Machine Learning‐Enabled Noncontact Sleep Structure Prediction

Automated, effective and efficient sleep‐stage monitoring and structure analysis is an essential enabling procedure for healthcare automation. Sleep diagnosis by polysomnography is a golden standard but expensive procedure involving huge effort from patients. There remain challenges for smart devices to precisely identify sleep stage and minimize intrusive effect on sleep progression. Herein, a novel noncontact sleep structure prediction system (NSSPS) using a single radar sensor is presented to analyze sleep structure without any tethered unit. The NSSPS is realized through training a convolutional recurrent neural network and neural conditional random fields using reflected radio frequency (RF) waves acquired by radar antennas. By capturing implicit temporal information in RF signals and transitions of sleep progression, high accuracy of sleep‐stage prediction is achieved and characteristics of sleep structure are extracted. The performance of the NSSPS is validated by transfer learning between radar signals with different frequency bands and crossvalidation among different subjects. Moreover, the NSSPS is demonstrated to estimate overnight parameters that are critical for sleep diagnosis. Benefiting from its low cost, convenient setup, and accurate prediction capability of sleep‐stage identification, the NSSPS can be widely deployed in “smart” homes and exploited to conduct daily sleep structure analysis. Herein, a novel system using a single radar sensor and deep learning is presented to monitor sleep without any tethered unit. By capturing implicit temporal information in radio signals, accurate sleep‐stage prediction and structure evaluation are achieved. The presented noncontact system can be widely deployed in “smart” homes or hospitals to conduct daily sleep analysis.