TY - CHAP U1 - Konferenzveröffentlichung A1 - Gaiduk, Maksym A1 - Seepold, Ralf A1 - Penzel, Thomas A1 - Ortega, Juan Antonio A1 - Glos, Martin A1 - Martínez Madrid, Natividad T1 - Recognition of sleep/wake states analyzing heart rate, breathing and movement signals T2 - 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2019), 23-27 July 2019, Messe Berlin, Germany N2 - This document presents an algorithm for a non-obtrusive recognition of Sleep/Wake states using signals derived from ECG, respiration, and body movement captured while lying in a bed. As a core mathematical base of system data analytics, multinomial logistic regression techniques were chosen. Derived parameters of the three signals are used as the input for the proposed method. The overall achieved accuracy rate is 84% for Wake/Sleep stages, with Cohen’s kappa value 0.46. The presented algorithm should support experts in analyzing sleep quality in more detail. The results confirm the potential of this method and disclose several ways for its improvement. KW - Sleep study KW - Multinomial logistic regression KW - Sleep/Wake states Y1 - 2019 SN - 978-1-5386-1311-5 SB - 978-1-5386-1311-5 U6 - https://doi.org/10.1109/EMBC.2019.8857596 DO - https://doi.org/10.1109/EMBC.2019.8857596 N1 - Volltextzugriff für Angehörige der Hochschule Konstanz via IEEE Xplore möglich SP - 5712 EP - 5715 PB - IEEE ER -