Analysis of EEG Epileptic Signals with Rough Sets and Support Vector Machines

  • Joo-Heon Shin
  • Dave Smith
  • Roman Swiniarski
  • F. Edward Dudek
  • Andrew White
  • Kevin Staley
  • Krzysztof J. Cios
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5651)


Epilepsy is a common chronic neurological disorder that impacts over 1% of the population. Animal models are used to better understand epilepsy, particularly the mechanisms and the basis for better antiepileptic therapies. For animal studies, the ability to identify accurately seizures in electroencephalographic (EEG) recordings is critical, and the use of computational tools is likely to play an important role. Electrical recording electrodes were implanted in rats before kainate-induced status epilepticus (one in each hippocampus and one on the surface of the cortex), and EEG data were collected with radio-telemetry. Several data mining methods, such as wavelets, FFTs, and neural networks, were used to develop algorithms for detecting seizures. Rough sets, which were used as an additional feature selection technique in addition to the Daubechies wavelets and the FFTs, were also used in the detection algorithm. Compared with the seizure-at-once method by using the RBF neural network classifier used earlier on the same data [12], the new method achieved higher recognition rates (i.e., 91%). Furthermore, when the entire dataset was used, as compared to only 50% used earlier, preprocessing using wavelets, Principal Component Analysis, and rough sets in concert with Support Vector Machines resulted in accuracy of 94% in identifying epileptic seizures.


epileptic seizures detection medical signal processing rough sets 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alkan, A., Koklukaya, E., Subasi, A.: Automatic seizure detection in EEG using logistic regression and artificial neural network. J. Neurosci. Methods. 148(2), 167–176 (2005)CrossRefPubMedGoogle Scholar
  2. 2.
    Cios, K.J., Pedrycz, W., Swiniarski, R., Kurgan, L.: Data Mining: A Knowledge Discovery Approach. Springer, Heidelberg (2007)Google Scholar
  3. 3.
    Dudek, F.E., Clark, S., Williams, P.A., Grabenstatter, H.L.: Kainate-induced status epilepticus: A chronic model of acquired epilepsy. In: Pitkänen, A., Schwartzkroin, P.A., Moshé, S.L. (eds.) Models of Seizures and Epilepsy, ch. 34, pp. 415–432. Elsevier Academic Press, Amsterdam (2006)CrossRefGoogle Scholar
  4. 4.
    Dudek, F.E., Staley, K.J., Sutula, T.P.: The Search for Animal Models of Epileptogenesis and Pharmacoresistance: Are There Biologic Barriers to Simple Validation Strategies? Epilepsia 43(11), 1275–1277 (2002)CrossRefPubMedGoogle Scholar
  5. 5.
    Dzhala, V.I., Talos, D.M., Sdrulla, D.A., Brumback, A.C., Mathews, G.C., Benke, T.A., Delpire, E., Jensen, F.E., Staley, K.J.: NKCC1 transporter facilitates seizures in the developing brain. Nat. Med. 11, 1205–1213 (2005)CrossRefPubMedGoogle Scholar
  6. 6.
    Gabor, A.: Seizure detection using a self-organizing neural network: validation and comparison with other detection strategies. Electroencephalogr Clin Neurophysiol. 107(1), 27–32 (1998)CrossRefPubMedGoogle Scholar
  7. 7.
    Gotman, J.: Automatic seizure detection: improvements and evaluation. Electroencephalogr Clin Neurophysiol. 76(4), 317–324 (1990)CrossRefPubMedGoogle Scholar
  8. 8.
    Khan, Y., Gotman, J.: Wavelet based automatic seizure detection in intracerebral electroencephalogram. Clin Neurophysiol. 114(5), 898–908 (2003)CrossRefPubMedGoogle Scholar
  9. 9.
    Lehnertz, K., Litt, B.: The first international collaborative workshop on seizure prediction: summary and data description. Clin Neurophysiol. 116(3), 493–505 (2005)CrossRefPubMedGoogle Scholar
  10. 10.
    Murro, A., King, D., Smith, J., Gallagher, B., Flanigin, H., Meador, K.: Computerized seizure detection of complex partial seizures. Electroencephalogr Clin Neurophysiol. 79(4), 330–333 (1991)CrossRefPubMedGoogle Scholar
  11. 11.
    Pawlak, Z.: Rough sets: Theoretical aspects of reasoning about data. Kluwer Academic Publishers, Dordrecht (1991)CrossRefGoogle Scholar
  12. 12.
    Schuyler, R., White, A., Staley, K., Cios, K.: Identification of Ictal and Pre-Ictal States using RBF Networks with Wavelet-Decomposed EEG. IEEE EMB 26(2), 86–93 (2007)Google Scholar
  13. 13.
    Stables, J.P., Bertram, E., Dudek, F.E., Holmes, G., Mathern, G., Pitkanen, A., White, H.S.: Therapy discovery for pharmacoresistant epilepsy and for disease-modifying therapeutics: Summary of the NIH/NINDS/AES Models II Workshop. Epilepsia 44, 1472–1478 (2003)CrossRefPubMedGoogle Scholar
  14. 14.
    Staley, K.J., Dudek, F.E.: Interictal Spikes and Epileptogenesis. Epilepsy Currents 6(6), 199–202 (2006)CrossRefPubMedPubMedCentralGoogle Scholar
  15. 15.
    Subasi, A.: Application of adaptive neurofuzzy inference system for epileptic seizure detection using wavelet feature extraction. Comput. Biol. Med. 37(2), 227–244 (2007)CrossRefPubMedGoogle Scholar
  16. 16.
    Swiniarski, R., Shin, J.: Classification of Mammograms Using 2D Haar Wavelet, Rough Sets and Support Vector Machines. In: Proceedings of the International Conference on Data Mining in Las Vegas, pp. 65–70 (2005)Google Scholar
  17. 17.
    Theodore, W.H., Spencer, S.S., Wiebe, S., Langfitt, J.T., Ali, A., Shafer, P.O., Berg, A.T., Vickrey, B.G.: Epilepsy in North America: A Report Prepared under the Auspices of the Global Campaign against Epilepsy, the International Bureau for Epilepsy, the International League Against Epilepsy, and the World Health Organization. Epilepsia 47(10), 1700–1722 (2006)CrossRefPubMedGoogle Scholar
  18. 18.
    Übeyli, E.D.: Combined neural network model employing wavelet coefficients for EEG signals classification. Digital Signal Processing 19(2), 297–308 (2009)CrossRefGoogle Scholar
  19. 19.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1999)Google Scholar
  20. 20.
    White, A., Williams, P., Ferraro, D., Clark, S., Kadam, S., Dudek, F.E., Staley, K.: Efficient unsupervised algorithms for the detection of seizures in continuous EEG recordings from rats after brain injury. J. Neurosci. Methods 152, 255–266 (2006)CrossRefPubMedGoogle Scholar
  21. 21.
    Williams, P.A., White, A.M., Clark, S., Ferraro, D.J., Swiercz, W., Staley, K.J., Dudek, F.E.: Development of spontaneous recurrent seizures after kainate-induced status epilepticus. J. Neurosci. 29, 2103–2122 (2009)CrossRefPubMedPubMedCentralGoogle Scholar
  22. 22.
    Williams, P., White, A., Ferraro, D., Clark, S., Staley, K., Dudek, F.E.: The use of radiotelemetry to evaluate electrographic seizures in rats with kainate-induced epilepsy. J. Neurosci. Methods 155(1), 39–48 (2006)CrossRefPubMedGoogle Scholar
  23. 23.
    Wilson, S.: Spike detection: a review and comparison of algorithms. Clin Neurophysiol. 113, 1873–1881 (2002)CrossRefPubMedGoogle Scholar
  24. 24.
    Wilson, S.B., Scheuer, M.L., Plummer, C., Young, B., Pacia, S.: Seizure detection: Correlation of human experts. Clin Neurophysiol. 114, 2156–2164 (2003)CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Joo-Heon Shin
    • 1
  • Dave Smith
    • 2
  • Roman Swiniarski
    • 3
  • F. Edward Dudek
    • 5
  • Andrew White
    • 2
  • Kevin Staley
    • 6
  • Krzysztof J. Cios
    • 1
    • 4
  1. 1.Virginia Commonwealth UniversityUSA
  2. 2.University of Colorado DenverUSA
  3. 3.San Diego State UniversityUSA
  4. 4.IITiS Polish Academy of SciencesGermany
  5. 5.University of UtahUSA
  6. 6.Massachusetts General Hospital and Harvard Medical SchoolUSA

Personalised recommendations