Cover
Vol. 4 No. 1 (2008)

Published: September 30, 2008

Pages: 86-91

Original Article

ECG SIGNAL RECOGNITION BASED ON WAVELET TRANSFORM USING NEURAL NETWORKS AND FUZZY SYSTEMS

Abstract

This work presents aneural and fuzzy based ECG signal recognition system based on wavelet transform. The suitable coefficients that can be used as a feature for each fuzzy network or neural network is found using a proposed best basis technique. Using the proposed best bases reduces the dimension of the input vector and hence reduces the complexity of the classifier. The fuzzy network and the neural network parameters are learned using back propagation algorithm.

References

  1. Ganong W.F., ”Review of medical physiology”, Prentice Hall, Thirteen Edition, 1987.
  2. Olmez T. and Dokur Z., “Application of Neural Computing & Applications, Vol. 11, pp. 144-155, 2003.
  3. Papaloukas S., Fotiadis D.I., Likas A., and Michail L.K., ”An ischemia detection method based on artificial neural networks”, Artificial Intelligence in medicine, Elsevier Science, Vol. 24, pp.167-178, Feb. 2002.
  4. Pektatil R., Ozbay Y., Ceylan M., and Karlik B., “Classification of ECG Signals using Fuzzy Clustering neural networks”, Proceeding of Turkish Symposium on artificial intelligence and neural networks, Vol. 1, pp. 105-108, July 2003.
  5. Prasad, and Sahambi J.S., “Classification of ECG Arrhythmias using Multi-Resolution Analysis and Neural Networks”, IEEE Trans., Biomed. Eng.., Vol. 1, pp. 227-231, 2003.
  6. Wieben O., Tompkins W.J., and Afonso V.X., “Classification of PVCs with a fuzzy logic system”, IEEE) Proceedings - 19th International Conference - IEEE/EMBS, pp. 65-67, Chicago, IL. USA Oct 1997.