MLSP Competition, 2010: Description of third place method.

The MLSP competition (2010) purpose is to design a pattern recognition system for “mind reading”. This paper is a study of the EEG competition dataset and the crafting of the third place winning method. It shortly presents our signal processing methods for feature extraction, and channel selection. We accurately tuned all the parameters of these preprocessing stage before feeding a Gaussian SVM classifier. Without using any complex signal processing techniques nor strong neuroscience prior knowledge, we were able to build to a simple and fast agnostic classifier which achieves good performances.

[1]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[2]  K.-R. Muller,et al.  Linear and nonlinear methods for brain-computer interfaces , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  Vince D. Calhoun,et al.  The sixth annual MLSP competition, 2010 , 2010, 2010 IEEE International Workshop on Machine Learning for Signal Processing.

[4]  Alain Rakotomamonjy,et al.  BCI Competition III: Dataset II- Ensemble of SVMs for BCI P300 Speller , 2008, IEEE Transactions on Biomedical Engineering.