Towards the Classification of Error-Related Potentials using Riemannian Geometry

TL;DR

This study demonstrates that Riemannian geometry-based feature extraction improves classification accuracy of error-related potentials in EEG data compared to traditional methods, with potential applications in brain-computer interfaces for error detection.

Contribution

The paper applies Riemannian geometry-based classification to ErrPs, showing improved accuracy over traditional methods in a BCI context.

Findings

Riemannian approach achieved 78.2% accuracy versus 75.9% for traditional methods.

Significant accuracy improvement in 3 out of 7 participants.

Riemannian features better captured feedback-elicited ErrPs.

Abstract

The error-related potential (ErrP) is an event-related potential (ERP) evoked by an experimental participant's recognition of an error during task performance. ErrPs, originally described by cognitive psychologists, have been adopted for use in brain-computer interfaces (BCIs) for the detection and correction of errors, and the online refinement of decoding algorithms. Riemannian geometry-based feature extraction and classification is a new approach to BCI which shows good performance in a range of experimental paradigms, but has yet to be applied to the classification of ErrPs. Here, we describe an experiment that elicited ErrPs in seven normal participants performing a visual discrimination task. Audio feedback was provided on each trial. We used multi-channel electroencephalogram (EEG) recordings to classify ErrPs (success/failure), comparing a Riemannian geometry-based method to a traditional approach that computes time-point features. Overall, the Riemannian approach outperformed the traditional approach (78.2% versus 75.9% accuracy, p < 0.05); this difference was statistically significant (p < 0.05) in three of seven participants. These results indicate that the Riemannian approach better captured the features from feedback-elicited ErrPs, and may have application in BCI for error detection and correction.