Non-Stationary Brain Source Separation for Multi-Class Motor Imagery
Résumé
This article describes a method to recover taskrelated brain sources in the context of multi-class Brain- Computer Interfaces (BCIs) based on non-invasive electroencephalography (EEG). We extend the method Joint Approximate Diagonalization (JAD) for spatial filtering using a maximum likelihood framework. This generic formulation (1) bridges the gap between the Common Spatial Patterns (CSP) and Blind Source Separation (BSS) of non-stationary sources, and (2) leads to a neurophysiologically adapted version of JAD, accounting for the successive activations/deactivations of brain sources during motor imagery trials. Using dataset 2a of BCI Competition IV (2008) in which nine subjects were involved in a four-class two-session motorimagery (MI) based BCI experiment, a quantitative evaluation of our extension is provided by comparing its performance against JAD and CSP in the case of cross-validation as well as session-to-session transfer. Whereas JAD, as already proposed in other works, does not prove to be significantly better than classical one-versus-rest CSP, our extension is shown to perform significantly better than CSP for cross-validated and session-to-session performance. The extension of JAD introduced in this paper yields among the best session-to-session transfer results presented so far for this particular dataset, thus it appears of great interest for real-life BCIs.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...