Unsupervised Detection of Multiple Sleep Stages Using a Single FMCW Radaropen access
- Authors
- Yoo, Young-Keun; Jung, Chae-Won; Shin, Hyun-Chool
- Issue Date
- Apr-2023
- Publisher
- MDPI
- Keywords
- sleep stage detection; contactless; non-learning; vital detection; signal processing; FMCW radar
- Citation
- APPLIED SCIENCES-BASEL, v.13, no.7
- Journal Title
- APPLIED SCIENCES-BASEL
- Volume
- 13
- Number
- 7
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/43890
- DOI
- 10.3390/app13074468
- ISSN
- 2076-3417
- Abstract
- The paper proposes a unsupervised method for detecting the three stages of sleep-wake, rapid eye movement (REM) sleep, and non-REM sleep-using biosignals obtained from a 61 GHz single frequency modulated continuous wave (FMCW) radar. To detect the subject's sleep stages based on non-learning techniques, the breathing and movement information characteristic of each sleep stage was extracted from the radar signals of the subject acquired in the sleep state and used as the feature factor tailored to the research objective. The experimental results derived from the clinical data obtained in the actual polysomnography (PSG) environment using FMCW radar show an average of 68% similarity to the actual three sleep stages observed in PSG. These results indicate the feasibility of using the FMCW radar sensor as an alternative to the conventional PSG-based method that poses multiple limitations to sleep-stage detection.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.