摘要
针对孕妇腹部单通道心电信号的胎心率难以提取的问题,提出一种基于联合聚类分析的单通道母体腹部信号(aECG)的胎心率(FHR)提取方法。首先从孕妇腹部信号提取微弱的和高信噪比的胎儿心电信号(fFCG)并进行预处理;然后使用联合聚类的方法从提取到的微弱的胎儿心电信号中,对胎儿QRS波群(fQRS)进行初步定位;最后根据胎儿QRS波群的初步定位结果,利用基于胎儿RR间期的校正算法提取准确的胎心率。提出的基于联合聚类分析的算法的平均性能为Se=98.28%,PPV=98.16%,F_(1)=98.23%,相较于传统的改进胎儿Pan-Tompkins算法(IFPTA)能够提高胎儿QRS波群的定位精度且能提取出更准确的胎心率。
A fetal heart rate(FHR) extraction method based on single-channel maternal abdominal electrocardiography(aECG) signal based on combined clustering analysis is proposed for the first time to solve the problem that it is challenging to extract FHR from single-channel aECG signal of pregnant women.Firstly,the weak fetal ECG signal with a low signal-to-noise ratio is extracted from the pregnant women’s aECG signal and preprocessing.Secondly,the combined clustering method is used to locate the fetal QRS(fQRS) complex from preprocessed fECG.Finally,according to the preliminary localization results of the fQRS complex,the correction algorithm based on fetal RR interval is used to extract FHR.The algorithm’s average performance based on the combined clustering analysis proposed in this paper is that Se=98.28%,PPV=98.16%,F_(1)=98.23%.Compared with the traditional improved fetal Pan-Tompkins algorithm(IFPTA),the algorithm proposed in this paper can improve the location accuracy of the fQRS complex and extract more accurate FHR.
作者
董亚朋
胡建成
张灵玉
丁大禹
杨波
DONG Yapeng;HU Jiancheng;ZHANG Lingyu;DING Dayu;YANG Bo(Key Laboratory of Biological Effect of Physical Field and Instrument,College of Electronic Engineering,Chengdu University of Information Technology,Chengdu 610225,China;College of Mathematics,Chengdu University of Information Technology,Chengdu 610225,China)
出处
《成都信息工程大学学报》
2021年第4期361-367,共7页
Journal of Chengdu University of Information Technology
基金
四川省科技厅资助项目(2019YFS0143)。
