Principal component analysis-based spectral recognition for SSVEP-based Brain-Computer Interfaces

Utilizing brain activity to interact with the external environment is no longer impossible thanks to recent advances in developing Brain-Computer Interfaces (BCIs). This paper proposes a novel recognition method for Steady-State Visual Evoked Potentials (SSVEPs) from electroencephalography (EEG). In this approach, EEG signals are pre-processed using spectral and time domain filters in order to enhance Signal-to-Noise Ratio (SNR). Features are then extracted from the spectral representation after obtaining the spectral principle components. SSVEP target frequency that corresponds to the frequency of a flickering object is determined using a linear classification process. We examined the performance of the proposed approach using two datasets. Results demonstrate a high detection accuracy of an average 96.12% for a 4-second time window and 92.85% for a 2-second time window. Our analysis demonstrates that the proposed approach achieves better detection accuracy compared to traditional methods including canonical correlation analysis and its variants.