Sleep monitoring using body sounds and motion tracking

摘要

This paper presents a system for sleep monitoring that can continuously analyze snoring, breathing, sleep phases and the activity of the patient during the night and the beginning of the day. Early results show that the system can be used to detect the occurrence of obstructive sleep apnea syndrome (OSAS). OSAS is traditionally diagnosed using polysomnography, which requires a whole night stay at the sleep laboratory of a hospital, where the patient is attached to multiple electrodes and sensors. Our system detects heartbeats, breathing, snoring, sleeping positions and movements using a special electret microphone and an inertial measurement unit (IMU). The system first analyses the sleep using the acoustic information provided by the electret microphone. From the acoustic information breathing events and heartbeats are identified. The system also analyses the patient's activity and positions from data delivered by the IMU. The information from both sensors is fused to detect sleep events. First experiments show that the system is capable of detecting and interpreting relevant data to improve sleep monitoring.