of data-driven self-learning applications in different industrial sectors and public services are investigated and discussed, such as Intelligent Transportation System, Smart Home, Industrial 4.0, Wireless Network Self-Optimization, and User Behavior Recognition. Finally, the advantages and future directions of fog-enabled intelligent IoT systems are summarized in terms of service flexibility, scalability, quality, maintainability, cost efficiency, as well as latency. Provides a comprehensive review of state-of-the-art IoT technologies and applications in different industrial sectors and public services Presents a fog-enabled service architecture with detailed technical approaches for realistic cross-domain application scenarios with limited prior domain knowledge Outlines a series of data-driven self-learning applications (with new algorithms) in different industrial sectors and public services.

Includes bibliographical references and index.

Access limited to authorized users.

Online resource; title from PDF title page (SpringerLink, viewed October 22, 2019).

Online Resources > Ebooks
All Resources