Classification of movement-related EEG in a memorized delay task experiment

Objectives: We studied the activation of cortical motor areas during a memo rized delay task with a classification technique. Methods: Multichannel EEG was recorded during the sequence of warning stimu lus, visual cue, reaction stimulus, and actual execution of hand or foot mo vements. Two different approaches are presented: first, we trained a classi fier on data from the time segments immediately preceding the actual moveme nts, and analyzed the whole recordings in overlapping segments with this fi xed classifier. The classification rates obtained as a function of experime ntal time reflect the activation of the same cortical areas that are active during the actual movements. In the second approach, we trained classifier s on data segments with the same latency in time as the data tested ('runni ng classifiers'). By this, we checked whether we could detect event-related activity sufficiently marked to allow for correct classification. Results: With the fixed classifier approach we found two maxima of classifi cation: one maximum after processing of the visual cue corresponding to an activation of motor cortex without overt movement, and a second maximum at the rime of the actual movement. The first maximum relates to a very short- lived brain state, in the order of 300 ms, while the broad second maximum ( 1.5 s) indicates a very stable and long-lasting activation. Conclusions: With the running classifier approach we found similar maxima a s with the fixed classifier, indicating that only the activity of motor are as is relevant for classification. Possible implications of our findings fo r the development of a brain computer interface (BCI) are discussed. (C) 20 00 Elsevier Science Ireland Ltd. All rights reserved.