Submission Deadline: 31 October 2025 View: 70 Submit to Special Issue
Prof. Dongkyun Kim
Email: dongkyun@knu.ac.kr
Affiliation: School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, Republic of Korea.
Research Interests: Internet of Vehicles (IoVs), Edge Computing, V2X, Connected Cars
Prof. Sobia Jangsher
Email: sobia.jangsher@dcu.ie
Affiliation: School of Electronic Engineering ,Dublin City University, Dublin,D09 V209,Ireland
Research Interests: AI/ML for Wireless Networks, Resource Allocation, Moving Networks, Small Cell Networks, Edge Computing, Federated Learning
Dr. Syed Hassan Ahmed
Email: sh.ahmed@ieee.org
Affiliation: Department of Computer Science ,California State University, Fullerton Campus, California, 92831, USA
Research Interests: Wireless Networks, Internet of Vehicles (IoVs), Edge Computing, Artificial Intelligence, Vehicular communications
The Internet of Vehicles (IoV) ecosystem comprises vehicles, infrastructure, and vulnerable road users (VRUs), including pedestrians and cyclists, all interconnected to enhance transportation safety and efficiency. In the era of 6G, the rising demand for advanced applications—such as high-definition (HD) streaming, infotainment services, and sensor fusion for autonomous driving—introduces significant challenges due to resource constraints.
VRUs primarily rely on mobile devices that are resource-limited and have battery constraints, presenting challenges for deploying advanced machine learning models directly on these devices. These challenges compromise the safety of road users. Integrating Split Learning with Tiny Machine Learning (TinyML) models offers a resilient solution by enabling efficient, privacy-preserving data processing on edge devices within the 6G-enabled IoV ecosystem.
Split Learning partitions a neural network between client devices and central servers, ensuring that raw data remains on local devices while only intermediate representations are shared. This approach preserves data privacy and reduces the computational load on resource-limited devices. Combined with TinyML, which focuses on deploying lightweight models suitable for computationally limited devices. This facilitates real-time data processing and decision-making for VRU safety applications.
This special issue aims to explore the integration of Split Learning and TinyML within edge computing frameworks to support IoV applications, with a particular focus on enhancing the safety and experience of VRUs. We invite original research and review articles that address various aspects of this integration, including but not limited to:
· Split Learning Architectures for IoVs
· TinyML Applications in VRU Safety Systems
· Implementing Split Learning in VRU Wearable Technology
· Collaborative Learning Approaches in IoV
· Real-Time Data Processing in IoV
· Adaptive Resource Allocation Strategies for Split Learning in IoV
· Privacy-Preserving Mechanisms in Split Learning
· Integration of Split Learning with Federated Learning
· Resource-Constrained Model Deployment for VRU Safety Systems
· Secure Data Transmission in VRU Edge Devices
· Dynamic Resource Allocation in Split Learning for IoVs
Login
Register
Submit a Paper
Propose a Special lssue