Abstract
Correct and accurate classification of ECG patterns in a long-term record requires optimal selection of feature vector. We propose a machine learning algorithm that learns from short randomly selected signal strips and, having an approval from a human operator, classifies all remaining patterns. We applied a genetic algorithm with aggressive mutation to select few most distinctive features of ECG signal. When applied to the MIT-BIH Arrhythmia Database records, the algorithm reduced the initial feature space of 57 elements to 3–5 features optimized for a particular subject. We also observe a significant reduction of misclassified beats percentage (from 2.7 % to 0.7 % in average for SVM classifier and three features) with regard to automatic correlation-based selection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Augustyniak, P.: The use of shape factors for heart beats classification in holterrecordings. Proc. Comput. Med. Zakop. 2–6(05), 47–52 (1997)
Augustyniak, P.: Adaptive discrete ECG representation—comparing variable depth decimation and continuous non-uniform sampling. Comput. Cardiol. 29, 165–168 (2005)
Augustyniak, P.: Wearable wireless heart rate monitor for continuous long-term variability studies. J. Electrocardiol. 44(2), 195–200 (2011)
Chang, K.C., Lee, R.G., Wen, C., Yeh, M.F.: Comparison of similarity measures for clustering electrocardiogram complexes. Comput. Cardiol. 32, 759–762 (2005)
de Chazal, P., O’Dwyer, M., Reilly, R.B.: Automatic classification of heartbeats using ecg morphology and heartbeat interval features. IEEE Trans. Biomed. Eng. 51(7), 1196–1206 (2004)
Holland, J.H., Reitman, J.S.: Cognitive systems based on adaptive algorithms. ACM SIGART Bull. 63, 43–49 (1977)
Jaworek, J., Augustyniak, P.: A cardiac telerehabilitation application for mobile devices. Comput. Cardiol. 38, 241–244 (2011)
Jokić, S., Krčo, S., Delić, V., Sakač, D., Lukić, Z., Loncar-Turukalo, T.: An efficient approach for heartbeat classification. Comput. Cardiol. 2010(37), 991–994 (2010)
Kittler, J.: Feature set search algorithms. In: Pattern Recognition and Signal Processing, pp. 41–60. Sijthoff and Noordhoff, Alphen aan den Rijn (1978)
Kononenko, I.: Estimating attributes: analysis and extensions of relief. In: De Raedt, L., Bergadano, F. (eds.) Machine Learning: ECML-94, pp. 171–182. Springer, Berlin (1994)
Lemay, M., Jacquemet, V., Forclaz, A., Vesin, J.M., Kappenberger, L.: Spatiotemporal QRST cancellation method using separate QRS and T-Waves templates. Comput. Cardiol. 32, 611–614 (2005)
Llamedo-Soria, M., Martinez, J.P.: An ECG classification model based on multilead wavelet transform features. Comput. Cardiol. 34, 105–108 (2007)
Llamedo-Soria, M., Martinez, J.P.: Analysis of multidoma in features for ECG classification. Comput. Cardiol. 36, 561–564 (2009)
Llamedo, M., Khwaja, A., Martinez, J.P.: Analysis of 12-lead classification models for ECG classification. Comput. Cardiol. 37, 673–676 (2010)
Llamedo, M., Martinez, J.: Heartbeat classification using feature selection driven by database generalization criteria. IEEE Trans. Biomed. Eng. 58(3), 616–625 (2011)
MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: Le Cam, L.M., Neyman, J. (eds.) Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, pp. 281–297. University of California Press, Berkeley (1967)
Mallat, S., Zhong, S.: Characterization of signals from multiscale edges. IEEE Trans. Pattern Anal. Mach. Intell. 14(7), 710–732 (1992)
Mensing, S., Bystricky, W., Safer, A.: Identifying and measuring representative QT intervals in predominantly non-normal ECGs. Comput. Cardiol. 33, 361–364 (2006)
Moody, G.B.: The MIT-BIH Arrhythmia Database CD-ROM, 3rd Edn. Harvard-MIT Division of Health Sciences and Technology, Cambridge (1997)
O’Dwyer, M., de Chazal, P., Reilly, R.I.: Beat classification for use in arrhythmia analysis. Comput. Cardiol. 27, 395–398 (2000)
Rejer, I.: Genetic algorithms in EEG feature selection for the classification of movements of the left and right hand. In: Proceedings CORES2013, pp. 579–589 (2013). doi:10.1007/978-3-319-00969-8-57
Rejer, I.: Genetic algorithm with aggressive mutation for feature selection in BCI feature space pattern. Anal. Appl. (2014). doi:10.1007/s10044-014-0425-3
Rodriguez-Sotelo, J.L., Cuesta-Frau, D., Castellanos-Dominguez, G.: An improved method for unsupervised analysis of ECG beats based on WT features and J-Means clustering. Comput. Cardiol. 34, 581–584 (2007)
Tibshirani, R.: Regression shrinkage and selection via thelasso. J. Stat. Soc. Ser. B 58(1), 267–288 (1996)
Vansteenkiste, E., Houben, R., Pizurica, A., Philips, W.: Classifying electrocardiogram peaks using new wavelet domain features. Comput. Cardiol. 35, 853–856 (2008)
Vapnik, V.N.: The Nature Of Statistical Learning Theory. Springer, New York (1995)
Acknowledgments
This scientific work is supported by the AGH University of Science and Technology in year 2015 as a research project No. 11.11.120.612.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Augustyniak, P. (2016). Accurate Classification of ECG Patterns with Subject-Dependent Feature Vector. In: Burduk, R., Jackowski, K., Kurzyński, M., Woźniak, M., Żołnierek, A. (eds) Proceedings of the 9th International Conference on Computer Recognition Systems CORES 2015. Advances in Intelligent Systems and Computing, vol 403. Springer, Cham. https://doi.org/10.1007/978-3-319-26227-7_50
Download citation
DOI: https://doi.org/10.1007/978-3-319-26227-7_50
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26225-3
Online ISBN: 978-3-319-26227-7
eBook Packages: EngineeringEngineering (R0)