Design and Validation of a Non-Contact Bed Micro-Movement Sensing System for HRV Monitoring

• Published in: IEEE robotics and automation letters Vol. 10; no. 5; pp. 5034 - 5041
• Main Authors: Feng, Yongfei, Zhou, Haoyu, Luo, Jingjing, Cai, Yichen, Wang, Hongbo
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.05.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: ballistocardiogram; Ballistocardiograms; Band-pass filters; bed-based health monitoring; Beds; Cutoff frequency; Deep learning; ECG-R wave reconstruction; Electrocardiography; Heart rate; Heart rate variability; Low-pass filters; Monitoring; Non-contact physiological monitoring; piezoelectric film sensor; Piezoelectric films; Polyvinylidene fluorides; Real time; Real-time systems; Robot sensing systems; Telemedicine; Training
• ISSN: 2377-3766; 2377-3766
• DOI: 10.1109/LRA.2025.3554456

The growing demand for non-wearable, long-term health monitoring solutions, especially for elderly, has driven the development of bed-based physiological monitoring systems. This letter introduces a novel non-contact, bed-based micro-movement sensing system designed for accurate heart rate variability (HRV) monitoring. The system uses a polyvinylidene fluoride (PVDF) piezoelectric film sensor to detect ballistocardiogram (BCG) signals through a 10 cm thick mattress, ensuring both comfort and practicality in real-world settings. A deep learning model combining an attention mechanism, phase shift correction, and a ResUNet architecture is employed to reconstruct ECG-R waves from the BCG signals, enabling precise RR interval estimation. The system computes a comprehensive set of HRV metrics, including time-domain, frequency-domain, and non-linear indices, with high accuracy. Extensive experiments involving 20 subjects validate the system's performance, demonstrating a mean absolute error of less than 10 ms in RR interval estimation. 20 out of 23 HRV metrics evaluated had average relative errors under 15%. The results highlight the system's robustness and its ability to operate effectively through thick bedding materials, offering a reliable and practical solution for continuous health monitoring. Furthermore, the proposed technology has the potential to be integrated into future bed-based caregiving robots, enabling real-time health monitoring and autonomous care servicing, thereby enhancing caregiving efficiency and intelligence.