Keywords:
Distributed Machine Learning, Vehicular Networks, 6G joint Terrestrial/Non-Terrestrial Networks, Federated Learning, IoT, and IoV
David's research focuses on integrating and leveraging advanced machine learning techniques, particularly distributed learning (DL), with 6G wireless and vehicular networks (VNs). His work emphasizes practical and scalable solutions for the next generation of communication technologies and the integration of terrestrial and non-terrestrial networks (T/NTNs). He explores the enhancement of network efficiency through federated learning (FL), transfer learning (TL), and split learning (SL), the deployment of federated learning on IoT devices, and the development of intelligent VNs supported by space-based infrastructures. Additionally, he investigates network slicing for DL in Internet of Vehicles (IoV) applications, the implementation of DL frameworks for IoT, and the innovative use of computation offloading to low Earth orbit (LEO) satellites. Overall, his research aims to advance the performance and capabilities of the future vehicular networks through distributed and intelligent learning approaches.
