Advertisement

Automatic Control and Computer Sciences

, Volume 52, Issue 6, pp 528–538 | Cite as

Denoising ECG Signals by Using Extended Kalman Filter to Train Multi-Layer Perceptron Neural Network

  • S. Gaamouri
  • M. Bousbia SalahEmail author
  • R. Hamdi
Article
First Online:
  • 9 Downloads

Abstract

The purpose of this paper is to study a denoising scheme for ECG signals by using extended Kalman filter based on Multilayer Perceptron Neural Network. A comparison with other enhancement conventional filters, such as, Wiener, wavelet, median and least mean square filters has been investigated. This approach is evaluated on several ECG by artificially adding white and colored Gaussian noises, and real non-stationary muscle artifact to visually inspect clean ECG recordings. It is also evaluated on studying the mean square error and Peak signal to noise ratio of the filters outputs. On the basis of these two parameters, a comparative analysis has been presented to explore the efficient denoising capability of the proposed method. The results of this simulation show the effectiveness of this approach.

Keywords:

electrocardiogram multilayer perceptron neural network extended Kalman filter conventional filters 
This is a preview of subscription content, log in to check access.

Notes

ACKNOWLEDGMENTS

We would like to thank the laboratory of automatic and signals at Annaba (LASA) for its support of this work.

REFERENCES

  1. 1.
    Saritha, C., Sukanya, V., and Murthy, Y.N., ECG signal analysis using wavelet transforms, Bulg. J. Phys., 2008, vol. 35, no. 1, pp. 68–77.zbMATHGoogle Scholar
  2. 2.
    Rakshit, M., Panigrahy, D., and Sahu, P.K., EKF with PSO technique for delineation of P and T wave in electrocardiogram (ECG) signal, Proc. 2nd IEEE Conf. on Signal Processing and Integrated Networks, 2015, pp. 696–701.Google Scholar
  3. 3.
    Kaur, T., A review for removal of baseline wander noise in ECG using various techniques, Int. J. Res. Appl. Sci. Eng. Technol., 2015, vol. 3, no. 7, pp. 2321–9653.Google Scholar
  4. 4.
    Gotchev, A., Nikolaev, N. and Egiazaian, K., Improving the transform domain ECG denoising performance by applying inter beat and intra-beat decorrelating transforms, Proc. The 2001 IEEE International Symposium on Circuits and Systems, 2001, pp. 17–20.Google Scholar
  5. 5.
    Karthika, R., Narender, K., Tech, M., and Vikram, B.R., ECG signal denoising using least-mean-square and normalised-least-mean-square algorithm based adaptive filter, Int. J. Mag. Eng., 2015, vol. 2, no. 2015, pp. 640–646.Google Scholar
  6. 6.
    Azami, H., Mohammadi, K., and Bozorgtabar, B., An improved signal segmentation using moving average and Savitzky-Golay filter, J. Signal Inf. Process., 2012, vol. 3, no. 1, p. 39.Google Scholar
  7. 7.
    Vidya, M.J. and Sadasiv, S.A., Comparative study on removal of noise in ECG signal using different filters, Int. J. Innovative Res. Dev., 2013, vol. 2, no. 4, pp. 915–927.Google Scholar
  8. 8.
    Lander, P. and Berbari, E.J., Time-frequency plane Wiener filtering of the high-resolution ECG: Background and time-frequency representations, IEEE Trans. Biomed. Eng., 1997, vol. 44, no. 4, pp. 247–255.CrossRefGoogle Scholar
  9. 9.
    Daqrouq, K., ECG baseline wandering reduction using discrete wavelet transforms, Asian J. Inf. Technol., 2005, vol. 4, no. 11, pp. 989–995.Google Scholar
  10. 10.
    Donoho, D.L., Denoising by soft-thresholding, IEEE Trans. Inf. Theory, 1995, vol. 41, no. 3, pp. 613–627.CrossRefzbMATHGoogle Scholar
  11. 11.
    Martis, R.J., Acharya, U.R., Mandana, K.M., et al., Application of principal component analysis to ECG signals for automated diagnosis of cardiac health, Expert Syst. Appl., 2012, vol. 39, no. 14, pp. 11792–11800.CrossRefGoogle Scholar
  12. 12.
    Deshpande, S. and Rajankar, S.O., Removing artifacts from electrocardiographic signals using independent components analysis, Int. J. Res. Sci. Adv. Technol., 2013, vol. 2, no. 5, pp. 182–184.Google Scholar
  13. 13.
    Sao, P., Hegadi, R., and Karmakar, S., ECG signal analysis using artificial neural network, Proc. National Conf. on Knowledge, Innovation in Technology and Engineering, 2015, pp. 82–86.Google Scholar
  14. 14.
    Popescu, M.C., Balas, V.E., Perescu-Popescu, L., and Mastorakis, N., Multilayer perceptron and neural networks, WSEAS Transactions on Circuits and Systems, 2009, vol. 8, no. 7, pp. 579–588.Google Scholar
  15. 15.
    Awasthi, V. and Raj, K., A comparison of Kalman filter and extended Kalman filter in State estimation, Int. J. Electron. Eng., 2011, vol. 3, no. 1, pp. 67–71.Google Scholar
  16. 16.
    Panigrahy, D. and Sahu, P.K., Extended Kalman smoother with differential evolution technique for denoising of ECG signal, Australasian Phys. Eng. Sci. Med., 2016, vol. 39, no. 3, pp. 783–795.CrossRefGoogle Scholar
  17. 17.
    Rachim, V.P., Kang, S.C., Chung, W.Y., and Kwon, T.H., Implementation of extended Kalman filter for real-time noncontact ECG signal acquisition in android-based mobile monitoring system, J. Sensor Sci. Technol., 2014, vol. 23, no. 1, pp. 7–14.CrossRefGoogle Scholar
  18. 18.
    Moein, S., An MLP Neural Network for ECG Noise Removal Based on Kalman Filter, New York: Springer, 2010.CrossRefGoogle Scholar
  19. 19.
    Sameni, R., Shamsollahi, M.B., and Jutten, C., and al., Filtering noisy ECG signals using the extended Kalman filter based on a modified dynamic ECG model, Proc. 32th IEEE Conf. on Computers in Cardiology, 2005, pp. 1017–1020.Google Scholar
  20. 20.
    Sayadi, O. and Shamsollahi, M.B., ECG denoising and compression using a modified extended Kalman filter structure, IEEE Trans. Biomed. Eng., 2008, vol. 55, no. 9, pp. 2240–2248.CrossRefGoogle Scholar
  21. 21.
    Belmahdi, F., Application du Filtre de Kalman pour le Debruitage des Signaux ECG, Algeria: Academic, 2015.Google Scholar
  22. 22.
    Moody, G.B. and Mark G.R., MIT BIH Arrhythmia Database. https://physionet.org/physiobank/database/mitdb/.Google Scholar
  23. 23.
    Moody, G.B., Muldrow, W.E., and Mark, G.R., The MIT-BIH Noise Stress Test. http://www.physionet.org/ physiobank/database/nstdb/.Google Scholar
  24. 24.
    Sayyad, R.A. and Mundada, K., Enhancement and denoising of ECG signal using extended Kalman filter and extended Kalman smoother, J. Innovation Electron. Commun. Eng., 2016, vol. 6, no. 1, pp. 22–26.Google Scholar
  25. 25.
    Wan, E.A. and Nelson, A.T., Neural dual extended Kalman filtering: Applications in speech enhancement and monaural blind signal separation, Proc. IEEE Conf. on Neural Networks for Signal Processing, 1997, pp. 466–475.Google Scholar
  26. 26.
    Podder, P., Khan, T.Z., and Khan, M.H., Comparative performance analysis of Hamming, Hanning and Blackman window, Int. J. Comput. Appl., 2014, vol. 96, no. 18, pp. 1–7.Google Scholar
  27. 27.
    de Lima, D.P., Sanches, R.F.V., and Pedrino, E.C., Neural network training using unscented and extended Kalman filter, Eng. J., 2017, vol. 1, no. 4, pp. 555–568.Google Scholar
  28. 28.
    Kaoulal, R., Hedeili, N., and Chikh, M.A., Application des Reseaux de Neurones dans la Reconnaissance des Arythmies Cardiaques, Algeria: Academic, 2003.Google Scholar
  29. 29.
    Sarkka, S., On unscented Kalman filtering for state estimation of continuous-time nonlinear systems, IEEE Trans. Autom. Control, 2007, vol. 52, no. 9, pp. 1631–1641.MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Arasaratnam, I. and Haykin, S., Cubature Kalman filters, IEEE Trans. Autom. Control, 2009, vol. 54, no. 6, pp. 1254–1269.MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Allerton Press, Inc. 2018

Authors and Affiliations

  1. 1.Department of Electronics Badji Mokhtar Annaba University, LASA Laboratory BP 12AnnabaAlgeria

Personalised recommendations

Cite article

Buy options