Date(s) : 13/06/2014 iCal
14 h 00 min - 15 h 00 min
Finding EEG Space-time-scale localized features using Matrix-based penalized discriminant analysis\nBy Juliette Spinnato\, I2M\n\nIn this talk we will explain a new method for constructing and selecting of discriminant space-time-scale features for electroencephalogram\n(EEG) signal classification\, suitable for Error Related Potentials (ErrP) detection in brain-computer interface (BCI). The method rests\non a new variant of matrix-variate Linear Discriminant Analysis (LDA)\, and differs from previously proposed approaches in mainly\nthree ways.\nFirst\, a discrete wavelet expansion is introduced for mapping time-courses to time-scale coefficients\, yielding time-scale localized features.\nSecond\, the matrix-variate LDA is modified in such a way that it yields an interesting duality property\, that makes interpretation easier.\nThird\, a space penalization is introduced using a surface Laplacian\, so as to enforce spatial smoothness.\nThe proposed approaches\, termed D-MLDA and D-MPDA are tested on EEG signals\, with the goal of detecting ErrP. Numerical results\nshow that D-MPDA outperforms D-MLDA and other matrix-variate LDA techniques. In addition this method produces relevant features\nfor interpretation in ErrP signals.
Catégories Pas de Catégories