PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Subject-independent mental state classification in single trials
Siamac Fazli, Florin Popescu, Marton Danoczy, Benjamin Blankertz, Klaus-Robert Müller and Cristian Grozea
Neural Networks Volume 22, Number 9, pp. 1305-1312, 2009.

Abstract

Current state of the art in Brain Computer Interfacing (BCI) involves tuning classifiers to subject-specific training data acquired from calibration sessions prior to functional BCI use. Using a large database of EEG recordings from 45 subjects, who took part in movement imagination task experiments, we construct an ensemble of classifiers derived from subject-specific temporal and spatial filters. The ensemble is then sparsified using quadratic regression with L1 regularization such that the final classifier generalizes reliably to data of subjects not included in the ensemble. Our offline results indicate that BCI-na¨ıve users could start real-time BCI use without any prior calibration at only very limited loss of performance.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Brain Computer Interfaces
ID Code:6455
Deposited By:Stefan Haufe
Deposited On:08 March 2010