Learned Intelligent Recognizer with Adaptively Customized RIS Phases in Communication Systems

TL;DR

This paper introduces an intelligent deep learning-based system that adaptively customizes RIS phases for target recognition in wireless communication, enhancing recognition accuracy while maintaining communication performance.

Contribution

It proposes a novel LSTM-based neural network that iteratively fuses past responses to adaptively optimize RIS configurations for environment sensing and recognition.

Findings

Significantly outperforms existing methods in recognition accuracy

Maintains communication performance during sensing tasks

Effectively adapts to scene, task, and target specifics

Abstract

This study presents an advanced wireless system that embeds target recognition within reconfigurable intelligent surface (RIS)-aided communication systems, powered by cuttingedge deep learning innovations. Such a system faces the challenge of fine-tuning both the RIS phase shifts and neural network (NN) parameters, since they intricately interdepend on each other to accomplish the recognition task. To address these challenges, we propose an intelligent recognizer that strategically harnesses every piece of prior action responses, thereby ingeniously multiplexing downlink signals to facilitate environment sensing. Specifically, we design a novel NN based on the long short-term memory (LSTM) architecture and the physical channel model. The NN iteratively captures and fuses information from previous measurements and adaptively customizes RIS configurations to acquire the most relevant information for the recognition task in subsequent moments. Tailored dynamically, these configurations adapt to the scene, task, and target specifics. Simulation results reveal that our proposed method significantly outperforms the state-of-the-art method, while resulting in minimal impacts on communication performance, even as sensing is performed simultaneously.