A wearable sleep position tracking system based on dynamic state transition framework

Abstract

Sleep monitoring is vital as sleep plays an important role in recovering physical and mental health. To have a sound sleep, one has to avoid bad sleep positions associated with personal health conditions. However, most of the existing sleep trackers merely show quantitative information about sleep patterns and duration at each sleep stage, overlooking the importance of sleep positions upon sleep quality. To accurately keep track of sleep positions, we propose a wearable sleep position tracking system consisting of two wristbands and one chest-band. We suggest a two-level classifier specialized for sleep motion based on Dynamic State Transition (DST)-framework. The DST-framework is designed to process the spatio-temporal sleep motion data collected via accelerometer/gyro sensing and classify twelve sleep position (SP) motions from four sleep positions. Our experimental results demonstrate that the proposed system effectively and accurately classify twelve SP motions for tracking sleep positions, and hence, serves as a key building block for comprehensive sleep care applications related to sleep positions.