Abstract
To use in the Rapid Serial Visual Presentation (RSVP) KeyboardTM, a brain computer interface (BCI) typing system developed by our group, we propose a robust classification method of handling non-stationarity in the electroencephelography (EEG) data that is caused by artifacts and/or sensor failure. Considering the effect of these non-stationarities, we build a mixture data model to use as EEG evidence in the fusion with an n-gram language model to develop a robust classification algorithm. Using Monte Carlo simulations on the pre-recorded EEG data containing sections with or without intentionally generated artifacts we compare the typing performances of non-robust and robust classification methods in terms of speed and accuracy.
Chapter PDF
Similar content being viewed by others
References
Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., Muller, K.R.: Optimizing spatial filters for robust eeg single-trial analysis. IEEE Signal Processing Magazine 25(1), 41–56 (2008)
Nezamfar, H., Orhan, U., Erdogmus, D., Hild, K., Purwar, S., Oken, B., Fried-Oken, M.: On visually evoked potentials in eeg induced by multiple pseudorandom binary sequences for brain computer interface design. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2044–2047 (2011)
Krusienski, D.J., Sellers, E.W., McFarland, D.J., Vaughan, T.M., Wolpaw, J.R.: To- ward enhanced P300 speller performance. Journal of Neuroscience Methods 167(1), 15–21 (2008)
Treder, M., Blankertz, B. (C)overt attention and visual speller design in an erp- based brain-computer interface. Behavioral and Brain Functions 6(1), 28 (2010)
Friedman, J.H.: Regularized discriminant analysis. Journal of the American Statistical Association 84(405), 165–175 (1989)
Roark, B., de Villiers, J., Gibbons, C., Fried-Oken, M.: Scanning methods and lan- guage modeling for binary switch typing. In: The NAACL HLT 2010 Workshop on Speech and Language Processing for Assistive Technologies, p. 2836. Association for Computational Linguistics (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Higger, M., Akcakaya, M., Orhan, U., Erdogmus, D. (2013). Robust Classification in RSVP Keyboard. In: Schmorrow, D.D., Fidopiastis, C.M. (eds) Foundations of Augmented Cognition. AC 2013. Lecture Notes in Computer Science(), vol 8027. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39454-6_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-39454-6_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39453-9
Online ISBN: 978-3-642-39454-6
eBook Packages: Computer ScienceComputer Science (R0)