Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2021, Vol. 57 ›› Issue (5): 833-840.DOI: 10.13209/j.0479-8023.2021.079

Previous Articles     Next Articles

Research of Sleep Staging Algorithms Based on ECG and Body Motion Signals

LIU Zhong1,2, WANG Xin’an1,†, LI Qiuping1, ZHAO Tianxia1   

  1. 1. The key Laboratory of Integrated Microsystems, Peking University Shenzhen Graduate School, Shenzhen 518000 2. School of Electronics Engineering and Computer Science, Peking University, Beijing 100871
  • Received:2020-09-03 Revised:2020-09-30 Online:2021-09-20 Published:2021-09-20
  • Contact: WANG Xin’an, E-mail: anxinwang(at)


刘众1,2, 王新安1,†, 李秋平1, 赵天夏1   

  1. 1. 北京大学深圳研究生院集成微系统科学与工程应用实验室, 深圳 518055 2. 北京大学信息科学技术学院, 北京 100871
  • 通讯作者: 王新安, E-mail: anxinwang(at)


 In order to study the overnight sleep condition and analyze each stage of the sleep process, polysomnography (PSG) and actigraphy were used to collect the ECG signal and body motion data. The features of ECG signal and heart rate variability (HRV) were extracted and used as the characteristic parameters of the data. In order to improve the recognition rate and prevent over-fitting, the data were divided into training set and test set, and an improved BP neural network model with genetic algorithm was designed to train and predict the samples. The results show that the improved BP neural network can effectively identify the test samples, and the comprehensive recognition accuracy is 86.29%. Wearable devices that detect both ECG and body motion signals with sleep stage classifying algorithms, can be used for family sleep monitoring and as a primary screen method for sleep disorders.

Key words: sleep stage, back propagation network, genetic algorithm, ECG signals, body motion signals


为了研究整夜睡眠状况和睡眠过程, 利用多导睡眠仪(polysomnography, PSG)和体动记录仪, 分别记录被试的ECG信号和体动信号, 再对 ECG信号提取心率变异性(heart rate variability, HRV)的特征值, 并将其作为实验数据的特征参数。为了提高识别率和防止过度拟合, 将实验数据分为训练集和测试集, 设计一个用遗传算法改进的BP神经网络模型, 对样本进行训练和预测。研究结果表明, 改进的BP神经网络能有效地识别测试样本, 综合识别准确率为86.29%。将检测ECG信号和体动信号的穿戴式设备与睡眠分期识别算法相结合, 能够用于家庭睡眠监测, 也可作为睡眠疾病的初筛方法。

关键词: 睡眠分期, 向后传播神经网络, 遗传算法, ECG信号, 体动信号