Document Type : Full Research Paper


1 Instructor, Electrical Group, Bookan Branch, Islamic Azad University

2 Associate Professor, Electrical Engineering School, Iran University of Science and Technology

3 Instructor, Engineering Faculty- Electrical Group, Gilan University



In this paper, the role of Vector Quantizer Neural Network in classification of six types of ECG signals has been investigated using the features that extracted from Daubechies6 Wavelet transformation. The six types of signals are: normal beat, left bundle branch block beat, right bundle branch block beat, premature ventricular contraction paced beat and fusion of paced and normal beats. The required data were obtained from the MIT/BIH arrhythmia databases. By using the annotation files of the databases, the patterns of these six types of ECG signals were separated. Then, for better feature extraction, filtering and scaling on the patterns were applied. We used the energies of the last five detailed signals obtained from the exerting the Wavelet transformation in six levels, as the pattern features for Vector Quantizer Network training and testing. From each class, five hundred patterns were used for network training and one hundred patterns for testing. The results indicated %93.1 accuracy for six classes and above %94.3 for lesser than six classes. Then the rate of similarity and dissimilarity of the classes were considered. Finally, the results of this method were compared with some other methods in terms of accuracy.


Main Subjects

[1]     اسماعیل‌پور جمال، پیاده‌سازی پیس‌میکر با استفاده از پردازنده‌های سیگنال‌های دیجیتال، پایان‌نامه کارشناسی ارشد الکترونیک دانشگاه گیلان، 1383، 125-136.
[2]     B. N. Hung, Y. S. Tsai, and T. H. Chu; FFT algorithm for PVC detection using IBM PC; in Proc. IEEE Eng. Med. And Biol Soc., 8th Annu. Int., Conf., 1986: 292- 295.
[3]     B. N. Hung, H. F. Cheng, and Y. S. Tsai; An application of fast Walsh transform in ECG diagnosis; in Proc, IEEE Eng. Med. And Biol. Soc. 9th Annu. Int. Conf., 1987: 497-498.
[4]     W. H. Chang, K. P. Lin, and S. Y. Tseng; ECG analysis based on Hilbert Transform descriptor; in Proc. IEEE Eng. Med. And Biol. Soc. 10th Annu. Int. Conf., 1988: 36-37.
[5]     Yu, Liu, and Lee; Hilbert transform in computer electrocardiografic diagnosis; J. BMES R.O.C., vol. 5, no. 3, Spet. 1985: 39 54.
[6]     K. P. Lin and W. H. Chang; QRS feature extraction using linear prediction; IEEE Trans. Biomed. Eng.; vol. 36, no. 10, Oct. 1989: 1050-1055.
[7]     J. Nadal and R. B. Paneral; Classification of cardiac arrhythmias using principal component analysis of the ECG; in Proc. IEEE Eng. Med. And Biol. Soc. 13th Annu. Int., Conf.; 1991: 580-581.
[8]     Fredric M. Harm and Soowham Han, Classification of Cardiac Arrhythmias Using Fuzzy ARTMAP; IEEE Transactions on Biomedical Engineering, vol. 43, NO. 4, 1996: 425-430.
[9]     Howard Demuth and Mark Beale; Neural Network Toolbox. Math Work, Version 4; 2004.
[10] Rangaraj M. Rangayyan, Biomedical Signal Analysis. IEEE Press 2002: 55-91.
[11] George B. Moody; WFDB Programmer's Guide. Harvard MIT 2003:15-30.
[12] Alan V. Oppenheim, Discrete-Time Signal Processing. Prentice Hall 1999: 180-220.
[13] ECG processing using Wavelets, http://cyber.
[14] منهاج محمدباقر، هوش محاسباتی، مرکز نشر دانشگاه صنعتی امیرکبیر، 1381، 221-254.
[15] Stanislaw Osowski and Tran Hoai Linh; ECG Beat Recognition Using Fuzzy Hybrid Neural Network; IEEE Trans. Biomed, Eng., vol. 48, NO.11, Novmb 2001: 1265-1271.
[16] Y. H. Hu, W. Tompkins, J. L. Urrusti, and V. X. Alfonso; Application of artificial neural networks for ECG signal detection and classification; J. Electocardiol. Vol 26; 1994: 66-73.
[17] Y. H. Hu, S. Palerddy, and W. Tompkins; A patient adaptable ECG beat classifier using a mixture of experts approach; IEEE Trans. Biomed. Eng., vol. 44, Sept.1997: 891-900.
[18] K. Minami, H. Nakajima, and T. Toyoshima; Real time discrimination of ventricular tachyarrhythmia with Fourier transform neural network; IEEE Trans. Biomed. Eng; vol. 46; Feb. 1999: 179-18.