Support Vector Machine Based Arrhythmia Classification Using Reduced Features

  • Song, Mi-Hye (Department of Biomedical Engineering, College of Health Science, Center for Emergency Medical Informatics (CEMI), Yonsei University) ;
  • Lee, Jeon (Department of Biomedical Engineering, College of Health Science, Center for Emergency Medical Informatics (CEMI), Yonsei University) ;
  • Cho, Sung-Pil (Department of Biomedical Engineering, College of Health Science, Center for Emergency Medical Informatics (CEMI), Yonsei University) ;
  • Lee, Kyoung-Joung (Department of Biomedical Engineering, College of Health Science, Center for Emergency Medical Informatics (CEMI), Yonsei University) ;
  • Yoo, Sun-Kook (Department of Medical Engineering, Center for Emergency Medical Informatics, College of Medicine, Yonsei University)
  • Published : 2005.12.01

Abstract

In this paper, we proposed an algorithm for arrhythmia classification, which is associated with the reduction of feature dimensions by linear discriminant analysis (LDA) and a support vector machine (SVM) based classifier. Seventeen original input features were extracted from preprocessed signals by wavelet transform, and attempts were then made to reduce these to 4 features, the linear combination of original features, by LDA. The performance of the SVM classifier with reduced features by LDA showed higher than with that by principal component analysis (PCA) and even with original features. For a cross-validation procedure, this SVM classifier was compared with Multilayer Perceptrons (MLP) and Fuzzy Inference System (FIS) classifiers. When all classifiers used the same reduced features, the overall performance of the SVM classifier was comprehensively superior to all others. Especially, the accuracy of discrimination of normal sinus rhythm (NSR), arterial premature contraction (APC), supraventricular tachycardia (SVT), premature ventricular contraction (PVC), ventricular tachycardia (VT) and ventricular fibrillation (VF) were $99.307\%,\;99.274\%,\;99.854\%,\;98.344\%,\;99.441\%\;and\;99.883\%$, respectively. And, even with smaller learning data, the SVM classifier offered better performance than the MLP classifier.

Keywords

References

  1. Y. H. Hu, S. Palreddy, and W. Tomkins, 'A patient adaptable ECG beat classification using a mixture of experts approach,' IEEE Trans. Biomed. Eng., vol. 44, no. 9, pp. 891-900, September 1997 https://doi.org/10.1109/10.623058
  2. Y. H. Hu, W. Tomkins, J. L. Urrusti, and V. X. Alfonso, 'Applications of artificial neural networks for ECG signal detection and classification,' Electrocardiology, vol. 24, pp. 123-129, 1994
  3. K. Minami, H. Nakajima, and T. Yoyoshima, 'Real time discrimination of the ventricular tachyarrhythmia with Fourier-transform neural network,' IEEE Trans. Biomed. Eng., vol. 46, no. 2, pp. 179-185, 1999 https://doi.org/10.1109/10.740880
  4. G. E. Oien, N. A. Bertelsen, T. Eftestol, and J. H. Husoy, 'ECG rhythm classification using artificial neural networks,' Proc. of the IEEE Digital Signal Processing Workshop, pp. 514- 517, 1996
  5. T. Sugiura, H. Hirata, Y. Harada, and T. Kazui, 'Automatic discrimination of arrhythmia waveforms using fuzzy logic,' Proc. of the IEEE Engineering in Medical and Biology Society, vol. 20, no. 1, pp. 108-111, 1998
  6. L. Y. Shyu, Y. H. Wu, and W. Hu, 'Using wavelet transform and fuzzy neural network for VPC detection from the Holter ECG,' IEEE Trans. Biomed. Eng., vol. 51, no. 7, pp. 1269-1273, 2004 https://doi.org/10.1109/TBME.2004.824131
  7. R. Schalkoff, Pattern Recognition: Statistical, Structural and Neural Approaches, Wiley, New York ,1992
  8. S. Kadambe, R. Murray, and G. F. B. Bartels, 'Wavelet transform-based QRS complex detector,' IEEE Trans. Biomed. Eng., vol. 46, no. 7, pp. 838-848, July 1999 https://doi.org/10.1109/10.771194
  9. K. L. Park, K. J. Lee, and H. R. Yoon, 'Application of a wavelet adaptive filter to minimize distortion of the ST-segment,' Med. And Biol. Eng. and Computing, vol. 36, no. 5, pp. 581-586, 1998 https://doi.org/10.1007/BF02524427
  10. H. C. Kim, D. J. Kim, and S. Y. Bang, 'Face recognition using LDA mixture model,' Proc. of the Pattern Recognition, vol. 2, pp. 925-928, 2002
  11. A. M. Martinez and A. C. Kak, 'PCA versus LDA,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp. 228-233, 2001 https://doi.org/10.1109/34.908974
  12. A. Smola and B. Scholkopf, 'A tutorial on support vector regression,' NeuroColt Tech. Rep. NV2-TR-1998-030, Royal Holloway College, Univ. London, London, U. K., 1998
  13. O. L. Mangasarian, 'Lagrangian support vector machines,' J. Machine Learning Res., vol. 1, pp. 161-177, 2001 https://doi.org/10.1162/15324430152748218
  14. J. Platt, 'Fast training of SVM using sequential optimization,' Advances in Kernel Methods- Support Vector Learning, B. Scholkpf, C. Burges, and A. Smola, Eds. Cambridge, MIT Press, U.K., pp. 185-208, 1998
  15. C. Burges, 'A tutorial on support vector machines for pattern recognition,' Knowledge Discovery and Data Mining, U. Fayyad, Ed. Norwell, Kluwer, MA, pp. 1-43, 2000
  16. K. Crammer and Y. Singer, 'On the learn ability and design of output codes for multi-class problems,' Proc. 13th Conf. Computational Learning Theory, pp. 35-46, 2000
  17. C. W. Hsu and C. J. Lin, A Comparison of Methods for Mmulti-class Support Vector Machines, Nat. Taiwan Univ., Taiwan, 2000