Supervisor: Dr Zhijin Qin
Research group(s): Antennas and Electromagnetics
Sparse representation can efficiently model signals in different applications to facilitate processing. For example, the underutilization of spectrum makes spectral signals being sparse in frequency domain. Such type of sparse property has enabled intensive research on signal and data processing, such as dimension reduction in data science, wideband spectrum sensing, and sparse channel estimation and feedback in massive MIMO. Recently, machine learning has shown the great potentials to break the bottleneck of communication systems. This project aims to investigate the machine learning enabled sparse signal processing in wireless communication scenarios, with particular focus on signal processing in channel estimation and beamform design for millimeter wave (mmWave) systems as well as the low-cost devices in Internet of Things (IoT) networks.