||When using Brain-Computer Interfaces (BCI) based on ElectroEncephaloGraphy (EEG), the identification of mental tasks
relies on two main points: feature extraction and classification [MAM+06, BFWB07, LCL+07]. Feature extraction aims at
describing EEG signals by a few relevant values called “features ”, whereas classification aims at automatically
assigning a class to these features. In this paper we focus on feature extraction, as the BCI community has stressed the
need to explore new feature extraction algorithms [MAM+06].
Recently, inverse models have been revealed as promising feature extraction algorithms for BCI [QDH04, GGP+05,
WGWB05, CLL06]. Such models aims at computing the activity in the whole brain volume, by using only scalp EEG
signals and a head model representing the brain as a set of voxels (volume elements). The activity computed in a few
brain regions has been used as features for BCI systems.
Despite good results, some limitations remain. Indeed, it seems that current methods cannot conciliate genericity, i.e., the
capability to deal with any kind of mental task, and the fact of generating few features. On one hand, methods that are
generic and automatic tend to generate a large number of features, as they extract several features for each voxel
[GGP+05]. The activity in neighboring voxels can be correlated and, as such, it would be more appropriate to gather these
voxels in brain regions. On the other hand, methods that generate few features have been proposed, but they are not
generic anymore as they need a priori knowledge on the mental tasks used, and are currently limited to motor imagerybased
BCI [QDH04, WGWB05]. Recently, we have proposed a method which is generic and which generates few features,
as voxels whose activity is correlated are gathered into Regions Of Interest (ROI) [CLL06]. However, this method is not
completely automatic and is limited to the use of two ROI whose spatial extension is hard to define [CLL06].
In this paper, we propose a generic feature extraction algorithm which can automatically identify any number of relevant
ROI and can properly define their spatial extension thanks to the new concept of fuzzy ROI. This algorithm is known as
FuRIA, which stands for “Fuzzy Region of Interest Activity”...