Decoding SSVEP responses based on PARAFAC decomposition

摘要

In this position paper, we investigate whether a parallel factoranalysis (Parafac) decomposition is beneficial to the decoding ofsteady-state visual evoked potentials (SSVEP) present inelectroencephalogram (EEG) recordings taken from the subject's scalp. Inparticular, we develop an automatic algorithm aimed at detecting thestimulation frequency after Parafac decomposition. The results arevalidated on recordings made from 54 subjects using consumer-grade EEGhardware (Emotiv's EPOC headset) in a real-world environment. Thedetection of one frequency among 12, 4 and 2 possible was consideredto assess the feasibility for Brain Computer Interfacing (BCI).We determined the frequencies subsets, among all subjects, that maximizethe detection rate.