Answers are grounded in this paper and cite their sources.
Multiple-in-multiple-out (MIMO) systems have been commonly used in human activity sensing (HAS) to capture the characteristics in space, time, and frequency domains, but with complicated hardware architecture and high cost. Here, we propose to use reconfigurable intelligent surfaces (RISs) in a single-channel system for human activity sensing (HAS) and sensing-assisted adaptive communications. Specifically, the RISs generate random patterns to acquire echo signals of a human target, and then fully connected neural networks recognize the location and posture of the human target. Based on the recognized results, the RIS-aided system can track the human target and adaptively switch the communication content according to the posture of the human target. The RIS-aided single-channel system provides a low-cost and low-complexity scheme for HAS and sensing-assisted adaptive communications, thus showing enormous potential for applications in smart homes and smart cities.
No takes yet. Share an insight, caveat, or question.
Cao et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: