Comparison of EEG signal preprocessing methods for SSVEP recognition

Abstract

This study was carried out to select EEG signal preprocessing methods to effectively detect and classify Steady State Visually Evoked Potentials (SSVEP). Algorithms, such as: Common Average Reference, Independent Component Analysis (in the task of electrooculography artifacts removing and SSVEP enhancement) and combinations of them were implemented and tested. The best classification accuracy improvement was obtained for CAR and ICA-SSVEP preprocessing methods. Experiments showed high usefulness of these methods in the context of SSVEP detection.