通过腹部起伏测呼吸状态的检测方法研究  

Method for detecting respiratory status by abdominal rise and fall

作　　者：邓冉琦 张莉[1] Deng Ranqi;Zhang Li(College of Biomedical Engineering,South-Central University for Nationalities,Wuhan 430070,China)

机构地区：[1]中南民族大学生物医学工程学院,武汉430070

出　　处：《国外电子测量技术》2022年第11期30-36,共7页Foreign Electronic Measurement Technology

基　　金：中央高校基本科研业务费专项资金项目(CZZ21007)资助。

摘　　要：针对当前实时检测呼吸状态的方式存在检测精度不够或佩戴方式繁琐等问题,提出一种利用腹部起伏测呼吸状态的检测方法。该方法基于肺部气体体积与腹部位移之间的高度相关性,利用气体压力传感器采集一次被试者平稳状态下的肺部气体体积,并将此数据作为基准数据,然后用加速度传感器采集被试者在呼吸缓慢、呼吸平稳、呼吸急促,3种呼吸状态下的腹部位移数据。计算肺部与腹部数据在3种不同状态下的规整距离,将该规整距离和从腹部数据中提取的周期一起作为二维特征,输入到支持向量机分类器进行分类判别,所有算法嵌入到硬件端进行计算。整体系统准确率在87%左右。该方法具有检测结果稳定可靠、实施成本低以及佩戴方式简便等优点,实用性较高。Aimed at the problems of cumbersome wearing and insufficient detection accuracy of the current respiratory state detection way, a respiratory status detection method based on abdominal undulation was proposed. Based on the high correlation between lung gas volume and abdominal displacement, the gas pressure sensor was used to collect the lung gas volume of a subject in a stationary state, and this data was used as the baseline data. Acceleration sensors were used to collect the abdominal displacement data of the subjects in three breathing states: slow breathing, steady breathing and rapid breathing. The structured distance between the lung and abdominal data in three different states was calculated. The structured distance and the period extracted from the abdominal data were used as two-dimensional features and input to the support vector machine classifier for classification and discrimination. All algorithms are embedded in the hardware side for calculation. The overall system accuracy rate is about 87%. The method has the advantages of stable and reliable detection results, low implementation cost and simple wearing mode, and has high practicability.

关 键 词：呼吸状态检测 相关性 规整距离 支持向量机 嵌入式系统 

分 类 号：R318.0[医药卫生—生物医学工程]