Logo image
Back
EEG band powers for characterizing user engagement in P300-BCI
Conference paper

EEG band powers for characterizing user engagement in P300-BCI

Yichuan Yichuan Liu, Hasan Ayaz, Banu Onaral and Patricia A Shewokis
2013 6th International IEEE/EMBS Conference on Neural Engineering (NER), pp 1066-1069
Nov 2013
DOI: https://doi.org/10.1109/NER.2013.6696121

Abstract

Band-pass filters Feature extraction Educational institutions Brain-computer interfaces Testing Biomedical Engineering Electroencephalography
An asynchronous P300-based brain computer interface (BCI) allows users to operate the BCI at their own pace by being able to detect a user's engagement. In our previous work, band powers has been shown to be able to provide additional information for characterizing user engagement and yielded better performance compared to the use of only the amplitudes of event-related potentials. In this follow up study, 19 subjects participated in an experiment which was designed to further evaluate additional predictors of user engagement using band powers. In addition to the regular P300 attended condition, two not-engaged conditions were considered: one with the P300 stimulus matrix still shown (control 1) and the other with stimulus covered by a blank screen (control 2). Alpha and beta band activities decreased in the order of control 2, control 1 and attended. Furthermore, the attended condition had lower delta activity compared to the control conditions. Classification results indicated that band powers were better at differentiating attended and control 2 conditions. Using band powers as additional features resulted in a moderate to moderately large (dz= 0.52 to 0.74) improvement over the classification of the two conditions.

Metrics

14 Record Views
4 citations in Scopus

Details

Logo image