Single trial P300 detection in children using expert knowledge and SOM

Preliminary results of an automatic system for single trial P300 visual evoked potential events detection are presented. For each single trial P300, several candidate events were generated, and then filtered, using 3 wave features. The surviving candidate events were fed into a SOM-based classifier. A context filter was applied before the final output. No stationary condition of the P300 is involved in the algorithms. Recordings of 27 assessment sessions, each with 120 trials, were visually inspected by experts to identify and mark the P300 events, which was accomplished in about one third of the trials. The dataset was divided in training (18) and testing (9) subsets. The system identifies the initial and end times of the P300; it obtained a sensitivity of 53.9%, a specificity of 64.0% and an accuracy of 61.2% in the testing dataset.