Spatial filters selection towards a rehabilitation BCI

Introducing BCI technology in supporting motor imagery (MI) training has revealed the rehabilitative potential of MI, contributing to significantly better motor functional outcomes in stroke patients. To provide the most accurate and personalized feedback during the treatment, several stages of the electroencephalographic signal processing have to be optimized, including spatial filtering. This study focuses on data-independent approaches to optimize spatial filtering step. Specific aims were: i) assessment of spatial filters' performance in relation to the hand and foot scalp areas; ii) evaluation of simultaneous use of multiple spatial filters; iii) minimization of the number of electrodes needed for training. Our findings indicate that different spatial filters showed different performance related to the scalp areas considered. The simultaneous use of EEG signals conditioned with different spatial filters could either improve classification performance or, at same level of performance could lead to a reduction of the number of electrodes needed for successive training, thus improving usability of BCIs in clinical rehabilitation context.