Decoding Steady-State VisualEvoked Potentials(SSVEPs)- Implementation and Performance Analysis

Sammanfattning: Steady-state visual evoked potential (SSVEP)-based brain-computer interfaces(BCIs) have been widely investigated. Algorithms from the canonical correlation analysis(CCA) family perform extremely well in detecting stimulus targets by analyzing the relationship of frequency features between electroencephalogram (EEG) signals and stimulus targets. In addition to CCA algorithms, convolutional neural networks(CCNs) also improve the performance of SSVEP-based BCIs by generalizing well on the frequency features of the EEG signals. To find a new method for speeding up an online SSVEP decoding system, we have evaluated three CCA methods which are standard CCA, individual-template CCA(IT-CCA), and Extended CCA, together with the complex spectrum CNN(C-CNN). The results have proved that algorithms requiring individual subject training highly outperform standard CCA.