PhD in Electrical And Electronic Engineering

Radio frequency (RF)-based contactless sensing has gained considerable momentum in recent years, driven by the widespread deployment of IoT infrastructures and rapid advancements in wireless communication technologies. Unlike traditional sensing methods that rely on wearable or on-body sensors, RF-based sensing passively captures signal distortions caused by human presence or activity and leverages machine learning or deep learning algorithms to perform various sensing tasks. This approach is particularly advantageous in low-light or visually obscured environments, offering practical convenience and enhanced privacy protection. This PhD project aims to develop healthcare monitoring solutions that utilize ubiquitous Wi-Fi signals to detect and track respiration under dynamic environmental conditions. The project will integrate advanced artificial intelligence (AI) and signal processing techniques to enable reliable, real-time, and contactless health monitoring. A major challenge in this domain is the inherent heterogeneity of wireless data. The collected signals often exhibit diverse statistical characteristics due to factors such as multipath propagation, hardware imperfections, and interference from nearby individuals. These variations can lead to inconsistent patterns and performance degradation. By tackling this problem, the project seeks to push the boundaries of RF-based sensing—expanding its sensing range, improving accuracy, and enhancing robustness and generalization—thereby contributing to the development of next-generation contactless healthcare monitoring systems.