Animation Effects Challenge Intention Decoding from EEG in Active Visual Search

Uscumlic, Marija ;   Blankertz, Benjamin

Motivated by the non-stationarity of our natural visual environment, we demonstrate that dynamic visual scenes challenge EEG-based intention decoding in active visual search task due to increased temporal uncertainty of the cognition-related EEG activity with reference to fixation onset. Importantly, we propose a method to overcome this issue by exploiting the knowledge obtained in a constrained experimental condition. This is of high importance for a symbiosis of modern brain-computer interface technology with human-computer interaction applications that aims at constant performance irrespective of the animation effects (e.g., the visual effects in human-computer interfaces).