A Multi-Modal System with Wireless Flexible Sensor Patches and a Depth-Sensing Imager for At-Home Monitoring of Rehabilitation Exercises

Long-term at-home monitoring of rehabilitation performance after spinal cord injuries is crucial for optimizing therapeutic outcomes, reducing the rehabilitation period, and improving patient quality of life. However, there is currently a lack of an easy-to-use system that allows patients to collect data during exercise. To address this gap, this paper introduces the development of a self-contained, multi-modal sensor system that captures surface electromyography (SEMG) and motion data, along with a depth-sensing imager for monitoring patient exercise activities. The system consists of a scalable number of wireless multi-sensor wearable patches that are easy to attach and comfortably worn over extended periods, and a time-of-flight depth-sensing imaging sensor, which detects patient activities while collecting minimal information to protect privacy. The multi-modal data is streamed to a Raspberry Pi and synchronized in real time. This system provides a new framework that supports the rehabilitation of spinal cord injuries and can be adapted for a broad range of other clinical monitoring applications.