Kezhi Wang

TL;DR: In this article, an uplink reconfigurable intelligent surface (RIS)-aided massive multiple-input multiple-output (MIMO) system with statistical channel state information (CSI) is considered.

TL;DR: The proposed deep neural network has fully connected layers and can predict the optimal IRS reflection vector and the optimal number of IRS reflection elements with low complexity and achieves higher secure energy efficiency than the conventional methods.

TL;DR: A channel-weighted aggregation scheme of FL (CWA-FL), in which the parameter server (PS) makes aggregation of the gradients according to the channel conditions of devices, which can avoid the synchronization issue among devices faced by over-the-air FL.

TL;DR: In this paper, the authors aim to answer four fundmental questions: 1) Why do we need RISs? 2) What is an RIS? 3] What are RIS's applications? 4) What are the relevant challenges and future research directions?

TL;DR: In this paper , the authors proposed a deep reinforcement learning (DRL)-based solution, i.e., soft actor-critic (SAC) to address the problem via modeling the problem as a Markov decision process (MDP), which carefully designed the reward function that combines sparse with non-sparse reward to achieve the balance between exploitation and exploration.