Weighted SVMs and Feature Relevance Assessment in Supervised Heart Beat Classification
The diagnosis of cardiac dysfunctions requires the analysis of long-term ECG signal recordings, often containing hundreds to thousands of heart beats. In this work, automatic inter-patient classification of heart beats following AAMI guidelines is investigated. The prior of the normal class is by far larger than the other classes, and the classifier obtained by a standard SVM training is likely to act as the trivial acceptor. To avoid this inconvenience, a SVM classifier optimizing a convex approximation of the balanced classification rate rather than the standard accuracy is used. First, the assessment of feature sets previously proposed in the litterature is investigated. Second, the performances of this SVM model is compared to those of previously reported inter-patient classification models. The results show that the choice of the features is of major importance, and that some previously reported feature sets do not serve the classification performances. Also, the weighted SVM model with the best feature set selection achieves results better than previously reported inter-patient models with features extracted only from the R spike annotations.
KeywordsSupport Vector Machine Heart Beat Support Vector Machine Model High Order Statistic Normal Beat
Unable to display preview. Download preview PDF.
- 1.Association for the Advancement of Medical Instrumentation, Testing and reporting performance results of cardiac rhythm and st segment measurement algorithms. ANSI/AAMI EC38:1998 (1998)Google Scholar
- 2.Callut, J., Dupont, P.: Fβ Support Vector Machines. In: Proceeding of International Joint Conference on Neural Networks, Montreal, Canada, July 31-August 4, pp. 1443–1448 (2005)Google Scholar
- 4.Cheng, W., Chan, K.: Classification of electrocardiogram using hidden markov models. In: Proceedings of the 20th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society, vol. 1, pp. 143–146 (1998)Google Scholar
- 6.Clifford, G.D., Azuaje, F., McSharry, P.: Advanced Methods And Tools for ECG Data Analysis. Artech House, Inc., Norwood (2006)Google Scholar
- 7.François, D.: Feature selection. In: Wang, J. (ed.) Encyclopedia of Data Mining and Warehousing, 2nd edn. Information Science Reference (2008)Google Scholar
- 8.Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P.C., Mark, R., Mietus, J., Moody, G., Peng, C.-K., Stanley, H.: PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)Google Scholar
- 10.Huang, Y., Du, S.: Proceeding of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, August 18-21, pp. 4365–4369 (2005)Google Scholar
- 15.Park, K., Cho, B., Lee, D., Song, S., Lee, J., Chee, Y., Kim, I., Kim, S.: Hierarchical support vector machine based heartbeat classification using higher order statistics and hermite basis function. In: Computers in Cardiology, pp. 229–232 (2008)Google Scholar
- 16.Platt, J.C.: Fast training of support vector machines using sequential minimal optimization. In: Scholkopf, B., Burges, C., Smola, A. (eds.) Advances in Kernel Methods. MIT Press, Cambridge (1999)Google Scholar
- 17.Soria, M., Martinez, J.P.: An ECG classification model based on multilead wavelet transform features. In: Computers in Cardiology, pp. 105–108 (2007)Google Scholar
- 18.Vapnik, V.N.: The Nature of Statistical Learning Theory (Information Science and Statistics). Springer, Heidelberg (1999)Google Scholar