Gaiduk Maksym, Seepold Ralf, Penzel Thomas, Ortega Juan A, Glos Martin, Madrid Natividad Martinez
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:5712-5715. doi: 10.1109/EMBC.2019.8857596.
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.
本文档介绍了一种算法，该算法通过躺在床上时采集的心电图、呼吸和身体运动信号，对睡眠/清醒状态进行非侵入式识别。作为系统数据分析的核心数学基础，选择了多项逻辑回归技术。这三种信号的派生参数用作该方法的输入。清醒/睡眠阶段的总体准确率为84%，科恩kappa值为0.46。所提出的算法应有助于专家更详细地分析睡眠质量。结果证实了该方法的潜力，并揭示了几种改进方法。
