Spatial filtering pipeline evaluation of cortically coupled computer vision system for rapid serial visual presentation

摘要

Rapid Serial Visual Presentation (RSVP) is a paradigm that supports the application of cortically coupled computer vision to image search. In RSVP, images are presented to participants which can evoke Event-related Potentials (ERPs) in their Electroencephalogram (EEG). Supervised spatial filtering techniques are often applied to enhance the discriminative information in the EEG. In this paper, we make two primary contributions: 1) We propose a novel spatial filtering method called Multiple Time Window LDA Beamformer (MTWLB); 2) We provide a comprehensive comparison of nine spatial filtering pipelines using three spatial filtering schemes, namely, MTWLB, xDAWN, Common Spatial Pattern (CSP) and three linear classification methods Linear Discriminant Analysis (LDA), Bayesian Linear Regression (BLR) and Logistic Regression (LR). The results reveal that MTWLB and xDAWN enhance the classification performance but CSP does not. The results also support the conclusion that LR can be effective for a RSVP-based BCI if discriminative features are available.