一种改进的心电图QRS波群检测算法

发布时间：2018-01-26 12:11

本文关键词： 心电信号 QRS波群区域极值配对小波变换 MIT-BIH　出处：《计算机工程与科学》2016年05期 　论文类型：期刊论文

【摘要】：在利用小波变换检测QRS波群时,最关键的部分就是模极值配对,提出一种区域极值配对算法来检测R波。首先利用二次样条小波基函数和多孔(ATrous)算法对心电(ECG)信号进行小波变换求取模极值,用正极大值来确定搜索区域,以这个正极大值为起点,以这个确定区域为搜索范围,向左搜索负极大值点,将这两个极值配对,他们之间的过零点就是R波的对应点,然后在检测到R波的基础上检测出Q波与S波,再结合距离最大值法检测出QRS波群的起止点。并采用医学相关理论对检测结果进行优化,进一步去除错检点,补偿漏检点。最后利用MIT-BIH心率失常数据库中记录的数据对该算法进行验证,实验结果表明所提算法能准确检测QRS波群,平均检出率达到了99.97%。
[Abstract]:When using wavelet transform to detect QRS wave group, the most important part is module extremum pairing. A region extremum pairing algorithm is proposed to detect R-wave. Firstly, the wavelet transform is used to calculate the modulus extremum of ECG ECG signal by using quadratic spline wavelet basis function and porous ATrousalgorithm. Using the positive maximum to determine the search region, taking the positive maximum as the starting point, taking the determined region as the search range, searching for the negative maximum point to the left, and matching the two extreme values. The 00:00 between them is the corresponding point of R wave, and then the Q wave and S wave are detected on the basis of detecting R wave. Then the starting and ending points of QRS wave group are detected by the maximum distance method, and the detection results are optimized by medical theory to further remove the fault detection points. Finally, the algorithm is verified by the data recorded in the MIT-BIH arrhythmia database. The experimental results show that the proposed algorithm can accurately detect the QRS wave group. The average detection rate was 99.97%.
【作者单位】：长沙理工大学计算机与通信工程学院;
【分类号】：TP391.41;R540.41
【正文快照】： 1引言心电图是心脏活动的电表示,能够客观反映心脏各部位的生理状况,因此具有重要临床意义。一系列的P波、QRS波、T波组成了心电信号[1],其中QRS波群占据范围最大,具有较高的幅值分量和频率分量,其特性最为明显,便于检测。在准确Address:School of Computer and Communication

【相似文献】