基于心冲击信号的睡姿识别
|
摘要
研究证明,睡眠质量与睡姿有着密切关系,不良的睡姿甚至会加剧多种疾病的潜在风险。为了更精准地进行睡眠健康监控,提出了一种基于心冲击(BCG)信号的睡姿模式识别算法,使用非接触、无干扰的压电薄膜传感器采集BCG信号,在腰腹部采集仰卧、俯卧、左侧卧和右侧卧4种睡姿信号,经小波变换降噪等预处理后提取基于J波的特征值,设计并比较基于神经网络和KNN的睡姿识别分类器。实验结果表明,神经网络睡眠识别算法的平均正确识别率为93%,KNN算法为84%,因此基于BCG信号的神经网络睡姿识别算法可以广泛用于睡眠监测应用。
Studies show that sleep position can affect one's sleep quality, and inappropriate position may potentially increase risks for multiple diseases. In this paper, a Ballistocardiogram(BCG)signal based sleeping position pattern recognition algorithm is presented. BCG signals from four different sleeping positions(supine, prone, left lateral and right lateral)are collected with a piezoelectric film sensor in a non-contact way. Eight characteristics are extracted from the preprocessed BCG signals after wavelet-based denoising, and the sleep position pattern is recognized using BP neural network and KNN. The experimental results show that recognition accuracy of the neural network algorithm and KNN are 93% and 84%, respectively. Therefore, BCG-based sleep position recognition with neural network has a potential to be widely used in sleep monitoring applications.
Studies show that sleep position can affect one's sleep quality, and inappropriate position may potentially increase risks for multiple diseases. In this paper, a Ballistocardiogram(BCG)signal based sleeping position pattern recognition algorithm is presented. BCG signals from four different sleeping positions(supine, prone, left lateral and right lateral)are collected with a piezoelectric film sensor in a non-contact way. Eight characteristics are extracted from the preprocessed BCG signals after wavelet-based denoising, and the sleep position pattern is recognized using BP neural network and KNN. The experimental results show that recognition accuracy of the neural network algorithm and KNN are 93% and 84%, respectively. Therefore, BCG-based sleep position recognition with neural network has a potential to be widely used in sleep monitoring applications.
引文
[1]Kalolella A B.Sleeping position and reported night-time asthma symptoms and medication[J].Pan African Medical Journal,2016,24.
[2]Khan S,Uddin M B,Ahmad M.Effects of elevated sleeping postures on cardiac functions analyzing electrical bio-impedance and skin blood perfusion[C]//International Conference on Electrical Information and Communication Technology,2015:162-166.
[3]Lin F,Zhuang Y,Song C,et al.Sleep Sense:A noncontact and cost-effective sleep monitoring system[J].IEEE Transactions on Biomedical Circuits&Systems,2016:1-14.
[4]Mador M J,Kufel T J,Magalang U J,et al.Prevalence of positional sleep apnea in patients undergoing polysomnography[J].Chest,2005,128(4):2130-2137.
[5]叶荫球,姜太平,张蕾.基于水平集方法和神经网络的人体睡姿识别[J].工业控制计算机,2013(5):88-90.
[6]任志斌,李洋,郭士杰,等.基于模糊粗糙集的睡姿压力图像识别[J].计算机工程与应用,2018,54(3):172-177.
[7]Xu X,Lin F,Wang A,et al.On-bed sleep posture recognition based on body-earth mover’s distance[C]//IEEE Biomedical Circuits and Systems Conference,2015:1-4.
[8]Brink M,Müller C H,Schierz C.Contact-free measurement of heart rate,respiration rate,and body movements during sleep[J].Behavior Research Methods,2006,38(3).
[9]Awal M A,Mostafa S S,Ahmad M,et al.An adaptive level dependent wavelet thresholding for ECG denoising[J].Biocybernetics&Biomedical Engineering,2014,34(4):238-249.
[10]Starr I,Wood E C.Twenty years studies with the ballistocardiograph,the relation between the amplitude of the fist record of health adults and eventual mortality and morbidity from heart disease[J].Circulation,1961,23(1):714-732.
[11]Cao X,Wang J,Zhang X,et al.A ballistocardiogram measurement system for home monitoring:design,performance,and evaluation[J].Science Bulletin,2014,59(23):2909-2917.
[12]Alvarado-Serrano C,Luna-Lozano P S,Pallàs-Areny R.An algorithm for beat-to-beat heart rate detection from the BCG based on the continuous spline wavelet transform[J].Biomedical Signal Processing&Control,2016,27:96-102.
[13]蒋芳芳,王旭,杨丹.基于心脏动力学的体震信号建模与仿真[J].系统仿真学报,2013,25(3):420-424.
[14]金晶晶,王旭,于艳波,等.基于正交小波变换的心冲击图自适应去噪方法[J].计算机科学,2010,37(8):232-235.
[15]杨军,俞梦孙,王宏山,等.多参数信息融合实现非脑电的睡眠结构分期[J].中国生物医学工程学报,2006,25(3):315-321.
[2]Khan S,Uddin M B,Ahmad M.Effects of elevated sleeping postures on cardiac functions analyzing electrical bio-impedance and skin blood perfusion[C]//International Conference on Electrical Information and Communication Technology,2015:162-166.
[3]Lin F,Zhuang Y,Song C,et al.Sleep Sense:A noncontact and cost-effective sleep monitoring system[J].IEEE Transactions on Biomedical Circuits&Systems,2016:1-14.
[4]Mador M J,Kufel T J,Magalang U J,et al.Prevalence of positional sleep apnea in patients undergoing polysomnography[J].Chest,2005,128(4):2130-2137.
[5]叶荫球,姜太平,张蕾.基于水平集方法和神经网络的人体睡姿识别[J].工业控制计算机,2013(5):88-90.
[6]任志斌,李洋,郭士杰,等.基于模糊粗糙集的睡姿压力图像识别[J].计算机工程与应用,2018,54(3):172-177.
[7]Xu X,Lin F,Wang A,et al.On-bed sleep posture recognition based on body-earth mover’s distance[C]//IEEE Biomedical Circuits and Systems Conference,2015:1-4.
[8]Brink M,Müller C H,Schierz C.Contact-free measurement of heart rate,respiration rate,and body movements during sleep[J].Behavior Research Methods,2006,38(3).
[9]Awal M A,Mostafa S S,Ahmad M,et al.An adaptive level dependent wavelet thresholding for ECG denoising[J].Biocybernetics&Biomedical Engineering,2014,34(4):238-249.
[10]Starr I,Wood E C.Twenty years studies with the ballistocardiograph,the relation between the amplitude of the fist record of health adults and eventual mortality and morbidity from heart disease[J].Circulation,1961,23(1):714-732.
[11]Cao X,Wang J,Zhang X,et al.A ballistocardiogram measurement system for home monitoring:design,performance,and evaluation[J].Science Bulletin,2014,59(23):2909-2917.
[12]Alvarado-Serrano C,Luna-Lozano P S,Pallàs-Areny R.An algorithm for beat-to-beat heart rate detection from the BCG based on the continuous spline wavelet transform[J].Biomedical Signal Processing&Control,2016,27:96-102.
[13]蒋芳芳,王旭,杨丹.基于心脏动力学的体震信号建模与仿真[J].系统仿真学报,2013,25(3):420-424.
[14]金晶晶,王旭,于艳波,等.基于正交小波变换的心冲击图自适应去噪方法[J].计算机科学,2010,37(8):232-235.
[15]杨军,俞梦孙,王宏山,等.多参数信息融合实现非脑电的睡眠结构分期[J].中国生物医学工程学报,2006,25(3):315-321.