Advertisement

A Modular Neural Network Approach for Cardiac Arrhythmia Classification

  • Eduardo Ramírez
  • Patricia MelinEmail author
  • German Prado-Arechiga
Chapter
  • 50 Downloads
Part of the Studies in Computational Intelligence book series (SCI, volume 862)

Abstract

In this work we describe a modular neural network approach to use expert modules as a classification model for 12-lead cardiac arrhythmias. The modular neural network is designed using Multilayer perceptron as classifiers. This modular neural network was trained and tested with the Physilalisch-Technische Bundesantalt diagnostic ECG database (PTB database) of physioBank. The electrocardiograms are preprocessed to improve their classification through the proposed modular neural network. This modular neural network uses the features extracted of each signal such as autoregressive model coefficients, Shannon entropy and multifractal wavelets. We used the twelve electrode signals or leads included in the PTB database, such as i, ii, iii, avf, avr, avl, v1, v2, v3, v4, v5, v6, vx, vy and vz. The modular neural network is composed by twelve expert modules, where each module is used to perform the classification for the specific signal lead. The expert modules are based on the following models: multilayer perceptron with scaled conjugate gradient backpropagation (MLP-SCG). Finally, the outputs from the expert modules are combined using winner-takes-all integration as modular neural network integration method.

Keywords

Modular neural network Multilayer perceptron 12-lead arrhythmia classification 

References

  1. 1.
    Martis, R.J., Achayra, U.R., Prasad, H., Chua, C.K.: Application of higher order statistics for atrial arrhythmia classification. Biomed. Sign. Process. Control 8(6), 888–900 (2013)CrossRefGoogle Scholar
  2. 2.
    Amezcua, J., Melin, P.: A modular LVQ neural network with fuzzy response integration for arrhythmia classification. In: IEEE Conference on Norbert Wiener in the 21st Century (2014)Google Scholar
  3. 3.
    Melin, P., Amezcua, J., Valdez, F., Castillo, O.: A new neural network model based on the LVQ algorithm for multi-class classification of arrhythmias. Inf. Sci. 279, 483–497 (2014)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Khalaf, A.F., Owis, M.L., Yassine, I.A.: A novel technique for cardiac arrhythmia classification using spectral correlation and support vector machines. Expert Syst. Appl. 42(21), 8361–8368 (2015)CrossRefGoogle Scholar
  5. 5.
    Homaeinezhad, M.R., Atyabi, S.A., Tavakkoli, E., Toosi, H.N., Ghaffari, A., Ebrahimpour, R.: ECG arrhythmia recognition via a neuro-SVM-KNN hybrid classifier with virtual QRS image-based geometrical features. Expert Syst. Appl. 39(2), 2047–2058 (2012)CrossRefGoogle Scholar
  6. 6.
    Zhao, Q., Zhang, L.: ECG feature extraction and classification using wavelet transform and support vector machines. IEEE Int. Conf. Neural Netw. Brain 2, 1089–1092 (2005)Google Scholar
  7. 7.
    Bousseljot, R., Kreiseler, D., Schnabel, A.: Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomedizinische Technik, Band 40, Ergänzungsband 1 p. S 317 (1995)Google Scholar
  8. 8.
    Wang, J.S., Chiang, W.C., Hsu, Y.L., Yang, Y.T.: ECG arrhythmia classification using a probabilistic neural network with a feature reduction method. Neurocomputing. 116, 38–45 (2013)CrossRefGoogle Scholar
  9. 9.
    Javadi, M., Asghar, S.A., Sajedin, A., Ebrahimpour, R.: Classification of ECG arrhythmia by a modular neural network based on mixture of experts and negatively correlated learning. Biomed. Sign. Process. Control. 8, 289–296 (2013)CrossRefGoogle Scholar
  10. 10.
    Al Rahhal, M.M., Bazi, Y., Alhichri, H., Alajlan, N., Melgani, F., Yager, R.R.: Deep learning approach for active classification of electrocardiogram signals. Inf. Sci. 345, 340–354 (2016)CrossRefGoogle Scholar
  11. 11.
    Megat, M.S.A., Jahidin, A.H., Norall, A.N.: Hybrid multilayered perceptron network classification of bundle branch blocks. In: IEEE 2012 International Conference Biomedical Engineering Icobe (2012). ISBN 978-1-4577-1991-2Google Scholar
  12. 12.
    Castillo, O., Melin, P., Ramirez, E., Soria, J.: Hybrid intelligent system for cardiac arrhythmia classification with fuzzy K-Nearest Neighbors and neural networks combined with a fuzzy system. Expert Syst. Appl. 39, 2947–2955 (2012)CrossRefGoogle Scholar
  13. 13.
    Melin, P., Ramirez, E., Prado-Arechiga, G.: Cardiac arrhythmia classification using computational intelligence: neural networks and fuzzy logic techniques. European Heart J. OXFORD academic 38, P6388 (2017)Google Scholar
  14. 14.
    Osowki, S., Markiewicz, T., Hoal, L.T.: Recognition and classification systems of arrhythmia using ensemble of neural networks. Measurement 41(6), 610–617 (2018)CrossRefGoogle Scholar
  15. 15.
    Osowksi, S., Siwek, K., Siroic, R.: Neural system for heartbeats recognition using genetically integrated ensemble of classifiers. Comput. Biol. Med. 41(3), 173–180 (2011)CrossRefGoogle Scholar
  16. 16.
    Jadhav, S.M., Nalbalwar, S.L., Ghatol, A.A.: ECG arrhythmia classification using modular neural network model. In: IECBES (2012) ISBN 978-1-4244-7600-8Google Scholar
  17. 17.
    Ozbay, Y., Tezel, G.: A new method for classification of ECG arrhythmias using neural network with adaptive activation function. Digit. Sig. Proc. 20, 1040–1049 (2010)CrossRefGoogle Scholar
  18. 18.
    Ozbay, Y., Ceylan, R., Karlik, B.: A fuzzy clustering neural network architecture for classification of ECG arrhythmias. Comput. Biol. Med. 36, 376–388 (2005)CrossRefGoogle Scholar
  19. 19.
    Gaetano, D., Panunzi, S., Rinaldi, F., Risi, A., Sciandrone, M.A.: A patient adaptable ECG beat classifier based on neural networks. Appl. Math. Comput. 213(1), 243–249 (2009)MathSciNetzbMATHGoogle Scholar
  20. 20.
    Melin, P., Castillo, O.: A review of the applications of type-2 fuzzy logic in classification and pattern recognition. Expert Syst. Appl. 40(13), 5413–5423 (2013)CrossRefGoogle Scholar
  21. 21.
    Melin, P., Castillo, O.: A review on the applications of type-2 fuzzy logic in classification and pattern recognition. Expert Syst. Appl. 40, 5413–5423 (2013)CrossRefGoogle Scholar
  22. 22.
    Ceylan, R., Ozbay, Y., Karlik, B.: A novel approach for classification of ECG arrhythmias: type-2 fuzzy clustering neural network. ACM 36(3), 6721–6727 (2009)Google Scholar
  23. 23.
    Chua, T.W., Tan, W.W.: Interval type-2 fuzzy system for ECG arrhythmia classification. Fuzzy Systems in Bioinformatics and Computational Biology, pp. 297–314. Springer, Berlin (2009). ISBN 978-3-540-89968-6CrossRefGoogle Scholar
  24. 24.
    Tan, W.W., FOO, C.L., Chua, T.: Type-2 fuzzy system for ECG arrhythmic classification, FYZZ-IEEE (2007). ISBN 1-4244-1209-9Google Scholar
  25. 25.
    Keller, J.M., Gray, M.R., Givens, J.A.: A fuzzy K-Nearest neighbor algorithm. IEEE Trans. Syst. Man Cybern. 15, 580–585 (1985)CrossRefGoogle Scholar
  26. 26.
    Ramirez, E., Castillo, O., Soria, J.: Hybrid system for cardiac arrhythmia classification with Fuzzy K-Nearest Neighbors and neural networks combined by a fuzzy inference system.In: Softcomputing for Recognigtion Based on Biometrics, Studies in Computational Intelligence, vol. 312, pp. 37–53, Springer (2010). ISBN 978-3-642-15110-1Google Scholar
  27. 27.
    Ramirez, E., Melin, P., Prado-Arechiga, G.: Hybrid model based on neural networks, type-1 and type-2 fuzzy systems for 2-lead cardiac arrhythmia classification. Expert Syst. Appl. 126, 295–307 (2019)CrossRefGoogle Scholar
  28. 28.
    Wozniak, M., Grana, M., Corchado, E.: A survey of multiple classifier systems as hybrid systems. Inf. Fusion 16, 3–17 (2014)CrossRefGoogle Scholar
  29. 29.
    Melin, P., Prado-Arechiga, G., Miramontes, I., Medina. M.: A hybrid intelligent model based on modular neural network and fuzzy logic for hypertension risk diagnosis. J. Hypertension 34 (2016)Google Scholar
  30. 30.
    Nazmy, T.M., EL-Messiry, H., AL-Bokhity, B.: Classification of cardiac arrhythmia based on hybrid system. Int. J. Comput. Appl. 2 (2010)CrossRefGoogle Scholar
  31. 31.
    Shao, Y.E., Hou, C.D., Chiu, C.C.: Hybrid intelligent modeling schemes for heart disease classification. Appl. Soft Comput. 14, 47–52 (2014)CrossRefGoogle Scholar
  32. 32.
    Luz, E.J.D.S., Schwartz, W.R., Camara-Chavez, G., Menotti, D.: ECG-based heartbeat classification for arrhythmia detection: a survey. Comput. Methods Prog. Biomed. 127, 144–164 (2015)CrossRefGoogle Scholar
  33. 33.
    Elhaj, F.A., Salim, N., Harris, A.R., Swee, T.T., Ahmed, T.: Arrhytmia recognition and classification using combined linear and nonlinear features of ECG signals. Comput. Methods Prog. Biomed. 127, 52–63 (2016)CrossRefGoogle Scholar
  34. 34.
    Jovic, A., Bogunovic, N.: Evaluating and comparing performance of feature combinations of heart rate variability measures for cardiac rhythm classification. Biomed. Sign. Process. Control. 7, 245–255 (2012)CrossRefGoogle Scholar
  35. 35.
    Martis, R.J., Achayra, U.R., Min, L.C.: ECG beat classification using PCA, LDA, ICA, and Discrete Wavelet Transform. Biomed. Sign. Process. Control 8, 437–448 (2013)CrossRefGoogle Scholar
  36. 36.
    Zopounidis, M., Doumpos, M.: Multicriteria classification and sorting methods: a literature review. Eur. J. Oper. Res 138, 229–246 (2002)zbMATHCrossRefGoogle Scholar
  37. 37.
    Gacek, A., Pedrycz, W.: Ecg signal processing, Classification and Interpretation, a comprehensive framework of computational intelligence, Springer (2012) ISBN 978-0-85729-867-6Google Scholar
  38. 38.
    Martindale, J.L., Brown, D.F.M.: A visual guide to ECG interpretation, second edition. Wolters Kluwer (2017) ISBN 978-1-4963-2153-4Google Scholar
  39. 39.
    Hampton, J.R., Adlam, D.: The ECG in practice, 6th edn. Churchill Livingstone, Elsevier (2013). ISBN 978-0-7020-4643-8Google Scholar
  40. 40.
    Jayasinghe, R.: ECG Workbook. Elsevier, Churchill Livingstone (2012). ISBN 978-0-7295-4109-1Google Scholar
  41. 41.
    Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdorff, J.M., Ivanov, P.C.H., Mark, R.G., Mietus, J.E., Moody, G.B., Peng, C.-K., Stanley, H.E.: physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation. 101(23), e215-e220 (2000)Google Scholar
  42. 42.
    Bishop, C.M.: Neural network for pattern recognition. Clarendon Press, Oxford, U.KGoogle Scholar
  43. 43.
    Leonarduzzi, R.F., Schlotthauer, G., Torres, M.E.: Wavelet leader based multifractal analysis of heart rate variability during myocardial ischaemia.In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Eduardo Ramírez
    • 1
  • Patricia Melin
    • 1
    Email author
  • German Prado-Arechiga
    • 1
  1. 1.Tijuana Institute of Technology, Graduate StudiesTijuanaMexico

Personalised recommendations