[1]李润川,张行进,陈刚,等.基于多特征融合的心搏类型识别研究[J].郑州大学学报(工学版),2021,42(04):7-12.[doi:10.13705/j.issn.1671-6833.2021.04.011]
 Li Runchuan,Zhang Xingjin,Chen Gang,et al.Research on Heartbeat Type Recognition ba<x>sed on Multi-feature Fusion[J].Journal of Zhengzhou University (Engineering Science),2021,42(04):7-12.[doi:10.13705/j.issn.1671-6833.2021.04.011]
点击复制

基于多特征融合的心搏类型识别研究()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
42卷
期数:
2021年04期
页码:
7-12
栏目:
出版日期:
2021-07-30

文章信息/Info

Title:
Research on Heartbeat Type Recognition ba<x>sed on Multi-feature Fusion
作者:
李润川张行进陈刚姚金良于捷王宗敏
郑州大学信息工程学院;郑州大学互联网医疗与健康服务河南省协同创新中心;

Author(s):
Li Runchuan; Zhang Xingjin; Chen Gang; Yao Jinliang; Yu Jie; Wang Zongmin;
School of Information Engineering, Zhengzhou University; Zhengzhou University Internet Medical and Health Services Henan Coordinated Innovation Center;

关键词:
Keywords:
DOI:
10.13705/j.issn.1671-6833.2021.04.011
文献标志码:
A
摘要:
心律失常是一种常见的心电活动异常,严重的可能会危及人的生命,因此准确诊断心律失常具有十分重要的意义。本文提出了一种新的方法,用于心律失常诊断中对心搏的识别分类。首先对原始心电信号进行去噪预处理,并根据R峰位置获得心搏段。然后提取235单心博特征点、R波幅值、PR间期、QT间期、ST段和RR间期作为特征参数,并对比分析不同特征组合下分类的性能,最后基于KNN模型使用最佳特征组合将心搏分为三类。实验结果表明,本文提出的基于多特征融合与KNN模型的心搏分类方法相比于其他方法具有更好的性能。
Abstract:
Arrhythmia is a common abnormality of cardiac electrical activity, which may seriously endanger human life. Therefore, accurate diagnosis of arrhythmia is of great significance. This paper proposes a new method for the recognition and classification of heartbeat in the diagnosis of arrhythmia. Firstly, the original ECG signal is denoised and preprocessed, and the heartbeat segment is obtained according to the R peak position. Then extract 235 single heartbeat feature points, R wave amplitude, PR interval, QT interval, ST segment and RR interval as feature parameters, and comparatively analyze the performance of classification under different feature combinations. Finally, heartbeats are divided into three categories ba<x>sed on KNN model using the best feature combination. Experimental results show that the heartbeat classification method ba<x>sed on multi-feature fusion and KNN model proposed in this paper has better performance than other methods.
更新日期/Last Update: 2021-08-26