Hybrid System for Cardiac Arrhythmia Classification with Fuzzy K-Nearest Neighbors and Neural Networks Combined by a Fuzzy Inference System

  • Eduardo Ramírez
  • Oscar Castillo
  • José Soria
Part of the Studies in Computational Intelligence book series (SCI, volume 312)

Abstract

In this paper we describe a hybrid architecture for classification of cardiac arrhythmias taking as a source the ECG records MIT-BIH Arrhythmia database. The Samples were taken from the LBBB, RBBB, PVC and Fusion Paced and Normal arrhythmias, as well as the normal heartbeats. These were segmented and transformation and 3 methods of classification were used: Fuzzy KNN, Multi Layer Perceptron with Gradient Descent and momentum Backpropagation and Multi Layer Perceptron with Scaled Conjugate Gradient Backpropagation. Finally, we used a Mamdani type fuzzy inference system to combine the outputs of each classifier, and we achieved a very high classification rate of 98%.

Keywords

Fuzzy KNN Mamdani Fuzzy System Neural Network Arrhythmia Classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Acharya, Kumar, Bhat: Classification of cardiac abnormalities using heart rate signals. Medical & Biological Enginnering & Computing (2004)Google Scholar
  2. 2.
    Alzate, A., Giraldo, E.: Clasificación de Arritmias utilizando ANFIS, Redes Neuronales y Agrupamiento Substractivo (2006)Google Scholar
  3. 3.
    Kulkarni, A.: Computer Vision and Fuzzy-Neural Systems, PH PTRGoogle Scholar
  4. 4.
    Azam, F.: Biologically Inspired Modular Neural Networks, Electrical and Computer Engineering. Blacksburg, Virginia (2004)Google Scholar
  5. 5.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1996)MATHGoogle Scholar
  6. 6.
    del Brío, B.M., Molina, A.S., Neuronales, R., Borrosos, S.: 3a Edición, Alfaomega Ra-Ma (2007)Google Scholar
  7. 7.
    Anuradha, B., Suresh Kumar, K., Veera Reddy, V.C.: Classification of Cardiac Signals using Time Domain Methods (2008)Google Scholar
  8. 8.
    Anuradha, B., Veera Reddy, V.C.: ANN for Classification of Cardiac Arrhythimias (2008)Google Scholar
  9. 9.
    Chuang, C.: Using Discrete Wavelet Transform of ECG Signals for Personal Identity Verification (2005)Google Scholar
  10. 10.
    Patra, D., Das, M.K., Pradhan, S.: Integration of Fcm, Pca and Neural Networks for Classification of Ecg Arrhythmias (2009)Google Scholar
  11. 11.
    Fahlman, S.: Faster Learning Variations of Backpropagation: An Empirical Study. In: Touretzky, D.S., Hinton, G.E., Sejnowski, T.J. (eds.) Proceedings of the 1988 Connectionist Models Summer School. Morgan Kaufmann Publishers, Los Altos (1988)Google Scholar
  12. 12.
    Freeman, J.A.: Simulating Neural Networks with Mathematica. Addison-Wesley, Reading (1994)Google Scholar
  13. 13.
    Clifford, G., Azuaje, F., McSharry, P.: Advanced Methods and Tools for ECG Data Analysis. Engineering Medicine & Biology. Artech House, Boston-London (2006)Google Scholar
  14. 14.
    Heart Health, National Geographic, http://yourtotalhealth.ivillage.com/
  15. 15.
    Nabney, I.T., Evans, D.J., Tenner, J., Gamlyn, L.: Benchmarking Beat Classification AlgorithmsGoogle Scholar
  16. 16.
    Pan, J., Tompkins, W.J.: A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. (1985)Google Scholar
  17. 17.
    Keller, J.M., Gray, M.R., Givens Jr., J.A.: A Fuzzy K-Nearest Neighbor Algorithm (1985)Google Scholar
  18. 18.
    Jang, J.-S.R., Sum, C.-T., Mizutani, E.: Neuro-Fuzzy and Soft Computing. Prentice-Hall, Englewood Cliffs (1997)Google Scholar
  19. 19.
    Khadra, Al-Fahoum, Al-Nashash: Detection of life-threatening cardiac arrhythmias using wavelets transformation. Med. Biol. Eng. Comput. (1997)Google Scholar
  20. 20.
    Barbosa, L., Kleisinger, G.H., Valdez, A.D., Monzón, J.E.: Utilización del Modelo Kohonen y del Perceptrón Multicapa para detectar Arritmias Cardiacas (2001)Google Scholar
  21. 21.
    Tsipouras, M., Fotiadis, D.: An Efficient System for the Detection of Arrhythmic Segments in ECG Recordings based on non-Linear Features of the RR Interval Signal (September 2003)Google Scholar
  22. 22.
    Engin, M.: ECG Beat Classification using neuro-fuzzy network. Elsevier, Amsterdam (2004)Google Scholar
  23. 23.
    Cepek, M., Chudácek, V., Petrik, M., Geogoulas, G., Stylios, C., Lhotská, L.: Comparison of Inductive Modeling Method to other Classification Methods for Holter ECGGoogle Scholar
  24. 24.
    MIT-BIH Arrhythmia Database. PhysioBank, Physiologic Signal Archives for Biomedical Research, http://www.physionet.org/physiobank/database/mitdb/
  25. 25.
    O’ Dwyer, M., de Chazal, P., Reilly, R.B.: Beat Classification for Use in Arrhythmia Analysis (2000)Google Scholar
  26. 26.
    Maglaveras, N., Stamkopoulos, T., Diamantaras, K., Pappas, C., Strintzis, M.: ECG pattern recognition and classification using non-linear transformations and neural networks (1998)Google Scholar
  27. 27.
    Belgacem, N., Chikh, M.A., Bereksi Reguig, F.: Supervised Classification of ECG using Neural NetworksGoogle Scholar
  28. 28.
    Neural Network for Mathematica, Wolfram Research Inc., Chicago, IL (2003)Google Scholar
  29. 29.
    de Chazal, P., Reilly, R.B.: Automatic Classification of ECG Beats using Wareform Shape and Heart Beat Interval Features (1998)Google Scholar
  30. 30.
    Ceylan, R., Ozbay, Y., Karlik, B.: A novel approach for classification of ECG arrhythmias: Type-2 fuzzy clustering neural network (2009)Google Scholar
  31. 31.
    Rogal, S., Paraiso, E., Kaestner, C., Figueredo, M., Neto, A.: Agrupamiento de Arritmias Cardiacas Utilizando ART2 (2008)Google Scholar
  32. 32.
    Reghav, S., Amit, K.: Fractal Feature Based ECG Arrhythmia Classification (November 2008)Google Scholar
  33. 33.
    Mehta, S.S., Lingayat, N.S.: Identification of QRS Complexes in 12-lead Electrocardiogram. Elsevier, Amsterdam (2009)Google Scholar
  34. 34.
    Ari, S., Saha, G.: In Search of an optimization technique for Artificial Neuronal Network to Classify abnormal heart sounds (2009)Google Scholar
  35. 35.
    Samarasinghe, S.: Neural Networks for Applied Science and Engineering. Auerback Publications (2007)Google Scholar
  36. 36.
    Sun, Y., Chan, K.: Arrhythmia detection and recognition in ECG Signals using nonlinear techniques, Ann. Biomed. Eng. (2000)Google Scholar
  37. 37.
    Yu, S.-N., Chen, Y.-H.: Selection of Higher Order Subband Features for ECG Beat Classification (2008)Google Scholar
  38. 38.
    Palreddy, S.: ECG Beats Database Description, PH. D. University of Wisconsin (1996)Google Scholar
  39. 39.
    Werbos, P.J.: The Roots of Backpropagation Forom Ordered Derivatives to Neuronal Networks and Political Forescasting. Wiley Series on Adaptive and Learning System for Signal Processing Communication and Control. Wiley, New York (1994)Google Scholar
  40. 40.
    Ozbay, Y., Ceylan, R., Karlik, B.: A Fuzzy Clustering Neuronal Network Architecture for Classification of ECG Arrhtymias (January 2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Eduardo Ramírez
    • 1
  • Oscar Castillo
    • 1
  • José Soria
    • 1
  1. 1.Graduate StudiesTijuana Institute of TechnologyTijuanaMéxico

Personalised recommendations