Comparative analysis of strategies for feature extraction and classification in SSVEP BCIs.

Abstract

Brain–computer interface (BCI) systems based on electroencephalography have been increasingly usedin different contexts, engendering applications from entertainment to rehabilitation in a non-invasiveframework. In this study, we perform a comparative analysis of different signal processing techniquesfor each BCI system stage concerning steady state visually evoked potentials (SSVEP), which includes: (1)feature extraction performed by different spectral methods (bank of filters, Welch’s method and the mag-nitude of the short-time Fourier transform); (2) feature selection by means of an incremental wrapper,a filter using Pearson’s method and a cluster measure based on the Davies–Bouldin index, in additionto a scenario with no selection strategy; (3) classification schemes using linear discriminant analysis(LDA), support vector machines (SVM) and extreme learning machines (ELM). The combination of suchmethodologies leads to a representative and helpful comparative overview of robustness and efficiency ofclassical strategies, in addition to the characterization of a relatively new classification approach (definedby ELM) applied to the BCI-SSVEP systems.