The Berlin brain-computer interface: EEG-based communication without subject training

摘要: The Berlin Brain-Computer Interface (BBCI) project develops a noninvasive BCI system whose key features are 1) the use of well-established motor competences as control paradigms, 2) high-dimensional from 128-channel electroencephalogram (EEG), and 3) advanced machine learning techniques. As reported earlier, our experiments demonstrate that very high information transfer rates can be achieved using readiness potential (RP) when predicting laterality upcoming left- versus right-hand movements in healthy subjects. A more recent study showed RP similarly accompanies phantom arm amputees, but signal strength decreases with longer loss limb. In complementary approach, oscillatory used to discriminate imagined (left hand right foot). feedback six subjects no or little experience control, three an rate above 35 bits per minute (bpm), further two 24 15 bpm, while one subject could not achieve any control. These results encouraging for EEG-based untrained is independent peripheral nervous activity does rely on evoked potentials even compared well-trained operating other systems.