A Channel Selection Method for Epileptic EEG Signals

  • Satarupa Chakrabarti
  • Aleena SwetapadmaEmail author
  • Prasant Kumar Pattnaik
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 755)


Epilepsy is a disorder of the central nervous system in which a considerably large number of neurons at a certain instance of time show abnormal electrical activity. EEG or electroencephalogram signals plays a significant role in the diagnosis of epilepsy. Worldwide roughly 50 million people are affected by epilepsy that includes patients from all walks of life. In this paper we have studied the performance of artificial neural network (ANN) on EEG signals (CHB-MIT database) by applying principal component analysis (PCA) for selection of channels. The results reflect the performance of the neural network in different configuration. Out of the 23 channels considered, after using PCA, the highest accuracy of 86.7% is achieved with 18 channels. With the reduction of channels the accuracy decreased simultaneously. The study also brings forth the shortcomings as well as determines the area in this domain that holds prospective for future scope of work.


  1. 1.
    Aarabi, A., Fazel-Rezai, R., Aghakhani, Y.: A fuzzy rule-based system for epileptic seizure detection in intracranial EEG. Clin. Neurophysiol. 120(9), 1648–1657 (2009)Google Scholar
  2. 2.
    Abraham, A.: Artificial neural networks. In: Sydenham, P.H. (ed.) Handbook of Measuring System Design. Wiley, New York (2005)Google Scholar
  3. 3.
    Adeli, H., Ghosh-Dastidar, S., Dadmehr, N.: A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy. IEEE Trans. Biomed. Eng. 54(2), 205–211 (2007)Google Scholar
  4. 4.
    Bizopoulos, P.A., Tsalikakis, D.G., Tzallas, A.T.: EEG epileptic seizure detection using k-means clustering and marginal spectrum based on ensemble empirical mode decomposition. In: IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE), Chania, Greece (2013)Google Scholar
  5. 5.
    Gajic, D., Djurovic, Z., Di Gennaro, S., et al.: Classification of EEG signals for detection of epileptic seizures based on wavelets and statistical pattern recognition. Biomed Eng Appl Basis Commun 26(02) (2014)Google Scholar
  6. 6.
    Giannakakis, G., Sakkalis, V., Pediaditis, M., et al.: Methods for seizure detection and prediction: an overview. In: Modern Electroencephalographic Assessment Techniques, 131–157. Humana Press, New York (2014)Google Scholar
  7. 7.
    Jolliffe, I.T.: Principal component analysis and factor analysis. In: Principal Component Analysis, 2nd edn. Springer, New York (2013)Google Scholar
  8. 8.
    Minasyan, G.R., Chatten, J.B., Chatten, M.J., et al.: Patient-specific early seizure detection from scalp EEG. J. Clin. Neurophys. 27(3), 163 (official publication of the American Electroencephalographic Society)Google Scholar
  9. 9.
    Nanthini, B.S., Santhi, B.: Seizure detection using SVM classifier on EEG signal. J. Appl. Sci. 14(14), 1658–1661 (2014)Google Scholar
  10. 10.
    Orosco, L., Correa, A.G., Laciar, E.: A survey of performance and techniques for automatic epilepsy detection. J. Med. Biol. Eng. 33(6), 526–537 (2013)Google Scholar
  11. 11.
    Parvez, M.Z., Paul, M.: Epileptic seizure detection by analyzing EEG signals using different transformation techniques. Neurocomputing 145, 190–200 (2014)Google Scholar
  12. 12.
    Physionet CHB-MIT Scalp EEG Database: Boston. (2010)
  13. 13.
    Ramgopal, S., Thome-Souza, S., Jackson, M., et al.: Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy. Epilepsy Behav. 37, 291–307 (2014)Google Scholar
  14. 14.
    Rojas, R.: Neural Networks: A Systematic Introduction. Springer Science & Business Media, Netherlands (2013)Google Scholar
  15. 15.
    Saab, M.E., Gotman, J.: A system to detect the onset of epileptic seizures in scalp EEG. Clin. Neurophysiol. 116(2), 427–442 (2005)Google Scholar
  16. 16.
    Sharmila, A., Geethanjali, P.: DWT based detection of epileptic seizure from EEG signals using naive Bayes and k-NN classifiers. IEEE Access 4, 7716–7727 (2016)Google Scholar
  17. 17.
    Shoeb, A.H.: Application of machine learning to epileptic seizure onset detection and treatment. Dissertation, Massachusetts Institute of Technology (2009)Google Scholar
  18. 18.
    Smith, L.I.: A Tutorial on Principal Components Analysis. Cornell University, USA (2002)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Satarupa Chakrabarti
    • 1
  • Aleena Swetapadma
    • 1
    Email author
  • Prasant Kumar Pattnaik
    • 1
  1. 1.KIIT UniversityBhubaneswarIndia

Personalised recommendations