Special Issue "Federated Learning for Internet of Vehicles Challenges, Concepts and Applications"

Submission Deadline: 01 July 2022 (closed)
Submit to Special Issue
Guest Editors
Dr. Gaurav Dhiman, Government Bikram College of Commerce, India.
Prof. Atulya Nagar, Liverpool Hope University, United Kingdom.
Prof. Seifedine Kadry, Noroff University College, Norway.

Summary

Federated learning opens up a brand new research field in Internet of Vehicles (IoV). Federated learning for Internet of Vehicles (FL-IoV) is the emergence of the Internet of Vehicles (IoV) aims to enhance the users’ quality of experience through proposing more sophisticated services ranging from guaranteeing the user safety to improving his comfort. The main focus of this special issue is to bring all the related managerial applications of Federated learning for Internet of Vehicles in a single platform with entities participate to compose its architecture such as vehicles, humans, roadside units, Intelligent Transport Systems (ITS). Moreover, different communication types co-exist to ensure the IoV connectivity and continuity. This diversity leads to new security requirements that seem more complex to take into account and enlarge the attack surface of such ecosystem.

 

Federated learning for Internet of Vehicles can sufficiently utilize the computing capabilities of multiple learning agents to improve the learning efficiency while providing a better privacy solution for the data owners. FL attracts tremendous interests from a large number of industries due to growing privacy concerns. Future Federated learning for Internet of Vehicles systems, such as cooperative autonomous driving and intelligent transport systems (ITS), feature a large number of devices and privacy-sensitive data where the communication, computing, and storage resources must be efficiently utilized.

 

Reinforcement learning has recently been studied in various fields and also used to optimally control IoV devices supporting the expansion of Internet connection beyond the usual standard devices. In this issue, we try to allow multiple reinforcement learning agents to explain the necessity of federated learning for IoV applications. For such multiple IoV devices, there is no guarantee that an agent who interacts only with one IoV device and learns the federated learning for IoV applications policy will also control another IoV device well.

 

This issue will be of particular interest for computer scientists and practitioners who are specialized in convergence of BDA with AI, ML and DL techniques to analysed data.

This issue will provide cost-efficient resource allocation solutions that are robust against common uncertainties and privacy concerns related to security in centralized and distributed computing systems.

 

Additionally, this issue presents a deep understanding of federated learning concepts and IoT devices and applications for which the federated learning is used. It begins by providing a comprehensive survey of state-of-the-art research on federated learning, giving the reader a general overview of the field. This book also investigates how a personalized federated learning framework is needed in cloud-edge architecture as well as in wireless-edge architecture for intelligent IoT applications.


Keywords
The scope of this research extends from latest trends in Federated learning from a pragmatic business perspective and its contingent combinational implementations with digital and Internet of Vehicles, which is elaborated as follows:
1. Comprehending capabilities of Internet of Vehicles
2. Developments in Internet of Vehicles based organizations
3. Elaborating multiple facets cognitive IoV and digital twins
4. A review of various Internet of Vehicles and digital twin ventures by research giants
5. Applications of cognitive and digital in business enabled by Internet of Vehicles(IoV)
6. Enabling prominent Internet of Vehicles based applications
7. Understanding intuitive abilities of Internet of Vehicles
8. Major frameworks and techniques implemented for Internet of Vehicles
9. Elaborating challenges of Real time Internet of Vehicles applications
10. Computation limitation of Internet of Vehicles implementations
11. Future of digital-cognitive enabled Internet of Vehicles