Advertisement

The application of wavelet and feature vectors to ECG signals

  • A. Matsuyama
  • M. Jonkman
Scientific Papers

Abstract

TheElectrocardiogram (ECG) is one of the most commonly known biological signals. Traditionally ECG recordings are analysed in the time-domain by skilled physicians. However, pathological conditions may not always be obvious in the original time-domain signal. Fourier analysis provides frequency information but has the disadvantage that time characteristics will be lost. Wavelet analysis, which provides both time and frequency information, can overcome this limitation. Here a new method, the combination of wavelet analysis and feature vectors, is applied with the intent to investigate its suitability as a diagnostic tool. ECG signals with normal and abnormal beats were examined. There were two stages in analysing ECG signals: feature extraction and feature classification. To extract features from ECG signals, wavelet decomposition was first applied and feature vectors of normalised energy and entropy were constructed. These feature vectors were used to classify signals. The results showed that normal beats and abnormal beats composed different clusters in most cases. In conclusion, the combination of wavelet transform and feature vectors has shown potential in detecting abnormalities in an ECG recording. It was also found that normalised energy and entropy are features, which are suitable for classification of ECG signals.

Key words

ECG wavelet normalised energy vector quantisation feature vector 

Reference

  1. 1.
    Valens, C.,A Really Friendly Guide to Wavelet, 1999. http://perso.wanadoo.fr/polyvalens/clemens/wavelets/ wavelets.htmlGoogle Scholar
  2. 2.
    Prasad, G. K. and Sahambi, J. S.,Classification of ECG arrhythmias using multi-resolution analysis and neural networks, Proceedings of the Conference on Convergent Technologies for Asia-Pacific Region 2003, 221:227–231, 2003.Google Scholar
  3. 3.
    Castro, B., Kogan, D., and Geva, A. B.,ECG feature extraction using optimal mother wavelet, Proceedings of the 21st IEEE Convention of the Electrical and Electronic Engineers in Israel 2000, 346–350, 2000.Google Scholar
  4. 4.
    Senhadji, L., Bellanger, J. J., Carrault, G., and Coatrieux, J. L.,Wavelet Analysis of E.C.G. Signals, Proceedings of the Twelfth Annual International Conference of IEEE, 811–812, 1990.Google Scholar
  5. 5.
    Provaznik, I. and Kozumplik, J.,Wavelet Transform in Electrocardiography-Data Compression, International Journal of Medical Informatics, 45:111–128, 1997.CrossRefPubMedGoogle Scholar
  6. 6.
    Bojanic, D. and Popovic, D. B.,QRS detection from an ongoing ECG recordings by using dyadic wavelets, Proceedings of EMBEC 02, 2002.Google Scholar
  7. 7.
    Schlegelmilch, F., Helbig, M., Natchkova, V., Ivanova, G., Schellhorn, K., Detschew, V., Mandler, D., and GrieBbach, G.,A Multi-Channel Approach for Online-Identification of QRS-Regions Using Adaptive Recursive Estimators, Proceedings of EMBEC 02, 568–569, 2002.Google Scholar
  8. 8.
    Mousa, A. and Yimaz, A.,Neural network detection of ventricular late potentials in ECG signals using wavelet transform extracted parameters, Proceedings of the 23rd Annual International Conference of the IEEE 2001, 1662:1668–1671, 2001.Google Scholar
  9. 9.
    Stamkopoulos, T., Diamantaras, K., Maglaveras, N., and Strintzis, M.,ECG analysis using nonlinear PCA neural networks for ischemia detection, IEEE Transactions on Signal Processing, 46:3058–3067, 1998.CrossRefGoogle Scholar
  10. 10.
    Szilagyi, S. M., Szilagyi, L., and David, L.,Comparison between neural-network-based adaptive filtering and wavelet transform for ECG characteristic points detection. Proceedings of the 19th Annual International Conference of the IEEE 1997, 272–274, 1997.Google Scholar
  11. 11.
    Kuppuraj, R. N.,A neural network system to classify simulated ECG rhythms, Proceedings of the Twelfth Southern 1993, 1–3, 1993.Google Scholar
  12. 12.
    Al-Nashash, H., Colaco, A., and El-Itawi, G.,ECG Arrhythmia Classification Using FFT, Wavelets and Neural Networks, Proceedings of EMBEC 02, 566–567, 2002.Google Scholar
  13. 13.
    Ogunbona, P. O., Milliss, M., De Bore, F., and Fernandes, M.,Classification of Gas Metal Arc Welds Using Wavelets, Proceedings of the Engineering Mathematics and Applications Conference, 383–386, 1998.Google Scholar
  14. 14.
    Misiti, M., Misiti, Y., Oppenheim, G., and Poggi, J. M.,Wavelet Toolbox User’s Guide, Mathwork, 2000.Google Scholar
  15. 15.
    PhysioBank, Physionet, http://www.physionet.org/physiobank/Google Scholar

Copyright information

© Australasian College of Physical Scientists and Engineers in Medicine 2006

Authors and Affiliations

  1. 1.School of Engineering and Logistics, Faculty of TechnologyCharles Darwin UniversityDarwinAustralia

Personalised recommendations