Channel Selection in EEG-based Prediction of Shoulder/Elbow Movement Intentions involving Stroke Patients: A Computational Approach

Brain computer interface (BCI) has gained a lot of attention recently, as a means to detect individuals´ intents using brain signals such as electroencephalographic (EEG) for control of machines. In order to achieve the possible use of BCI in stroke rehabilitation, computational intelligent algorithms are important for reliable separation of shoulder versus elbow movement intentions. Efforts have been made on developing data processing and classification algorithm for such task. Differently, this paper investigates the optimal use of electrodes and signal channels, which is formulated as a data-driven feature selection problem. 163 EEG electrodes are used to collect scalp recordings to predict shoulder abduction and elbow flexion intentions in healthy and stroke subjects. We combine the support vector channel selection with a time-frequency synthesized classification algorithm and examine the performances of using different subsets of channel inputs. Preliminary results show that 1) a reduced number of electrodes can be used to achieve the same or better performance than using the full set of signal channels; 2) besides the fact that the accuracy on able-bodied subjects is expectedly higher than the stroke subject, the stroke subject tends to need more electrodes to achieve the best performance; 3) visualization of spatial distribution of channel rankings shows reasonable connection with functional motor cortex areas