Journal of Medical Systems

, Volume 32, Issue 5, pp 403–408 | Cite as

A Radial Basis Function Neural Network Model for Classification of Epilepsy Using EEG Signals

  • Kezban Aslan
  • Hacer Bozdemir
  • Cenk Şahin
  • Seyfettin Noyan Oğulata
  • Rızvan Erol
Original Paper

Abstract

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient’s epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify epilepsy groups such as partial and primary generalized epilepsy by using Radial Basis Function Neural Network (RBFNN) and Multilayer Perceptron Neural Network (MLPNNs). Four hundred eighteen patients with epilepsy diagnoses according to International League against Epilepsy (ILAE 1981) were included in this study. The correct classification of this data was performed by two expert neurologists before they were executed by neural networks. The neural networks were trained by the parameters obtained from the EEG signals and clinic properties of the patients. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. According to test results, RBFNN (total classification accuracy = 95.2%) has classified more successfully when compared with MLPNN (total classification accuracy = 89.2%). These results indicate that RBFNN model may be used in clinical studies as a decision support tool to confirm the classification of epilepsy groups after the model is developed.

Keywords

Epilepsy EEG Radial basis function (RBF) Multilayer perceptron (MLP) Neural network 

References

  1. 1.
    Pedley, T. A., Mendiratta, A., and Walczak, T. S., Seizures and epilepsy. In: Ebersole, J. S., Pedley, T. A., (Eds.), Current Practice of Clinical Electroencephalography (pp 506–587). USA: Lippincott Williams and Wilkins, 2002.Google Scholar
  2. 2.
    Smith, S. J. M., EEG in neurological conditions other than epilepsy: When does it help, what does it add? J. Neurol. Neurosurg. Psychiatry. 76:8–12, 2005.CrossRefGoogle Scholar
  3. 3.
    Smith, S. J. M., EEG in diagnosis, classification, and management of patients with epilepsy. J. Neurol. Neurosurg. Psychiatry. 76:2–7, 2005.Google Scholar
  4. 4.
    King, M. A., Newton, M. R., and Jackson, G. D., et al, Epileptology of the first -seizure presentation: a clinical, electroencephalographic and magnetic resonance imaging study of 300 consecutive patients. Lancet. 352:1007–1011, 1998.CrossRefGoogle Scholar
  5. 5.
    Trescher, H. W., and Lesser, R. P., The epilepsies. In: Bradley, G. W., and Daroff, B. R., (Eds.), Neurology in Clinical Practice (pp 1745–1779). USA: Buterworth-Heineman, 2000.Google Scholar
  6. 6.
    Kiloh, L. G., McComas, A. J., and Osselton, J. W., Clinical electroencephalography. Great Britain: Butterworht, 1972.Google Scholar
  7. 7.
    Veezhinathan, M., and Ramakrishnan, S., Detection of obstructive respiratory abnormality using flow-volume spirometry and radial basis function neural networks. J. Med. Syst. 31:461–465, 2007.CrossRefGoogle Scholar
  8. 8.
    Srinivasan, V., Eswaran, C., and Sriraam, N., Artificial neural network based epileptic detection using time-domain and frequency-domain features. J. Med. Syst. 29(6):647–660, 2005.CrossRefGoogle Scholar
  9. 9.
    Ergun, U., et al, Classification of MCA stenosis in diabetes by MLP and RBF neural network. J. Med. Syst. 28(5):475–487, 2004.CrossRefGoogle Scholar
  10. 10.
    Yildirim, H., et al, Classification of the frequency of carotid Artery stenosis with MLP and RBF neural networks in patients with coroner artery disease. J. Med. Syst. 28(6):591–301, 2004.CrossRefGoogle Scholar
  11. 11.
    Gogou, G., Maglaveras, N., Ambrosiadou, B. V., Goulis, D., and Pappas, C., A neural network approach in diabetes management by insulin administration. J. Med. Syst. 25(2):119–131, 2001.CrossRefGoogle Scholar
  12. 12.
    Webber, W. R. S., Lesser, R. P., Richardson, R. T., and Wilson, K., An approach to seizure detection using an artificial neural network. Electroencephalogr. Clin. Neurophysiol. 98:250–272, 1996.CrossRefGoogle Scholar
  13. 13.
    Pradhan, N., Sadasivan, P. K., and Arunodaya, G. R., Detection of seizure activity in EEG by artificial neural network: A preliminary study. Comput. Biomed. Res. 29:303–313, 1996.CrossRefGoogle Scholar
  14. 14.
    Gabor, A. J., Seizure detection using a self-organizing neural network: validation and comparison with other detection strategies. Electroencephalogr. Clin. Neurophysiol. 107:27–32, 1998.CrossRefGoogle Scholar
  15. 15.
    Walczak, S., and Nowack, W. J., An artificial neural network to diagnosing epilepsy using lateralized burst of theta EEGs. J. Med. Syst. 25(1):9–20, 2001.CrossRefGoogle Scholar
  16. 16.
    Subasi, A., and Ercelebi, E., Classification of EEG signals using neural network and logistic regression. Comput. Methods Programs Biomed. 78:87–99, 2005.CrossRefGoogle Scholar
  17. 17.
    Alkan, A., Koklukaya, E., and Subasi, A., Automatic seizure detection in EEG using logistic regression and artificial neural network. J. Neurosci. Methods. 148:167–176, 2005.CrossRefGoogle Scholar
  18. 18.
    Guler, I., and Ubeyli, E. D., Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients. J. Neurosci. Methods. 148(2):113–121, 2005.CrossRefGoogle Scholar
  19. 19.
    Sahin C., Ogulata, S. N., Aslan, K., and Bozdemir, H., The application of neural networks in classification of epilepsy using EEG signals. Lect. Notes Comput. Sci. 4729:499–508, 2007.CrossRefGoogle Scholar
  20. 20.
    Kellaway, P., Orderly approach to visual analysis: Elements of the normal EEG and their characteristics in children and adults. In: Ebersole, J. S., and Pedley, T. A. (Eds.), Current Practice of Clinical Electroencephalography (pp. 100–159). Philadelphia: Lippincott Williams and Wilkins, 2002.Google Scholar
  21. 21.
    Krose, B., and Smaget, P. V. D., An introduction to neural networks. Amsterdam: The University of Amsterdam Press, 1996.Google Scholar
  22. 22.
    Haykin, S., Neural networks: A comprehensive foundation. New York: Macmillan, 1994.MATHGoogle Scholar
  23. 23.
    Duda, R. O., Hart, P. E., and Stork, D. G., Pattern classification. New York: Wiley, 2000.Google Scholar
  24. 24.
    Bernand, E., Optimization training neural nets. IEEE Trans. Neural. Netw. 3(2):989–993, 1992.Google Scholar
  25. 25.
    Hagan, M. T., and Menhaj, M. B., Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural. Netw. 5(6):989–993, 1994.CrossRefGoogle Scholar
  26. 26.
    Fontenla-Romero, O., Erdogmus, D., Principe, J. C., Alonso-Betanzos A. and Castillo E., Accelerating the converge speed of neural networks learning methods using least squares. European Symposium on Artificial Neural Networks (pp 255–260), 2003.Google Scholar
  27. 27.
    Wilamowki, B. M., Iqlikci, S., Kaynak, O., and Onder, E. M., An algorithm for fast converge in training neural networks. IEEE Proceedings of International Joint Conference on Neural Networks (pp 1778–1782), 2005.Google Scholar
  28. 28.
    Lera, G., and Pinzolas, M., A quasi-local Levenberg–Marquardt algorithm for neural network training. IEEE World Congress on Computational Intelligence. 3:2242–2246, 1998.Google Scholar
  29. 29.
    Manolis, I. A. L., and Antonis, A. A., Is Levenberg–Marquardt the most efficient optimization algorithm for implementing bundle adjustment. IEEE Proceedings of International Conference on Computer Vision. 2:1526–1531, 2005.Google Scholar
  30. 30.
    Lee, C., Chung, P., Tsai, J., and Chang, C., Robust radial basis function neural networks. IEEE Trans. Syst. Man Cybern., Part B, Cybern. 29:674–685, 1999.CrossRefGoogle Scholar
  31. 31.
    Ergun, U., Serhatlioglu, S., Hardalac, F., and Guler, I., Classification of carotid artery stenosis of the patients with diabetes by neural network and logistic regression. Comput. Biol. Med. 34:389–405, 2004.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Kezban Aslan
    • 1
  • Hacer Bozdemir
    • 1
  • Cenk Şahin
    • 2
  • Seyfettin Noyan Oğulata
    • 2
  • Rızvan Erol
    • 2
  1. 1.Department of Neurology, Faculty of MedicineCukurova UniversityAdanaTurkey
  2. 2.Department of Industrial Engineering, Faculty of Engineering and ArchitectureCukurova UniversityAdanaTurkey

Personalised recommendations