Advertisement

Adaptive RBF-HMM Bi-Stage Classifier Applied to Brain Computer Interface

  • José Luis Martínez Pérez
  • Antonio Barrientos Cruz
Part of the Communications in Computer and Information Science book series (CCIS, volume 127)

Abstract

Brain Computer Interface is a new technology aimed to communicate the user’s intentions without using nerves or muscles. To obtain this objective, BCI devices make use of classifiers which translate inputs from the user’s brain signals into commands for external devices. This paper describes an adaptive bi-stage classifier based on RBF neural networks and Hidden Markov Models. The first stage analyses the user’s electroencephalografic input signal and provides sequences of pre-assignations to the second stage. The segment of EEG signal is assigned to the HMM with the highest probability of generating the pre-assignation sequence.

The algorithm is tested with real samples of electroencephalografic signal, from five healthy volunteers using the cross-validation method. The results allow to conclude that it is possible to implement this algorithm in an on-line BCI device, but a huge dependency in the percentage of the correct classification from the user and the setup parameters has been detected.

Keywords

Electroencephalography Brain computer interface Linear discriminant analysis Spectral analysis Biomedical signal detection Pattern recognition 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Vidal, J.J.: Toward direct brain-computer communication (1973)Google Scholar
  2. 2.
    Wolpaw, J.R., et al.: Brain-Computer Interface Technology: A Review of the First International Meeting. IEEE Trans. on Reh. Eng. 8(2), 164–171 (2000)CrossRefGoogle Scholar
  3. 3.
    Birbaumer, N., et al.: The thought translation device (TTD) for completely paralyzed patients. IEEE Trans. on Reh. Eng. 8(2), 190–193 (2000)CrossRefGoogle Scholar
  4. 4.
    Wolpaw, J.R., et al.: Brain-Computer interface for communication and control. Clinical Neurophysiology 113, 767–791 (2002)CrossRefGoogle Scholar
  5. 5.
    Donchin, E., Spencer, K.M., Wijesinghe, R.: The mental prosthesis: assessing the speed of a P300-based brain-computer interface. IEEE Transactions on Rehabilitation Engineering 8(2), 174–179 (2000)CrossRefGoogle Scholar
  6. 6.
    Kostov, A., Polak, M.: Parallel man-machine training in development of EEG-based cursor control. IEEE Trans. on Reh. Eng. 8(2), 203–205 (2000)CrossRefGoogle Scholar
  7. 7.
    Pfurtscheller, et al.: Current trends in Graz brain-computer interface (BCI) research. IEEE Trans. on Reh. Eng. 8(2), 216–219 (2000)CrossRefGoogle Scholar
  8. 8.
    Pfurtscheller, et al.: Brain oscillations control hand orthosis in a tetraplegic. Neuroscience Letters 1(292), 211–214 (2000)CrossRefGoogle Scholar
  9. 9.
    Pineda, J.A., et al.: Learning to Control Brain Rhythms: Making a Brain-Computer Interface Possible. IEEE Trans. on Reh. Eng. 11(2), 181–184 (2003)CrossRefGoogle Scholar
  10. 10.
    Ripley, B.: Pattern Recognition and Neural Networks, 2nd edn. Cambridge University Press, London (2000)Google Scholar
  11. 11.
    Penny, W.D., et al.: EEG-based communication: A pattern recognition approach. IEEE Trans. on Reh. Eng. 8(2), 214–215 (2000)CrossRefGoogle Scholar
  12. 12.
    Neuper, C., et al.: Motor Imagery and Direct Brain-Computer Communication. Proceedings of the IEEE 89(7), 1123–1134 (2001)CrossRefGoogle Scholar
  13. 13.
    Proakis, J.G., Manolakis, D.G.: Tratamiento digital de señales: [principios, algoritmos y aplicaciones]. Prentice-Hall, Madrid (1997)Google Scholar
  14. 14.
    Martinez, J.L., Barrientos, A.: The windowing Effect in Cerebral Pattern Classification. In: An Application to BCI Technology. IASTED Biomedical Engineering BioMED 2006, pp. 1186–1191 (February 2006)Google Scholar
  15. 15.
    Martinez, J.L., Barrientos, A.: Brain Computer Interface. Comparison of Neural Networks Classifiers. In: Proceedings of the BIODEVICES International Conference on Biomedical Electronics and Devices, vol. 1(1), pp. 3–10 (January 2008)Google Scholar
  16. 16.
    Martinez, J.L., Barrientos, A.: Linear Discriminant Analysis on Brain Computer Interface. In: IEEE International Symposium on Intelligent Signal Processing, Conference Proceedings Book, pp. 859–864 (October 2007) Google Scholar
  17. 17.
    Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition (February 1989)Google Scholar
  18. 18.
    Rabiner, L.R., Juang, B.H.: An Introduction to Hidden Markov Models (January 1986)Google Scholar
  19. 19.
    Martinez, J.L., Barrientos, A.: Brain Computer Interface. In: Application of an adaptive bi-stage classifier based on RBF-HMM, Proceedings of the BIODEVICES International Conference on Biomedical Electronics and Devices, vol. 1(1), pp. 13–20 (January 2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • José Luis Martínez Pérez
    • 1
  • Antonio Barrientos Cruz
    • 1
  1. 1.Grupo de Robótica y CibernéticaUniversidad Politécnica de MadridMadridSpain

Personalised recommendations