BedSense: A Bed-Mounted Sensor Node System for Sleep Activities Monitoring and Nocturnal Falls Detection

The increasing elderly population is affecting the socioeconomic balance in developed countries. Falls in general and particularly nocturnal falls are major key role players in healthcare costs. In this article, we propose a novel real-time sensor node system, nonwearable, and mounted on the contour of the bed mattress to continuously monitor sleep activities and detect nocturnal falls. The proposed system consists of eight-node sensors, each consisting of an inertial measurement unit (IMU), a microcontroller unit (MCU), and a serial network interface. The sensor nodes communicate on a single bus with a remote monitoring station. The system utilizes bed vibrations from accelerometers generated by body movements to detect and categorize sleep activities as well as identify fall events. The system generates real-time results and provides information about sleeping postures. The efficacy and robustness of the system were assessed by measuring key performance metrics, including sensitivity, accuracy, precision, and F1-score. Experiments conducted on 25 volunteers showed results exceeding 90% for all four metrics.