An Efficient Method Of ECG Beats Feature Extraction/Classification With Multiclass SVM Error Correcting Output Codes

Document Type : Original Article

Authors

1 Computer Science & Eng. Dept., Faculty of Electronic Eng., Menoufia University.

2 Department of Computer Science, University of Malakand, Pakistan

3 Department of Computer Science, University of Malakand, Pakistan.

4 Electronic & Comm. Eng. Dept., Faculty of Electronic Eng., Menoufia University.

Abstract

This paper presents an efficient algorithm for classifying the ECG beats to the main four types. These types are normal beat (normal), Left Bundle Branch Block beats (LBBB), Right Bundle Branch Block beats (RBBB), Atrial Premature Contraction (APC). Feature extraction is performed from each type using Legendre moments as a tool for characterizing the signal beats. A Multiclass Support Vector Machine (multiclass SVM) is used for the classification on process with Legendre polynomial coefficients as inputs. A comparison study is presented between the proposed and some existing approaches. Simulation results reveal that the proposed approach gives 97.7% accuracy levels compared to 95.7447%, 95.88%, 95.03% , 93.40%, 96.02%, 95.95%, 96.24% achieved with Discrete wavelet (DWT), Haar wavelet and principle component analysis (PCA) as feature extractors and ANN, Simple Logic Random Forest, LibSVM and J48 as classifiers.

Keywords


0px; "> [1] “ECG (Electrocardiogram).” [Online]. Available:
https://choosingwiselycanada.org/ecg-electrocardiogram/. [Accessed: 28-
Feb-2018].
[2] M. H. Song, J. Lee, S. P. Cho, K. J. Lee, and S. K. Yoo, “Support vector
machine based arrhythmia classification using reduced features,” Int. J.
Control Autom. Syst., vol. 3, no. 4, p. 571, 2005.
[3] D. Sambhu, A. C. Umesh, Automatic Classification of ECG Signals with
Features Extracted Using Wavelet Transform and Support Vector Machines,
rd-spacing: 0px; -webkit-text-size-adj” International Journal of Advanced Research in Electrical, Electronics and
Instrumentation Engineering , Vol. 2, Special Issue 1, PP. 235-241,
December 2013
[4] A. Khalil and H. Khalil, “Classification of ECG Signals Using Legendre
Moments Classification of ECG Signals Using Legendre Moments,” Vol.
1, No. 3, 2015, pp. 284-291 January, 2015.
[5] Q. Zhao, “Feature Extraction and Classification Using Wavelet Transform
and Support Vector Machines,” International Conference on Neural
Networks and Brain, ICNN&B '05, pp. 1089–1092, 13-15 Oct. 2005..
[6] K. S. Sayed, A. F. Khalaf, and Y. M. Kadah, “Arrhythmia classification
based on novel distance series transform of phase space trajectories,”
ConfProc IEEE Eng Med BiolSoc pp. 5195–5198, Milan, Italy, 25-
29 August 2015.
[7] J.-S. Wang, W.-C. Chiang, Y.-L. Hsu, and Y.-T. C. Yang, “ECG arrhythmia
classification using a probabilistic neural network with a feature reduction
method,” Neurocomputing, vol. 116, pp. 38–45, 2013.
[8] M. K. Das and S. Ari, “ECG Beats Classification Using Mixture of
Features,” Int. Sch. Res. Not., vol. 2014, pp. 1–12, 2014.
[9] M. R. Teague, “Image analysis via the general theory of moments,” J. Opt.
Soc. Am., vol. 70, no. 8, pp. 920–930, 1980.
[10]Taha E. Taha, Ayman El-Sayed, Salma R. El-Soudy,“A Survey on
Classification of ECG Signal Study,” Communications on Applied
Electronics,Vol.6 – No.5, 2016.
[11]S. R. Kumari and P. R. Kumar, “Cardiac Arrhythmia Prediction Using
Improved Multilayer Perceptron Neural Network,” Int. J. Electron. Commun.
Instrum. Eng. Res. Dev., vol. 3, no. 4, pp. 73–80, 2013.
[12]“MIT-BIH Database.” [Online]. Available:
http://www.physionet.org/physiobank/database/nstdb/. [Accessed: 01-Dec-
2016].
[13]J. Pan and W. J. Tompkins, “A real-time QRS detection algorithm.,” IEEE
Trans. Biomed. Eng., vol. 32, no. 3, pp. 230–236, 1985.
[14]V. Vapnik, The nature of statistical learning theory. Springer science &
business media, 2013.
[15]T. G. Dietterich and G. Bakiri, “Solving multiclass learning problems via
error-correcting output codes,” Journal of artificial intelligence research, vol.
2, pp. 263–286, 1994.
[16]E. D. Übeyli, “ECG beats classification using multiclass support vector
machines with error correcting output codes,” Digit. Signal Process. A Rev.
J., vol. 17, no. 3, pp. 675–684, 2007.
[17]P. Laguna, G. B. Moody, R. Jané, P. Caminal, and R. G. Mark, “KarhunenLoève transform as a tool to analyze the ST-segment. Comparison with QT
interval.,”, Journal of Electrocardiogy, vol. 28, pp. 41–49, 1995.
[18]“Github.” [Online]. Available: https://github.com/. [Accessed: 22-Dec-2017].