ℓ1-Penalized Linear Mixed-Effects Models for BCI
A recently proposed novel statistical model estimates population effects and individual variability between subgroups simultaneously, by extending Lasso methods. We apply this ℓ1-penalized linear regression mixed-effects model to a large scale real world problem: by exploiting a large set of brain computer interface data we are able to obtain a subject-independent classifier that compares favorably with prior zero-training algorithms. This unifying model inherently compensates shifts in the input space attributed to the individuality of a subject. In particular we are now able to differentiate within-subject and between-subject variability. A deeper understanding both of the underlying statistical and physiological structure of the data is gained.
Unable to display preview. Download preview PDF.
- 1.Andrew, G., Gao, J.: Scalable training of L 1-regularized log-linear models. In: Proceedings of the 24th international conference on Machine learning (ICML 2007), pp. 33–40. ACM Press, New York (2007)Google Scholar
- 2.Blankertz, B., Curio, G., Müller, K.R.: Classifying single trial EEG: Towards brain computer interfacing. In: Diettrich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Inf. Proc. Systems (NIPS 2001), vol. 14, pp. 157–164 (2002)Google Scholar
- 5.Dornhege, G., Millán, J.R., Hinterberger, T., McFarland, D., Müller, K.R. (eds.): Toward Brain-Computer Interfacing. MIT Press, Cambridge, MA (2007)Google Scholar
- 6.Fazli, S., Grozea, C., Danoczy, M., Blankertz, B., Popescu, F., Muller, K.R.: Subject independent EEG-based BCI decoding. In: Advances in Neural Information Processing Systems 22, pp. 513–521. MIT Press, Cambridge (2009)Google Scholar
- 7.Fazli, S., Danóczy, M., Schelldorfer, J., Müller, K.R.: ℓ1-penalized Linear Mixed-Effects Models for high dimensional data with application to BCI. Neuroimage (2011), (in press)Google Scholar
- 8.Krauledat, M., Tangermann, M., Blankertz, B., Müller, K.R.: Towards zero training for brain-computer interfacing. PLoS ONE 3, e2967 (2008)Google Scholar
- 10.Schelldorfer, J., Bühlmann, P.: Estimation for high-dimensional linear mixed-effects models using ℓ1-penalization. arXiv preprint 1002.3784 (2010)Google Scholar