Automatic Classification of ECG Using Multi-Classifiers with a New Fusion Method

Abstract:

ECG signal contains abundant information of human heart activity. It is important basis of doctors’ diagnose. With the development of computer technology, computer aided analysis has been widely applied in the field of ECG analysis. Most of the traditional method is based on single classifier and too complex. Also, the accuracy is not high. This paper focuses on ECG heart beat classification, extracting different types of feature, training different classifiers by vector model and support vector machine (SVM), merging the result of multiple classifiers. In this paper, we used the advanced voting method (voting by weight) to fusion the result of different classifier, having compared it with the traditional voting method.It performed better than traditional method in term of accuracy

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 3917-3922
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.3917
• Online since: November 2014
• Authors: Yi Chang Wang, Feng Qi Yan*, Yu Fang
• Keywords: ECG Signal, Extract Features, Fusion of Classifiers, Heart-Beat Classification

References

[1] Kaici Zhang. ECG clinical informatics. Hunan Science and Technology Press. 2002, 3; 117-133; 1633-1635.

[2] Hu Ji. The key technology of ECG analysis [PHD thesis]. National University of Defense Technology, (2006).

[3] Li Su. Research of remote ECG diagnosis system [PHD thesis]. Harbin Engineering University, (2006).

[4] Chuangmin Zhao. Multi-feature Selection Algorithm of Automatic ECG Analysis [Master thesis]. Suzhou University, (2012).

[5] Rodriguez J, Goñi A and Illarramendi A. Real-time classification of ECGs on a PDA. Information Technology in Biomedicine, IEEE Transactions on. 2005, 9(1): 23-34.

DOI: 10.1109/titb.2004.838369

[6] Jiang X, Zhang L Q, Zhao Q B, et al. ECG arrhythmias recognition system based on independent component analysis feature extraction. TENCON 2006 - 2006 IEEE Region 10 Conference, VOLS 1-4. 2006: 1308-1311.

DOI: 10.1109/tencon.2006.343781

[7] Harvard-MIT Division of Health Sciences and Technology Biomedical Engineering Center. MIT- BIH Arrhythmia Database Directory. http: /physionet. xjtu. edu. cn/physiobank/database/html/mitbdir/mitbdir. html.

[8] Xin Chen. Clinical Electrocardiography. People's Health Press, (2009).

[9] Jiawei Zhang. Recognition of ECG morphology and its role in the classification of research [PHD thesis]. East China Normal University, (2011).

[10] Jiafei Tong. Research of the Pattern Recognition Classification of Statistical ECG common disease [Master thesis]. East China Normal University, (2010).

[11] Joseph E. Mietus, Ary L. Goldberger and Joseph E. Mietus. Heart Rate Variability Analysis with the HRV Toolkit. http: /physionet. xjtu. edu. cn/tutorials/hrv-toolkit.