IMPROVING CLASSIFICATION FOR BRAIN COMPUTER INTERFACES USING TRANSITIONS AND A MOVING WINDOW

Ricardo Aler, Inés M. Galván, José M. Valls

2009

Abstract

The context of this paper is the brain-computer interface (BCI), and in particular the classification of signals with machine learning methods. In this paper we intend to improve classification accuracy by taking advantage of a feature of BCIs: instances run in sequences belonging to the same class. In that case, the classification problem can be reformulated into two subproblems: detecting class transitions and determining the class for sequences of instances between transitions. We detect a transition when the Euclidean distance between the power spectra at two different times is larger than a threshold. To tackle the second problem, instances are classified by taking into account, not just the prediction for that instance, but a moving window of predictions for previous instances. Our results are competitive with those obtained in the BCI III competition.

References

  1. Curran, E. and Stokes, M. (2003). Learning to control brain activity: a review of the production and control of eeg components for driving braincomputer interface (bci) systems. Brain Cognition, 51.
  2. Dornhege, G., Krauledat, M., Muller, K.-R., and Blankertz, B. (2007). Toward Brain-Computer Interfacing, chapter General Signal Processing and MAchine Learning Tools for BCI Analysis, pages 207-234. MIT Press.
  3. G. Pfurtscheller, C. N. and Birbaumer, N. (2005). Motor Cortex in Voluntary Movements, chapter 14, pages 367-401. CRC Press.
  4. Galan, F., Oliva, F., and Guardia, J. (2005). Bci competition iii. data set v: Algorithm description. In Brain Computer Interfaces Competition III.
  5. Gan, J. Q. and Tsui, L. C. (2005). Bci competition iii. data set v: Algorithm description. In Brain Computer Interfaces Competition III.
  6. Garner, S. (1995). Weka: The waikato environment for knowledge analysis. In S.R. Garner. WEKA: The waikato environment for knowledge analysis. In Proc. of the New Zealand Computer Science Research Students Conference, pages 57-64.
  7. Millán, J. (2004). On the need for on-line learning in brain-computer interfaces. In Proceedings of the International Joint Conference on Neural Networks, Budapest, Hungary. IDIAP-RR 03-30.
  8. Millan J del R, Renkens F, M. J. and Gerstner, W. (2004). Noninvasive brain-actuated control of a mobile robot by human eeg. IEEE Trans Biomed Eng, 51.
  9. Vapnik, V. (1998). Statistical Learning Theory. John Wiley and Sons.
Download


Paper Citation


in Harvard Style

Aler R., Galván I. and Valls J. (2009). IMPROVING CLASSIFICATION FOR BRAIN COMPUTER INTERFACES USING TRANSITIONS AND A MOVING WINDOW . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009) ISBN 978-989-8111-65-4, pages 65-71. DOI: 10.5220/0001535800650071


in Bibtex Style

@conference{biosignals09,
author={Ricardo Aler and Inés M. Galván and José M. Valls},
title={IMPROVING CLASSIFICATION FOR BRAIN COMPUTER INTERFACES USING TRANSITIONS AND A MOVING WINDOW},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009)},
year={2009},
pages={65-71},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001535800650071},
isbn={978-989-8111-65-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2009)
TI - IMPROVING CLASSIFICATION FOR BRAIN COMPUTER INTERFACES USING TRANSITIONS AND A MOVING WINDOW
SN - 978-989-8111-65-4
AU - Aler R.
AU - Galván I.
AU - Valls J.
PY - 2009
SP - 65
EP - 71
DO - 10.5220/0001535800650071