EEG Signal Classification Using Empirical Mode Decomposition and Support Vector Machine

Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 131)


In this paper, we present a new method based on empirical mode decomposition (EMD) for classification of seizure and seizure-free EEG signals. The EMD method decomposes the EEG signal into a set of narrow-band amplitude and frequency modulated (AM-FM) components known as intrinsic mode functions (IMFs). The method proposes the use of the area parameter and mean frequency estimation of IMFs in the classification of the seizure and seizure-free EEG signals. These parameters have been used as an input in least squares support vector machine (LS-SVM), which provides classification of seizure EEG signals from seizure-free EEG signals. The classification accuracy for classification of seizure and seizure-free EEG signals obtained by using proposed method is 98.33% for second IMF with radial basis function kernel of LS-SVM.


Epileptic seizure EEG signal Empirical mode decomposition Support vector machine EEG signal classification 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Iasemidis, L.D., Shiau, D.S., et al.: Adaptive epileptic seizure prediction system. IEEE Trans. Biomed. Eng. 50, 616–627 (2003)CrossRefGoogle Scholar
  2. 2.
    Gotman, J.: Automatic detection of seizures and spikes. J. Clin. Neurophysiol. 16, 130–140 (1999)CrossRefGoogle Scholar
  3. 3.
    Hese, P.V., Martens, J.P., Boon, P., Dedeurwaerdere, S., Lemahieu, I., Walle, R.V.: Detection of spike and wave discharges in the cortical EEG of genetic absence epilepsy rats from Strasbourg. Phys. Med. Biol. 48, 1685–1700 (2003)CrossRefGoogle Scholar
  4. 4.
    Srinivasan, V., Eswaran, C., Sriraam, N.: Artificial neural network based epileptic detection using time-domain and frequency-domain features. J. Med. Syst. 29, 647–660 (2005)CrossRefGoogle Scholar
  5. 5.
    Boashash, B., Mesbah, M., Colditz, P.: Time frequency detection of EEG abnormalities. In: Boashash, B. (ed.) Time-Frequency Signal Analysis and Processing: A Comprehensive Reference, ch. 15, article 15.5, pp. 663–670. Elsevier (2003)Google Scholar
  6. 6.
    Pachori, R.B., Sircar, P.: EEG signal analysis using FB expansion and second-order linear TVAR process. Signal Process 88, 415–420 (2008)MATHCrossRefGoogle Scholar
  7. 7.
    Adeli, H., Zhou, Z., Dadmehr, N.: Analysis of EEG records in an epileptic patient using wavelet transform. J. Neurosci. Methods 123, 69–87 (2003)CrossRefGoogle Scholar
  8. 8.
    Khan, Y.U., Gotman, J.: Wavelet based automatic seizure detection in intracerebral electroencephalogram. Clin. Neurophysiol. 114, 898–908 (2003)CrossRefGoogle Scholar
  9. 9.
    Tzallas, A.T., Tsipouras, M.G., Fotisdis, D.I.: Automatic seizure detection based on time-frequency analysis and artificial neural networks. Comput. Intell. Neurosci., article ID 80510 (2007)Google Scholar
  10. 10.
    Güler, N.F., Übeyli, E.D., Güler, İ.: Recurrent neural networks employing Lyapunov exponents for EEG signal classification. Expert Syst. Appl. 29, 506–514 (2005)CrossRefGoogle Scholar
  11. 11.
    Lehnertz, K., Elger, C.E.: Spatio-temporal dynamics of the primary epileptogenic area in temporal lobe epilepsy characterized by neuronal complexity loss. Electroencephalogr. Clin. Neurophysiol. 95, 108–117 (1995)CrossRefGoogle Scholar
  12. 12.
    Accardo, A., Affinito, M., Carrozzi, M., Bouquet, F.: Use of the fractal dimension for the analysis of electroencephalographic time series. Biol. Cybern. 77, 339–350 (1997)MATHCrossRefGoogle Scholar
  13. 13.
    Kannathal, N., Choob, M.L., et al.: Entropies for detection of epilepsy in EEG. Computer Methods Progr. Biomed. 80, 187–194 (2005)CrossRefGoogle Scholar
  14. 14.
    Casdagli, M.C., Iasemidis, L.D., et al.: Non-linearity in invasive EEG recordings from patients with temporal lobe epilepsy. Electroencephalogr. Clin. Neurophysiol. 102, 98–105 (1997)CrossRefGoogle Scholar
  15. 15.
    Song, Y., Lió, P.: A new approach for epileptic seizure detection: sample entropy based feature extraction and extreme learning machine. J. Biomed. Sci. Eng. 3, 556–567 (2010)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Ghosh-Dastidar, S., Adeli, H., Dadmehr, N.: Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection. IEEE Trans. Biomed. Eng. 54, 1545–1551 (2007)CrossRefGoogle Scholar
  17. 17.
    Ghosh-Dastidar, S., Adeli, H., Dadmehr, N.: Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection. IEEE Trans. Biomed. Eng. 55, 512–518 (2008)CrossRefGoogle Scholar
  18. 18.
    Ocak, H.: Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Syst. Appl. 36, 2027–2036 (2009)CrossRefGoogle Scholar
  19. 19.
    Guo, L., Rivero, D., Pazos, A.: Epileptic seizure detection using multiwavelet transform based approximation entropy and artificial neural networks. J. Neurosci. Methods 193, 156–163 (2010)CrossRefGoogle Scholar
  20. 20.
    Pachori, R.B.: Discrimination between ictal and seizure-free EEG signals using empirical mode decomposition. Res. Lett. Signal Process., article ID 293056 (2008)Google Scholar
  21. 21.
    Oweis, R.J., Abdulhey, E.W.: Seizure classification in EEG signals utilizing Hilbert-Huang transform. Biomed. Eng. Online 10, 38 (2011)CrossRefGoogle Scholar
  22. 22.
    Pachori, R.B., Bajaj, V.: Analysis of normal and epileptic seizure EEG signals using empirical mode decomposition, Computer Methods Progr. Biomed. (2011) (in press), doi:10.1016/j.cmpb.2011.03.009 Google Scholar
  23. 23.
    Huang, N.E., et al.: The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. R. Soc. Lon. A 454, 903–995 (1998)MATHCrossRefGoogle Scholar
  24. 24.
    Andrzejak, R.G., Lehnertz, K., et al.: Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity dependence on recording region and brain state. Phys. Rev. E. 64, article ID 061907 (2001)Google Scholar
  25. 25.
    Flandrin, P., Rilling, G., Goncalves, P.: Empirical mode decomposition as a filter bank. IEEE Signal Process. Lett. 11, 112–114 (2004)CrossRefGoogle Scholar
  26. 26.
    Cohen, M.E., Hudson, D.L., Deedwania, P.: Applying continuous chaotic modeling to cardic signal analysis. IEEE Eng. Med. Biol. Mag. 15, 97–102 (1996)CrossRefGoogle Scholar
  27. 27.
    Schroeder, J.: Signal processing via Fourier-Bessel series expansion. Digit. Signal Process. 3, 112–124 (1993)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Pachori, R.B., Hewson, D.: Assessment of effects of sensory perturbations using Fourier-Bessel expansion method for postual stability analysis. J. Intell. Syst. 20(2), 167–186 (2011)CrossRefGoogle Scholar
  29. 29.
    Pachori, R.B., Sircar, P.: Analysis of multicomponent AM-FM signals using FB-DESA method. Digit. Signal Process. 20, 42–62 (2010)CrossRefGoogle Scholar
  30. 30.
    Pachori, R.B., Sircar, P.: A new technique to reduce cross terms in Wigner distribution. Digit. Signal Process. 17, 466–474 (2007)CrossRefGoogle Scholar
  31. 31.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)MATHGoogle Scholar
  32. 32.
    Sukens, J.A.K., Vandewalle, J.: Least squares support vector machine classifiers. Neural Process. Lett. 9, 293–300 (1999)CrossRefGoogle Scholar
  33. 33.
    Khandoker, A.H., Lai, D.T.H., Begg, R.K., Palaniswami, M.: Wavelet-based feature extraction for support vector machines for screening balance impairments in the eldery. IEEE Trans. Neural Syst. Rehabil. Eng. 15, 587–597 (2007)CrossRefGoogle Scholar

Copyright information

© Springer India Pvt. Ltd. 2012

Authors and Affiliations

  1. 1.School of EngineeringIndian Institute of Technology IndoreIndoreIndia

Personalised recommendations