Novel ECG Signal Classification Based on KICA Nonlinear Feature Extraction
- 655 Downloads
Electrocardiogram (ECG) signal feature extraction is important in diagnosing cardiovascular diseases. This paper presents a new method for nonlinear feature extraction of ECG signals by combining principal component analysis (PCA) and kernel independent component analysis (KICA). The proposed method first uses PCA to decrease the dimensions of the ECG signal training set and then employs KICA to calculate the feature space for extracting the nonlinear features. Support vector machine (SVM) is utilized to determine the nonlinear features of the ECG signal classification. Genetic algorithm is also used to optimize the SVM parameters. The proposed method is advantageous because it does not require a huge amount of sampling data, and this technique is better than traditional strategies to select optimal features in the multi-domain feature space. Computer simulations reveal that the proposed method yields more satisfactory classification results on the MIT–BIH arrhythmia database, reaching an overall accuracy of 97.78 %.
KeywordsECG signal Feature extraction Principal component analysis Kernel independent component analysis Classification Support vector machine
This paper was supported by the National Natural Science Foundation of China (Nos. 61177078, 61307094, 31271871), the Specialized Research Fund for the Doctoral Program of Higher Education of China (No. 20101201120001), and Tianjin Research Program of Application Foundation and Advanced Technology (No. 13JCYBJC16800).
- 3.G. Biagetti, P. Crippa, A. Curzi, S. Orcioni, C. Turchetti, A multi-class ECG beat classifier based on the truncated KLT representation. in Proceedings of the 2014 UKSim-AMSS 8th European Modelling Symposium (EMS), pp. 93–98 (2014)Google Scholar
- 4.C.C. Chang, C.J. Lin, LIBSVM: a library for support vector machines. ACM TIST 2(3), 27 (2011)Google Scholar
- 5.P. Crippa et al., Multi-class ECG beat classification based on a Gaussian mixture model of Karhunen-Loève transform. Int. J. Simul. Syst. Sci. Tech. (accepted)Google Scholar
- 9.M. Kallas, C. Francis, L. Kanaan, D. Merheb, P. Honeine, H. Amoud, Multi-class SVM classification combined with kernel PCA feature extraction of ECG signals. in 2012 19th International Conference on Telecommunication (ICT), pp. 1–5 (2012)Google Scholar
- 16.M.C. Nait-Hamoud, A. Moussaoui, Two novel methods for multiclass ECG arrhythmias classification based on PCA, fuzzy support vector machine and unbalanced clustering. in IEEE proceedings of International Conference on Machine and Web Intelligence (ICMWI), pp. 140–145 (2010)Google Scholar
- 17.X. Qu, W.J. Cai, D.F. Ge, ECG signal classification based on BPNN. in IEEE Proceedings of International Conference on Electric Information and Control Engineering (ICEICE), pp. 1362–1364 (2011)Google Scholar