Skip to main content
SpringerLink
Log in

Comparison of Feature Extraction Methods for EEG BCI Classification

  • Conference paper
  • First Online:
Information and Software Technologies (ICIST 2015)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 538))

Included in the following conference series:

Abstract

This work analyzes several feature extraction methods used in today’s EEG BCI (electro-encephalogram brain computer interface) classification systems. Comparison of multiple EEG energy algorithms is presented for solving a 4-class motor imagery BCI classification problem. Furthermore, multiple feature vector generation techniques are employed into analysis. The effectiveness of CSP (common spatial pattern) filtering method in preprocessing step is shown. Channel difference feature extraction method is presented. It is discussed that key aim in today’s EEG signal analysis should be dedicated to finding more accurate techniques for determining better quality features. Initial tests prove that static feature extraction methods are not optimal and adaptive algorithms are required to overcome subject specific EEG signal variations. Further work and new dynamic feature extraction methods are required to solve the problem.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

References

  1. Brodu, N., et al.: Comparative study of band-power extraction techniques for motor imagery classification. In: IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB), pp. 1–6 (2011)

    Google Scholar 

  2. Pfurtscheller, G., et al.: Graz-Brain-Computer Interface: State of Research, pp. 65–84. MIT Press, Cambridge (2007)

    Google Scholar 

  3. Kaiser, JF.: On a simple algorithm to calculate the energy of a signal. In: IEEE International Conference on Acoustic Speech Signal Process, Albuquerque, NM (1990)

    Google Scholar 

  4. Martišius, I., et al.: Using higher order nonlinear operators for SVM classification of EEG data. Elektronika ir Elektrotechnika 119(3), 99–102 (2012)

    Article  Google Scholar 

  5. Dolezal, J., Cerny, V., Stastny, J.: Online motor-imagery based BCI. In: International Conference on Applied Electronics (AE), pp. 65–68, 5–7 (2012)

    Google Scholar 

  6. Tandonnet, C., Burle, B., Hasbroucq, T., Vidal, F.: Spatial enhancement of EEG traces by surface Laplacian estimation: comparison between local and global methods. Clin. Neurophysiol. 116, 18–24 (2005)

    Article  Google Scholar 

  7. Qin, L., He, B.: A wavelet-based time-frequency analysis approach for classification of motor imagery for brain-computer interface applications. J. Neural Eng. 2, 65–72 (2005)

    Article  Google Scholar 

  8. Müller-Gerking, J., et al.: Designing optimal spatial filters for single-trial EEG classification in a movement task. Clin. Neurophysiol. 110(5), 787–798 (1999)

    Article  Google Scholar 

  9. Thang, L.Q., Temiyasathit, C.: Increase performance of four-class classification for motor-imagery based brain-computer interface. In: 2014 International Conference on Computer, Information and Telecommunication Systems (CITS), pp. 1–5, 7–9 (2014)

    Google Scholar 

  10. Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugenics 7, 179–188 (1936)

    Article  Google Scholar 

  11. Ben-Hur, A., Weston, J.: A user’s guide to support vector machines. In: Carugo, O., Eisenhaber, F. (eds.) Data Mining Techniques for the Life Sciences. Methods in Molecular Biology, vol. 609, pp. 223–239. Humana Press, New York (2010)

    Chapter  Google Scholar 

  12. Szachewicz, P.: Classification of Motor Imagery for Brain-Computer Interfaces. Master’s thesis, Poznan University of Technology, Poznan (2013)

    Google Scholar 

  13. Hsu, C.-W., et al.: A Practical Guide to Support Vector Classification. National Taiwan University, Taiwan (2010)

    Google Scholar 

  14. Brunner, C., et al.: BCI Competition 2008 – Graz data set A (2008). https://www.bbci.de/competition/iv/desc_2a.pdf

  15. Schlogl, A., et al.: Evaluation criteria in BCI research. In: Dornhege, G., del Millan, J.R., Hinterberger, T., McFarland, D.J., Muller, K.-R. (eds.) Toward Brain-Computer Interfacing, pp. 327–342. MIT Press, Cambridge (2007)

    Google Scholar 

  16. Ang, K.K., et al.: Filter bank common spatial pattern (FBCSP) in brain-computer interface. In: Neural Networks, IJCNN 2008. IEEE World Congress on Computational Intelligence, pp. 2390–2397, 1–8 June 2008

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Software Engineering Department, Kaunas University of Technology, Studentu St. 50, Kaunas, Lithuania

    Tomas Uktveris & Vacius Jusas

Authors
  1. Tomas Uktveris
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vacius Jusas
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tomas Uktveris .

Editor information

Editors and Affiliations

  1. Kaunas University of Technology, Kaunas, Lithuania

    Giedre Dregvaite

  2. Kaunas University of Technology, Kaunas, Lithuania

    Robertas Damasevicius

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Uktveris, T., Jusas, V. (2015). Comparison of Feature Extraction Methods for EEG BCI Classification. In: Dregvaite, G., Damasevicius, R. (eds) Information and Software Technologies. ICIST 2015. Communications in Computer and Information Science, vol 538. Springer, Cham. https://doi.org/10.1007/978-3-319-24770-0_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-24770-0_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-24769-4

  • Online ISBN: 978-3-319-24770-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation