心电信号中特征波分割方法研究综述  

A Review of Research on Feature Wave Segmentation Methods in ECG Signals

作　　者：马建红[1] 段豪 韩颖[1] MA Jianhong;DUAN Hao;HAN Ying(School of Cyber Science and Engineering,Zhengzhou University,Zhengzhou 450002,China)

机构地区：[1]郑州大学网络空间安全学院,河南郑州450002

出　　处：《郑州大学学报（理学版）》2023年第2期79-87,共9页Journal of Zhengzhou University:Natural Science Edition

基　　金：国家重点研发计划重点专项子课题项目(2020YFB1712401-1);郑州市协同创新重大专项项目(20XTZX06013)。

摘　　要：在心电图信号中,正常的心跳波形通常包含P波、QRS波和T波,这些特征波的识别对疾病的辅助诊疗有着重要的价值,因而特征波的分割成为当前研究热点之一。首先概述了心电信号特征波分割的整体流程,并对传统信号处理算法应用于特征波分割任务进行了总结;然后分析对比了机器学习算法、深度学习算法在心电特征波分割任务中的特点;最后展望自监督学习算法在心电特征波分割领域的应用前景,为该领域的技术发展提供了新的研究思路。In the ECG signal,the normal heartbeat waveform usually includes P wave,QRS wave and T wave.The identification of these feature waves had important application value for the auxiliary diagnosis and treatment of diseases,so the segmentation of feature waves became one of the current research hotspots.Firstly,the whole process of ECG signal feature wave segmentation was summarized,and the application of traditional signal processing algorithms to feature wave segmentation was summarized.Then,the characteristics of machine learning algorithm and deep learning algorithm in ECG feature wave segmentation task were analyzed and compared.Finally,the application of self-supervised learning algorithm in ECG feature wave segmentation was prospected,which provided a new research idea for the technical development in this field.

关 键 词：心电图 心电特征波 心电分割 心电定位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]