A preliminary result on sleep posture identification with BCG signals
Konferenz: BIBE 2019 - The Third International Conference on Biological Information and Biomedical Engineering
20.06.2019 - 22.06.2019 in Hangzhou, China
Tagungsband: BIBE 2019
Seiten: 4Sprache: EnglischTyp: PDFPersönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt
Zhang, Yichao (Engineering Research Center of Mobile Health Management System, Ministry of Education, Hangzhou Normal University, Hangzhou, Zhejiang, China)
Song, Weize; Yuan, Zhenming; Sun, Xiaoyan (Engineering Research Center of Mobile Health Management System, Ministry of Education, School of Information Science and Engineering, Hangzhou Normal University, Hangzhou, Zhejiang, China)
Frequent changing of sleep postures may affect one’s sleep quality. Research also indicated that obstructive sleep apnea (OSA) was body posture dependent, while OSA can cause severe consequences. In this paper, a smart device for sleep monitoring without interrupting one’s normal sleep was proposed. The user’s Ballistocardiography (BCG) signal was recorded with pressure sensors installed under an ordinary mattress. Some posture specific signal characteristics were revealed, and preliminary results demonstrated the feasibility of the system for unobtrusive sleep posture identification with neural network based BCG signal processing. The accuracy of four-class body posture identification (lateral, prone and supine) was 96.47%.