北京生物医学工程

基于DCT的心电信号分类算法

Classification algorithm of ECG based on DCT

作者：卢潭城吕愿愿邓永莉刘明亮陆起涌

单位：复旦大学电子工程系(上海200433)

分类号：R318.04;TP391.4

出版年·卷·期（页码）：2016·35·3（259-266）

摘要：

目的提高心电信号的分类准确率，降低算法复杂度。方法首先以MIT-BIH心电数据作为学习模板，然后在心电信号的频域和时域上提取其离散余弦变换(discrete cosine transform,DCT)、R-R间期和QRS复合波的三种特征值进行分析，最后采用最小欧式距离分类器判断待测心电信号的类型。结果该分类模型通过MIT-BIH和AHA国际标准心电数据库的验证，分别得到96.6%和94.1%的分类准确率。结论本文的心电分类模型区别于其他分类算法的一个最大特点就是算法复杂度低，这是异常心律能够被实时检测和预警的关键，而且建立的心电分类模型已经能够在普通的手机平台上实现。

Objective To improve the classification accuracy of ECG and reduce the complexity of the algorithm.Methods This paper uses MIT-BIH ECG database as learning templates,then extracts its eigenvalues of DCT,R-R interval and QRS from frequency and time domain of ECG signals to analyze.Finally,the type of ECG signal is classified based on the minimum Euclidean distance classifier.Results The classification model is tested and verified by international standard MIT-BIH and AHA ECG database,with the classification accuracy of 96.6% and 94.1%,respectively.Conclusions Lower complexity in ECG classification model than other algorithm is the greatest feature,which is the key of detecting real-time abnormal heart rhythms.And ECG classification model has been realized on a common mobile platform.

参考文献：

［1］杨虎. 远程心电监测技术进展［J］. 中国医疗器械信息，2005，11(6)：11-12.

Yang Hu. The technology development of TELE electrocardiogram monitoring［J］. China Medical Device Information，2005，11(6)：11-12.

［2］Lu TC, Peng L, Xiang G, et al. A portable ECG monitor with low power consumption and small size based on AD8232 chip ［C］. Applied Mechanics and Materials, 2014: 2884-2887.

［3］王丽苹，董军. 心电图模式分类方法研究进展与分析［J］. 中国生物医学工程学报，2010，29(6): 916-926.

Wang Liping, Dong Jun. The advance research and analysis of electrocardiogram pattern classification［J］. Chinese Journal of Biomedical Engineering，2010，29(6): 916-926.

［4］夏宏器，邓开伯. 心律失常的临床分析与决策［M］. 北京：中国协和医科大学出版社，2002：6-111.

［5］Pathoumvanh S, Hamamoto K, Indahak P. Arrhythmias Detection and Classification base on Single Beat ECG Analysis ［C］. 2014 4th Joint International Conference on JICTEE. Chiang Rai, 2014: 1-4

［6］Lai S, Chien W, Lan C, et al. An efficient DCT-IV-based ECG compression algorithm and its hardware accelerator design ［C］. 2013 3 IEEE International Symposium on ISCAS. Beijing, 2013: 1296-1299.

［7］韩君泽. 心电信号自动检测与诊断方法的研究［D］. 哈尔滨：哈尔滨工业大学，2013.

［8］张茜，邵堃，刘磊. 一种基于最小距离分类器的恶意代码检测方法［J］. 广西师范大学学报：自然科学版，2009，27(3):183-187.

Zhang Qian, Shao Kun, Liu Lei. A detection of malicious code based on minimum distance classifier ［J］. Journal of Guangxi Normal University: Natural Science Edition, 2009，27(3):183-187.

［9］宋喜国，邓亲恺. MIT-BIH心率失常数据库的识读及应用［J］. 中国医学物理学杂志，2004，21(4):230-232.

Song Xiguo, Deng Qinkai. On the format of MIT-BIH arrhythmia database ［J］. Chinese Journal of Medical Physics，2004，21(4):230-232.

［10］Linh TH, Stanislaw O, Stodolski M. On-line Heart Beat Recognition Using Hermite Polynomials and Neuro-fuzzy Network ［J］. IEEE Transactions on Instrumentation and Measurement, 2003, 52(4): 1224-1231.

［11］Vargas F, Lettnin D, Felippetto de Castro MC, et al. Electrocardiogram Pattern Recognition by Means of MLP Network and PCA: A Case Study on Equal Amount of Input Signal Types ［C］. Brazilian Symposium on Neural Networks, 2002: 200-205.

［12］He L, Hou WS, Zhen XL, et al. Recognition of ECG Patterns Using Artificial Neural Network ［C］. Proceedings of the Sixth International Conference on Intelligent Systems Design and Applications. Jinan, 2006: 6(2)477-481.

［13］张雷刚. 心电信号的特征提取与分类研究［D］. 合肥：中国科学技术大学，2012.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录