Performance Evaluation of Neural Networks and Adaptive Neuro Fuzzy Inference System for Classification of Cardiac Arrhythmia

  • Authors

    • L. V.Rajani Kumari
    • Y. Padma Sai
    • N. Balaji
    https://doi.org/10.14419/ijet.v7i4.22.28707
  • Electrocardiogram, discrete wavelet transform, S-Transform, ANN, ANFIS

  • Abstract

    In diagnosing the heart diseases, the beat classification of Electrocardiogram (ECG) plays a vital role. This work proposes a good design of an expert system for classification of the normal beat (N), left bundle branch block beat (L), premature ventricular contraction (V), paced beat (P) , atrial premature beat (A) and right bundle branch block beat (R) using time domain, S-Transform and discrete wavelet transform (DWT). The extracted feature set is given to adaptive neuro fuzzy inference system (ANFIS) and artificial neural network (ANN) for classification. The performance analyses on various normal ECG and abnormal ECG signals from 44 subjects of the MIT-BIH arrhythmia database. In this work, the performances of three neural networks, Cascade forward back propagation, nonlinear autoregressive exogenous model (NARX) and Elman back propagation are compared with ANFIS. Contrast to the neural networks the ANFIS shows better performance in the experimental outcomes.

     

     

  • References

    1. [1] Benchaib, Y., Chikh, M.: A specialized learning for neural classification of cardiac arrhythmias. J. Theor. Appl. Inf. Technol. 6(1), 92–100 (2009).

      [2] Kavitha, K., Ramakrishnan, K., Singh, M.: Modeling and design of evolutionary neural network for heart disease detection. Int. J. Comput. Sci. Issues 7(5), 272–283 (2010).

      [3] Ghorbanian, P., Ghaffari, A., Nataraj, C.: Heart arrhythmia detection through continuous wavelet transform and principal component analysis with neural network classifier. Comput. Cardiol. 37, 669–672 (2010)

      [4] Vijaya, V., Rao, K., Rama, V.: Arrhythmia detection through ECG feature extraction using wavelet analysis. Eur. J. Sci. Res. 66(3), 441–448 (2011)

      [5] Ozbay, Y., Karlik, B.: A recognition of ECG arrhythmias using artificial neural networks. In: Proceedings—23rd Annual Conference, 23, pp. 1–5 (2001)

      [6] Aprasit, W., Laosen, N., Chevakidagarn, S.: Data filtering technique for neural networks forecasting. WSEAS Int. Conf. Simul. Model. Optim 7, 225–230 (2007)

      [7] Baranchuk, A., Shaw, C., Alanazi, H., Campbell, D., Bally, K., Redfearn, D., Simpson, C.Abdollah, H.: Electrocardiography pitfalls and artifacts: the 10 commandments. Crit. Care Nurse 29(1), 67–73 (2009)

      [8] Ball, R., Tissot, P.: Demonstration of artificial neural network in Matlab. Div. Nearhsore Res. 12, 1–5 (2006)

      [9] Kannathal, N., Acharya, U., Lim, C., Sadasivan, P., Krishnan, S.: Classification of cardiac patient states using artificial neural networks. Intell. Inf. Syst. Conf. 8(4), 206–211 (2003)

      [10] Nugent, C., Lopez, J., Smith, A., Black, N.: Prediction models in the design of neural network based ECG classifiers: a neural network & genetic programming approach. BMC Med. Inform.Decis. Mak. 2(1), 1–6 (2002)

      [11] Hede´n, B., O ¨ hlin, H., Rittner, R., Edenbrandt, L.: Acute myocardial infarction detected in the 12-lead ECG by artificial neural network. Dep. Clin. Physiol. Cardiol. 96, 1798–1802 (1997)

      [12] Stamkopoulos, T., Diamantaras, K., Maglaveras, N., Strintzis, M.: ECG analysis using non-linear pca neural networks for ischemia detection. Trans. Signal Process. 46(11), 3058–3067 (1998)

      [13] Bortolan, G., Willems, J.: Diagnostic ECG classification based on neural networks. J. Electrocardiol. 75(9), 1–6 (1993)

      [14] Suzuki, Y.: Self-organizing QRS-wave recognition ECG using neural networks. Trans. Neural Netw. 6(6), 1469–1477 (1995).

      [15] Edenbrandt, L., Devine, B., Macfarlane, P.: Neural networks for classification of ECG ST-segments. Eur. Heart J. 14(4), 464–468 (1992)

      [16] Bortolan, G., Degani, R., Willems, J.: ECG classification with neural networks and cluster analysis. Comput. Cardiol. 20, 177–180 (1991)

      [17] Manchanda, S., Ehsanullah, M.: Suspected cardiac syncope in elderly patients: use of the 12-lead electrocardiogram to select patients for Holter monitoring. Gerontology 47, 195–197 (2001).

      [18] P.deChazal, M.O’Dwyer, R.Reilly, Automatic classification of heart beats using ECG morphology and heart beat interval features , IEEE Trans. Biomed. Eng.51 (7) (2004) 1196–1206.

      [19] G.DeLannoy, D.Francois, J.Delbeke, M.Verleysen, Weighted conditional random fields for supervised interpatient heart beat classification, IEEE Trans. Biomed. Eng. 59 (1) (2012) 241–247.

      [20] L.deOliveira, R.Andreao & M.Sarcinelli-Filho, 2011. Premature ventricular beat classification using a dynamic Bayesian network. Boston, MA,s.n.

      [21] T.Ince, S.Kiranyaz, M.Gabbouj, A generic and robust system for automated patient-specific classification of ECG signals, IEEE Trans. Biomed. Eng. 56 (5) (2009) 1415–1426.

      [22] W.Jiang, S.Kong, Block-based neural networks for personalized ECG signal classification, IEEE Trans. Neural Netw. 18 (6) (2007) 1750–1761.

      [23] X.Jiang, L.Zhang, Q.Zhao, & S.Albayrak. ECG arrhythmias recognition system based on independent component analysis feature extraction. HongKong ,s.n. , 2006

      [24] M.Lagerholm, C.Peterson, G.Braccini, L.Edenbrandt, Clustering ECG complexes using Hermite functions and self-organizing maps, IEEE Trans. Biomed. Eng.47 (7) (2002) 838–848.

      [25] M.Llamedo, J.Martinez, Heart beat classification using features election driven by data base generalization criteria, IEEE Trans. Biomed. Eng.58 (3) (2011) 616–625.

      [26] S.Osowski, L.T.Hoai, T.Markiewicz, Support vector machine-based expert system for reliable heart beat recognition, IEEE Trans. Biomed. Eng. 51 (4) (2004) 582–589.

      [27] S.Yang, & H.Shen, Heart beat classification using discrete wavelet transform and kernel principal component analysis. Sydney, NSW, s.n., pp.34–38, 2013.

      [28] C.Ye, B.Kumar, M.Coimbra, Heart beat classification using morphological and dynamic features of ECG signals, IEEE Trans. Biomed. Eng. 59 (10) (2012) 2930–2941.

      [29] X.D.Zeng, S.Chao & F.Wong, Ensemble learning on heart beat type classifycation. Macao, s.n, 2011.

      [30] Manab Kumar Das and Samit Ari, “ECG Beats Classification Using Mixture of Featuresâ€, International Scholarly Research Notices, Volume 2014

      [31] L. V. Rajani Kumari, Y. Padma Sai, N. Balaji and R. Gowrisree “ Comparison of Artificial Neural Networks for Cardiac Arrhythmia Classificationâ€, International Journal of Advance Engineering and Research Development, Volume 4, Issue 10, October -2017, e-ISSN (O): 2348-4470 p-ISSN (P): 2348-6406

  • Downloads

  • How to Cite

    V.Rajani Kumari, L., Padma Sai, Y., & Balaji, N. (2018). Performance Evaluation of Neural Networks and Adaptive Neuro Fuzzy Inference System for Classification of Cardiac Arrhythmia. International Journal of Engineering & Technology, 7(4.22), 250-253. https://doi.org/10.14419/ijet.v7i4.22.28707

    Received date: 2019-03-31

    Accepted date: 2019-03-31