Liang Liu
The Hong Kong Polytechnic University, Hong Kong SAR, China
Prof. Liang Liu is an Associate Professor at the Department of Electrical and Electronic Engineering of the Hong Kong Polytechnic University. His research interests include wireless communications and networking, advanced signal processing and optimization techniques, and Internet-of-Things (IoT). He is an IEEE ComSoc Distinguished Lecturer for the class of 2025-2026. He is the recipient of the 2021 IEEE Signal Processing Society Best Paper Award and the 2017 IEEE Signal Processing Society Young Author Best Paper Award. He is an Editor for IEEE Transactions on Wireless Communications and an Associate Editor for IEEE Transactions on Signal Processing. He is a Fellow of IEEE and Young Member of The Hong Kong Academy of Engineering.
Wireless digital twin is emerging as a critical technology for optimizing 6G networks. However, accurately constructing these twins is challenging, because it involves modelling the complex interaction between the electromagnetic (EM) signals and the environment. Traditionally, such interaction can be accurately characterized by Maxwell’s equations, which, however, are extremely difficult to be solved. In this talk, we will introduce how to exploit various learning techniques used in computer vision for predicting radio signal propagation in complex environment. First, our talk will focus on the application of the image-to-image technique for estimating radio map, which characterizes a quantity of interest in the wireless environments, such as channel pathloss, at different points of a particular geographical region. Then, we will show the utilization of the Gaussian splatting technique for predicting high-dimension channel information, e.g., the strength of signal from each path, at each receiver point. Last, we will outline the future research directions for wireless digital twin.