Comparison of Feature Reduction Methods in the Task of Arrhythmia Classification

  • Lukáš Zaorálek
  • Tomáš Peterek
  • Pavel Dohnálek
  • Petr Gajdoš
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 303)

Abstract

The main goal of the work is to test two well-known algorithms for feature transform such as Singular Value Decomposition and Principal Component Analysis in the task of arrhythmia recognition in ECG records. The original signal were transformed by these two techniques and a neural network was used for classification. Values of sensitivity and accuracy were observed and consequently compared for each transformation. Unlike in other similar works, our experiments were performed on a high number of beats and the tested database included over 47 000 experimental heart beats with different diseases.

Keywords

SVD Neural network Arrhythmias PVC PCA 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lin, C.-H., Kuo, C.-L., Chen, J.-L., Chang, W.-D.: Fractal features for car-diac arrhythmias recognition using neural network based classifier. In: International Conference on Networking, Sensing and Control, ICNSC 2009, March 26-29, pp. 930–935 (2009), doi:10.1109/ICNSC.2009.4919405Google Scholar
  2. 2.
    Osowski, S., Siroic, R., Siwek, K.: Genetic algorithm for integration of ensemble of classifiers in arrhythmia recognition. In: Instrumentation and Measurement Technology Conference, I2MTC 2009, May 5-7, pp. 1496–1500. IEEE (2009), doi:10.1109/IMTC.2009.5168692Google Scholar
  3. 3.
    Lin, C.-H., Chen, P.-J., Chen, Y.-F., Lee, Y.-Y., Chen, T.: Multiple Cardiac Arrhythmia Recognition Using Adaptive Wavelet Network. In: 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005, January 17-18, pp. 5655–5659 (2006), doi:10.1109/IEMBS.2005.1615769Google Scholar
  4. 4.
    Das, M.K., Ari, S.: ECG arrhythmia recognition using artificial neural network with S-transform based effective features. In: 2013 Annual IEEE India Conference (INDICON), December 13-15, pp. 1–6 (2013), doi:10.1109/INDCON.2013.6726153Google Scholar
  5. 5.
    Masters, T.: Practical Neural Network Recipes in C++. Academic Press, New York (1993)Google Scholar
  6. 6.
    Peterek, T., Krohova, J., Smondrk, M., Penhaker, M.: Principal component analysis and fuzzy clustering of SA HRV during the Orthostatic challenge. In: 2012 35th International Conference on Telecommunications and Signal Processing (TSP), July 3-4, pp. 596–599 (2012), doi:10.1109/TSP.2012.6256366Google Scholar
  7. 7.
    Prauzek, M., Peterek, T., Penhaker, M.: Reduction of ECG precordial leads. In: 2010 2nd International Conference on Signal Processing Systems (ICSPS), July 5-7, vol. 1, pp. V1354–V1357 (2010), doi:10.1109/ICSPS.2010.5555640Google Scholar
  8. 8.
    Moravec, P., Gajdoš, P., Snášel, V., Saeed, K.: Normalization Impact on SVD-Based Iris Recognition. In: Saeed, K., Abraham, A., Porwik, P. (eds.) Proceedings of International Conference on Biometrics and Kansei Engineering 2009, pp. 60–64. IEEE Press (2009) ISBN 978-0-7695-3692-7 Google Scholar
  9. 9.
    Shidaganti, G.I., Chickerur, S.: Rational Value Sequence based Singular Value Decomposition for facial recognition. In: 2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI), August 22-25, pp. 979–983 (2013), doi:10.1109/ICACCI.2013.6637309Google Scholar
  10. 10.
    Reddy, T.A., Devi, K.R., Gangashetty, S.V.: Nonlinear principal component analysis for seismic data compression. In: 2012 1st International Conference on Recent Advances in Information Technology (RAIT), March 15-17, pp. 927–932 (2012), doi:10.1109/RAIT.2012.6194558Google Scholar
  11. 11.
    Burke, H.B., Rosen, D.B., Goodman, P.H.: Comparing artificial neural networks to other statistical methods for medical outcome prediction. In: 1994 IEEE International Conference on Neural Networks, IEEE World Congress on Computational Intelligence, June 27-July 2, vol. 4, pp. 2213–2216 (1994), doi:10.1109/ICNN.1994.374560Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Lukáš Zaorálek
    • 1
    • 2
  • Tomáš Peterek
    • 1
  • Pavel Dohnálek
    • 1
    • 2
  • Petr Gajdoš
    • 1
    • 2
  1. 1.IT4innovationsVŠB - Technical Univesity of OstravaOstravaCzech Republic
  2. 2.Department of Computer Science, FEECSVŠB - Technical Univesity of OstravaOstravaCzech Republic

Personalised recommendations