The EOG event recognition method in an EEG signal towards SSVEP BCI improvement
[ 1 ] Instytut Automatyki i Inżynierii Informatycznej, Wydział Elektryczny, Politechnika Poznańska | [ 2 ] Wydział Elektryczny, Politechnika Poznańska | [ P ] pracownik | [ D ] doktorant
2015
artykuł naukowy
angielski
- hybrid BCI
- EEG
- EOG artifact
- SSVEP
- tree classifier
EN This paper presents a method of recognizing EOG artifacts in an EEG signal. Moreover, it shows the possibility of determining the direction of eye movement. The idea behind this method is to develop a hybrid brain computer interface relying on SSVEP phenomena and EOG artifacts acquired from the EEG signal. Recognition of an EOG event and its direction can be used to improve the SSVEP detection accuracy, overall system responsiveness, and increase the information transfer rate (ITR). Eye movement direction is recognized using a decision tree and histogram based features calculated from EEG signals recorded in Fp1-O1 and Fp2-O2 points. The accuracy of 75% was achieved for a group of 8 subjects, while the average precision of detecting movement direction in horizontal plane was 78%.
376 - 378
11