Classifying Ecog Signals Prior To Voluntary Movement Onset

Recently, in brain-computer interface (BCI) researches, earlier neural signals have allowed researchers to reduce the time gap between a subject's real action and the BCI response. The aims of this study were to use pre-movement signals to predict motor tasks, and to decide whether the prefrontal area, which has been recognized as generating pre-movement signals that reflect motor intention or preparation, generates useful pre-movement signals. Six patients with intractable epilepsy participated in this study and performed self-paced hand grasping and elbow flexion while electrocorticography (ECoG) was recorded. The electrodes that showed clear power differences in a specific frequency band between two different movements were chosen at a preparatory stage (-2.0 s to 0 s). The average value of the squared power of the signal sample was extracted for the feature. A support vector machine (SVM) was used as a classifier. A total of twelve electrodes differentiating hand grasping and elbow flexion were selected. Four electrodes were placed on the prefrontal area. The average prediction rate was 74% (range, 55.4 to 99.3%) across the six subjects. The successful prediction of movement intention indicates that the prefrontal area may generate useful pre-movement signals and implies that our approach could produce BCI response faster than a subject's real actions.