Classification of multichannel EEG recordings during motor imagination has been exploited successfully for brain-computerinterfaces (BCI). In this paper, we consider EEG signals as the outputs of a networked dynamical system (the cortex), and exploitsynchronization features from the dynamical system for classification. Herein, we also propose a new framework forlearning optimal filters automatically from the data, by employing a Fisher ratio criterion. Experimental evaluations comparing theproposed dynamical system features with the CSP and the AR features reveal their competitive performance duringclassification. Results also show the benefits of employing the spatial and the temporal filters optimized using the proposed learning approach.
展开▼
