EEG error-related potentials detection with a Bayesian filter

Several studies describe evoked EEG potentials elicited when a subject is aware of an erroneous decision either taken by him or by an external interface. This paper try to detect Error-related potentials (ErrP) elicited when a human user want to monitors an external system upon which he has no control whatsoever. To this end we use a Bayesian filter to classify erroneous or correct events. On average over three subjects, the proposed probabilistic classifier achieves single-trial classification of 85% for correct trials and 71% for erroneous trials.