ECG beat classification with synaptic delay based artificial neural networks

  • R. J. Duro
  • J. Santos
Methodology for Data Analysis, Task Selection and Nets Design
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1240)


In this work we present an application of Synaptic Delay Based Artificial Neural Networks to the classification of beats in ECG signal processing, both in terms of the ”shape” of the P-QRS-T complex and its position in time without any explicit windowing or thresholding process. The signal is simply introduced as it is to the network, sample by sample as time passes, and the network using internal delay terms modeling the length of the synaptic connections, learns to perform all the temporal reasoning processes required for the classification through the application of Discrete Time Backpropagation. We present an example of classification using real ECG patterns from the European ST-T Database.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fu, K.S., Syntactic Pattern Recognition. In: Handbook of Pattern Recognition and Image Processing. London, Academic Press, 1986.Google Scholar
  2. 2.
    Tartakovsky, M., Rosenberg, N., Ron, S., Shabton, I., Elkin, S., and Cocos, M., Unsupervised Template Construction for QRS Classification in Holter Type Analysis, Cornp in Cardiology, 1980: 9–13.Google Scholar
  3. 3.
    Wang, J.Y.J., Application of Pattern Recognition Techniques to QRS Complex Classification-A Review, Comp in Cardiology, 1983: 77–82.Google Scholar
  4. 4.
    Barro, S., Ruiz, R., Cabello, D., Mira, J., Algorithmic Sequential Decision-Making in the Frequency Domain for Life Threatening Ventricular Arrhythmias and Imitative Artefacts: a Diagnostic System, Jour of Biom Eng, 1989, 11: 320–328.Google Scholar
  5. 5.
    Skordalakis, E., Syntactic ECG processing: a review, Pattern Recog. 1986 19–4: 305–313.Google Scholar
  6. 6.
    Udupa, J.K., and Murthy, I., Syntactic Approach to ECG Rythm Analysis IEEE Trans BME, 1980, 27–7: 370–375.Google Scholar
  7. 7.
    Papakonstantinou, G., Skordalakis, E., and Grilzali, F., An Attribute Grammar for QRS Detection, Pattern Recog, 1986, 19:297–303.Google Scholar
  8. 8.
    Bugarín, A., Barro, S., Ruiz, R., Presedo, J., and Palacios, F., Syntactic Characterization of QRS Morphology, In: Proc. 13th Int. Conf. IEEE EMBS 1991 12–2: 588–589.Google Scholar
  9. 9.
    Fu, K.S., A Step towards Unification of Syntactic and Statistical Pattern Recognition, IEEE Trans on PAMI, 1983, 5–2: 200–205.Google Scholar
  10. 10.
    Trahanias, P., Skordalakis, E., Syntactic Pattern Recognition of the ECG, IEEE Trans PAMI, 1990, 12–7: 648–657.Google Scholar
  11. 11.
    Vila, J.A., Presedo, J., Bugarín A., Barro, S., Ruiz, R., and Palacios, F., Application of Syntactic Processing to ECG Analysis, Proc. Twelfth International Congress of the European Federation for Medical Informatics, MIE94, 1994: 579–584.Google Scholar
  12. 12.
    Taddei, A., Bragini, A., Distante, G., ...The European ST/T Database: Development, Distribution and Use, Computers in Cardiology, 1990, 17: 177–180.Google Scholar
  13. 13.
    Day, S.P., and Davenport, M.R., Continuous Time Temporal Backpropagation with Adaptable Time Delays, IEEE Trans. on Neural Networks, 1993, 4–2: 348–354.Google Scholar
  14. 14.
    Duro, R.J., Santos, J., Fast Discrete Time Backpropagation for Adaptive Synaptic Delay Based Neural Networks, Submitted for publication in IEEE Trans. on Neural Networks.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • R. J. Duro
    • 1
  • J. Santos
    • 2
  1. 1.Departamento de Ingeniería IndustrialUniversidade da Coruña. Escuela Politécnica SuperiorFerrol (La Coruña)Spain
  2. 2.Departamento de ComputationUniversidade da Coruña. Facultade de InformáticaLa CorunaSpain

Personalised recommendations