Automatic Arrhythmia Classification Method Using Simple Statistical Features
Citation
Khudhur A. Alfarhan, MohdYusoffMashor, Abdul Rahman MohdSaad "Automatic Arrhythmia Classification Method Using Simple Statistical Features", International Journal of Engineering Trends and Technology (IJETT), V44(3),107-111 February 2017. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group
Abstract
Arrhythmia detection and classification methods are normally involve complex procedures and it is quite hard to achieve good accuracy. Current study presents an arrhythmia detection and classification method using simple statistical features extraction methods and library support vector machine (LIBSVM) classifier. The electrocardiogram (ECG) signals for three classes, namely normal sinus rhythm (NSR), premature atrial contraction (PAC) and premature ventricle contraction (PVC) were obtained from MIT arrhythmia database. The obtained ECG signals were denoised using bandpass filter. The denoised signals were segmented into 3.34 seconds. The segmented ECG signals were normalized to prepare them for features extraction stage. The R-R intervals were calculated to extract the features from them. The features extraction methods that were used in this study are the mean absolute value (MAV) of ECG segment, root mean square (RMS) of ECG segment, the median of R-R intervals, and standard deviation (SD) of R-R intervals. The extracted features were classified using LIBSVM classifier. The achieved accuracy from this method is 98.54%. The results showed that the proposed method for arrhythmia detection and classification is accurate, simple and reasonable method comparing to the other studies.
References
[1] WHR, “Coronary Heart Disease in Malaysia,” World Health Rankings, 2014. [Online]. Available: http://www.worldlifeexpectancy.com/malaysia-coronary-heart-disease.
[2] S. W. Fei, “Diagnostic study on arrhythmia cordis based on particle swarm optimization-based support vector machine,” Expert Syst. Appl., vol. 37, no. 10, pp. 6748–6752, 2010.
[3] S. C. Bulusu, M. Faezipour, V. Ng, M. Nourani, L. S. Tamil, and S. Banerjee, “Transient ST-segment episode detection for ECG beat classification,” in Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011, 2011, pp. 121–124.
[4] M. K. Sarkaleh and A. Shahbahrami, “Classification of ECG arrhythmias Using Discrete Wavelet Transform and Neural Networks,” Int. J. Comput. Sci. Eng. Appl., vol. 2, no. 1, pp. 1–13, 2012.
[5] Z. Zhang, J. Dong, X. Luo, K. S. Choi, and X. Wu, “Heartbeat classification using disease-specific feature selection,” Comput. Biol. Med., vol. 46, no. 1, pp. 79–89, 2014.
[6] M. Pooyan and F. Akhoondi, “Accurate Detection and Cassification of Ventricular Abnormamlitiess Using Morphological Features,” J. Fundam. Appl. Sci., vol. 8, no. 3S, pp. 1659–1670, 2016.
[7] F. Buendía-Fuentes, M. a. Arnau-Vives, a. Arnau-Vives, Y. Jiménez-Jiménez, J. Rueda-Soriano, E. Zorio-Grima, a. Osa-Sáez, L. V. Martínez-Dolz, L. Almenar-Bonet, and M. a. Palencia-Pérez, “High-Bandpass Filters in Electrocardiography: Source of Error in the Interpretation of the ST Segment,” ISRN Cardiol., vol. 2012, pp. 1–10, 2012.
[8] B. S. Raghavendra, D. Bera, A. S. Bopardikar, and R. Narayanan, “Cardiac arrhythmia detection using dynamic time warping of ECG beats in e-healthcare systems,” in 2011 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks, 2011, pp. 1–6.
[9] E. Dolatabadi and S. Primak, “Ubiquitous WBAN-based electrocardiogram monitoring system,” 2011 IEEE 13th Int. Conf. e-Health Networking, Appl. Serv. Heal. 2011, pp. 110–113, 2011.
[10] S. Xue, X. Chen, Z. Fang, and S. Xia, “An ECG arrhythmia classification and heart rate variability analysis system based on android platform,” 2015 2nd Int. Symp. Futur. Inf. Commun. Technol. Ubiquitous Healthc., pp. 1–5, 2015.
[11] E. M. A. Anas, S. Y. Lee, and K. H. Hasan, “Sequential algorithm for life threatening cardiac pathologies detection based on mean signal strength and EMD functions,” Biomed. Eng. Online, pp. 1–22, 2010.
[12] J. F. Kenney and E. S. Keeping, Mathematics of Statistics, 3rd ed. Princeton, NJ: Van Nostrand, 1962.
[13] L. I. Smith, A tutorial on Principal Components Analysis Introduction, 1st ed. 2002.
[14] C. Chang and C. Lin, “LIBSVM?: A Library for Support Vector Machines,” ACM Trans. Intell. Syst. Technol., vol. 2, pp. 1–39, 2013.
[15] L. Qiao, C. Rajagopalan, and G. D. Clifford, “A machine learning approach to multi-level ECG signal quality classification,” Comput. Methods Programs Biomed., vol. 117, no. 3, pp. 435–447, 2014.
[16] S. Chen, W. Hua, Z. Li, L. Jian, and X. Gao, “Heartbeat classification using projected and dynamic features of ECG signal,” Biomed. Signal Process. Control, vol. 31, pp. 165–173, 2017.
Keywords
Electrocardiogram (ECG), Arrhythmia, LIBSVM, Statistical Features.