计算机应用 ›› 2013, Vol. 33 ›› Issue (04): 1173-1175.DOI: 10.3724/SP.J.1087.2013.01173

• 典型应用 • 上一篇    下一篇

基于数学形态学及支持向量机的心率失常识别

刘雄飞,晏晨伟,胡志坤   

  1. 中南大学 物理与电子学院,长沙 410083
  • 收稿日期:2012-11-01 修回日期:2012-11-25 出版日期:2013-04-01 发布日期:2013-04-23
  • 通讯作者: 晏晨伟
  • 作者简介:刘雄飞(1960-),男,湖南长沙人,教授,主要研究方向:数字信号处理、心电图检测算法、车牌定位识别算法;晏晨伟(1989-),男,江西南昌人,硕士研究生,主要研究方向:心电图检测、嵌入式软件;胡志坤(1976-),男,湖北鄂州人,副教授,主要研究方向:复杂系统的在线监测与故障诊断。

Arrhythmia classification based on mathematical morphology and support vector machine

LIU Xiongfei,YAN Chenwei,HU Zhikun   

  1. School of Physics and Electronics, Central South University, Changsha Hunan 410083, China
  • Received:2012-11-01 Revised:2012-11-25 Online:2013-04-23 Published:2013-04-01
  • Contact: YAN Chenwei

摘要: 为实现对不同类型的心电图自动分析,研究并提出了一种顺序筛选极大值的R波定位算法,并采用支持向量机(SVM)进行最后的心律失常心拍识别。定位算法以数学形态学为基础,结合心电图自身特点,定义R波筛选区间,避免了传统算法中的阈值选择;定位R波峰后以R波峰为中心提取不同类型的心率失常的心拍,选择径向基(RBF)支持向量机进行识别分类。使用MIT-BIH心率失常数据库文件进行实验仿真,结果表明,算法对含不同类型心拍的心电图R波峰正确检测率较高(99.36%),学习后的SVM能有效识别早搏、房颤、束支传导阻滞、正常等不用类型心拍,总体识别率达到99.75%。

关键词: 心电图, 数学形态学, R波检测, 心律失常分类, 支持向量机

Abstract: To achieve automatic analysis for different types of ElectroCardioGraph (ECG), a sequential screening method for maximum value was brought to detect R wave, while Support Vector Machine (SVM) was used to identify arrhythmia heart beats finally. The localization algorithm based on mathematical morphology combined with characteristics of ECG defined R-wave screening interval to avoid threshold selection in traditional algorithm. After R-peaks being positioned, various types of arrhythmia heart beats were extracted with R wave crest as its center and classified by selecting Radial Basis Function (RBF) or SVM. The results of the simulation experiment on the MIT-BIH database files indicate that this algorithm acquired high relevance ratio at 99.36% for ECG with different types of heart beats. After learning, the SVM can effectively identify as many as 4 types, such as atrial premature beat, premature ventricular beat, bundle branch block and normal heart beat, the overall recognition rate is 99.75%.

Key words: ElectroCardioGram (ECG), mathematical morphology, R wave detection, arrhythmia classification, Support Vector Machine (SVM)

中图分类号: