Multi-direction hand movement classification using EEG-based source space analysis

Recent advances in the brain-computer interfaces (BCIs) have demonstrated the inference of movement related activity using non-invasive EEG. However, most of the sensorspace approaches that study sensorimotor rhythms using EEG do not reveal the underlying neurophysiological phenomenon while executing or imagining the movement with finer control. Therefore, there is a need to examine feature extraction techniques in the cortical source space which can provide more information about the task compared to sensor-space. In this study, we extend the traditional sensor-space feature extraction method, Common Spatial Pattern (CSP), to the source space, using various regularization approaches. We use Weighted Minimum Norm Estimate (wMNE) as a source localization technique. We show that for a multi-direction hand movement classification problem, the source space features can result in an increase of over 10% accuracy compared to sensor space features. Fisher's Linear Discriminant (FLD) classifier with the One-versus-rest approach is used for the classification.