Zero-Power Integrated Sensing and Communication in Smart Healthcare Environments

In this paper, we propose a unified framework for integrated sensing and communication (ISAC) that utilizes received signal strength (RSS) measurements from zero-power backscatter radio frequency identification (RFID) tags for both communication and sensing. The proposed system employs a passive tag array, which can facilitate RSS-based key generation for resilient communication and healthcare sensing for fall detection. For key generation, we propose a time-series peak pattern coding method that can achieve strong randomness and low bit mismatch rate between two users, while for fall detection, we propose both a threshold-based approach and a spatio-temporal graph neural network (ST-GNN) method. We present experiments conducted in an indoor laboratory to collect data and validate the effectiveness of the proposed methods. The results demonstrate that the ST-GNN significantly outperforms traditional threshold-based techniques, achieving over 95% accuracy in fall detection across various datasets. Moreover, our backscatter ISAC system provides a cost-effective and sustainable solution for smart healthcare environments.