吉林大学学报(信息科学版) ›› 2016, Vol. 34 ›› Issue (3): 315-319.

• 论文 • 上一篇    下一篇

基于小波变换和支持向量机的心电信号ST 段分类

杨宇1, 司玉娟1,2, 宋晓洋1   

  1. 1. 吉林大学 通信工程学院, 长春 130012; 2. 吉林大学 珠海学院电子信息系, 广东 珠海 519041
  • 收稿日期:2015-08-29 出版日期:2016-05-25 发布日期:2016-12-21
  • 作者简介:杨宇(1991—), 男, 湖北鄂州人,吉林大学硕士研究生,主要从事通信与信息系统研究,(Tel)86-15948384148(E-mail) yangxiaojiang@ yahoo. com; 通讯作者: 司玉娟(1963—), 女, 长春人, 吉林大学教授, 博士生导师, 主要从事通信与信息系统研究, (Tel)86-13604424766(E-mail)siyj@ jlu. edu. cn。
  • 基金资助:

    吉林省重点科技攻关基金资助项目(20150204039GX);吉林省长春市重大科技攻关专项基金资助项目(14KG064); 广东省省级科技计划基金资助项目(2013B010101020)

ST Segment Classification of ECG Signals Based on Wavelet Transform and Support Vector Machine

YANG Yu1, SI Yujuan1,2, SONG Xiaoyang1   

  1. 1. College of Communication Engineering, Jilin University, Changchun 130012, China;2. Department of Electronic Information Science & Technology, College of Zhuhai, Jilin University, Zhuhai 519041, China
  • Received:2015-08-29 Online:2016-05-25 Published:2016-12-21

摘要:

摘要: 为完成ECG(Electrocardiogram)信号特征点提取, 并对ST 段分类, 提出了一种基于离散小波变换和支持向量机的ST 分类算法。首先对信号进行预处理, 完成噪声消除, QRS 波群检测和提取特征值; 然后计算ST段平均值、曲线面积和标准差, 并结合使用SVM(Support Vector Machine)对ST段进行分类。Matlab 仿真结果表
明, 小波去噪效果明显,ST 段未出现失真现象, 特征点提取完整。经MIT鄄BIT 数据库验证, 分类结果显示交叉验证准确率平均值为80. 70%, 训练准确率平均值为91. 83%, 测试准确率平均值为74. 28%。

关键词: 特征点提取, 分类, 小波变换, 支持向量机

Abstract:

Abstract: To complete the ECG signal feature points extraction and the classification of ST segment, we put forward an algorithm based on the discrete wavelet transform, combined with the f derivative and the SVM(Support Vector Machine). The algorithm can accomplish the signal preprocessing, noise elimination, QRS complex detection and extraction of characteristic value, calculating the average ST segment, curve area and the standard deviation, and the simple classification of ST segment by using the SVM combined with the three sets of data. The matlab simulation results show that the wavelet denoising is effective and has no distortion, and completely extract ST segment feature points. The data are downloaded from the MIT-BIT database, the classification results show that cross-validation average accuracy is 80. 70%,the average accuracy of training is 91. 83%, the average testing accuracy was 74. 28%.

Key words: feature point extraction, classification, wavelet transform, support vector machine(SVM)

中图分类号: 

  • TN911