基于压力传感器的阻塞型睡眠呼吸暂停综合征的检测
首发时间:2018-12-25
摘要:阻塞性睡眠呼吸暂停(OSA)是一种常见与睡眠相关的呼吸系统疾病,会对人们尤其是老年人的健康造成影响。在传统的基于多导睡眠导图(PSG)的OSA检测过程中,人们的睡眠可能会受到干扰,检测设备也容易脱落。本研究提出了一种基于非接触智能床垫的睡眠呼吸暂停检测方法,可以在不干扰人们睡眠的情况下进行检测。通过压力传感器捕获人体胸部和腹部的压力变化,然后对压力信号滤波得到心冲击图信号,进行处理得到心跳周期。从得到的心跳周期序列中准确分析出心率变异性,在固定的时间长度上提取心跳间隔信号的特征,接下来使用分类模型来检测是否发生睡眠呼吸暂停。采用模型融合技术,提高睡眠呼吸暂停检测的准确性。
关键词: 阻塞型睡眠呼吸暂停 心率变异性 分类模型 模型融合
For information in English, please click here
Detection of Obstructive Sleep Apnea Syndrome Based on Pressure Sensor
Abstract:Obstructive sleep apnea (OSA) is a common sleep-related respiratory disease that affects people's health, especially in the elderly. In the traditional PSG-based OSA de-tection process, people's sleep may be disturbed, equipment pipelines are also easy to fall off. In this paper, we study a sleep apnea detection method based on non-contact mattress, which can detect OSA accurately without disturbing people's sleep. Piezoelectric ceramics sensors are used to capture pressure changes in the human chest and abdomen. Then heart rate is obtained from impulse waveforms that converted by filtering and processing of the pressure signals. At last, heart rate variability, i.e. the heartbeat cycle series, is accurately calculated by processing the physiological signal. The features of the heartbeat interval signal is extracted over a fixed length of time, wherein a classification model is used to predict whether sleep apnea will occur. Model integration technique is adopted achieve better sleep apnea detection accuracy. Results show that the proposed algorithm can be as an effective means to predict OSA.
Keywords: Obstructive sleep apnea HRV Classification model Model integration
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于压力传感器的阻塞型睡眠呼吸暂停综合征的检测
评论
全部评论0/1000