SleepSense: A Noncontact and Cost-Effective Sleep Monitoring System

Feng Lin, Yan Zhuang, Chen Song, Aosen Wang, Yiran Li, Changzhan Gu, Changzhi Li, Wenyao Xu

Research output: Contribution to journalArticlepeer-review

58 Scopus citations

Abstract

Quality of sleep is an important indicator of health and well being. Recent developments in the field of in-home sleep monitoring have the potential to enhance a person's sleeping experience and contribute to an overall sense of well being. Existing in-home sleep monitoring devices either fail to provide adequate sleep information or are obtrusive to use. To overcome these obstacles, a noncontact and cost-effective sleep monitoring system, named SleepSense, is proposed for continuous recognition of the sleep status, including on-bed movement, bed exit, and breathing section. SleepSense consists of three parts: a Doppler radar-based sensor, a robust automated radar demodulation module, and a sleep status recognition framework. Herein, several time-domain and frequency-domain features are extracted for the sleep recognition framework. A prototype of SleepSense is presented and evaluated using two sets of experiments. In the short-term controlled experiment, the SleepSense achieves an overall 95.1% accuracy rate in identifying various sleep status. In the 75-minute sleep study, SleepSense demonstrates wide usability in real life. The error rate for breathing rate extraction in this study is only 6.65%. These experimental results indicate that SleepSense is an effective and promising solution for in-home sleep monitoring.

Original languageEnglish
Article number7524724
Pages (from-to)189-202
Number of pages14
JournalIEEE Transactions on Biomedical Circuits and Systems
Volume11
Issue number1
DOIs
StatePublished - Feb 2017

Keywords

  • Evaluation
  • non-contact sensing
  • sleep monitoring

Fingerprint

Dive into the research topics of 'SleepSense: A Noncontact and Cost-Effective Sleep Monitoring System'. Together they form a unique fingerprint.

Cite this