Deep Riemannian Neural Architectures for Domain Adaptation in Burst cVEP-based Brain Computer Interface - A&O (Apprentissage et Optimisation)
Communication Dans Un Congrès Année : 2024

Deep Riemannian Neural Architectures for Domain Adaptation in Burst cVEP-based Brain Computer Interface

Résumé

Code modulated Visually Evoked Potentials (cVEP) is an emerging paradigm for Brain-Computer Interfaces (BCIs) that offers reduced calibration times. However, cVEP-based BCIs still encounter challenges related to cross-session/subject variabilities. As Riemannian approaches have demonstrated good robustness to these variabilities, we propose the first study of deep Riemannian neural architectures, namely SPDNets, on cVEP-based BCIs. To evaluate their performance with respect to subject variabilities, we conduct classification tasks in a domain adaptation framework using a burst cVEP open dataset. This study demonstrates that SPDNet yields the best accuracy with single-subject calibration and promising results in domain adaptation.

Fichier principal
Vignette du fichier
ES2024-112.pdf (1.81 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04720928 , version 1 (04-10-2024)

Identifiants

Citer

Sébastien Velut, Sylvain Chevallier, Marie-Constance Corsi, Frédéric Dehais. Deep Riemannian Neural Architectures for Domain Adaptation in Burst cVEP-based Brain Computer Interface. ESANN 2024, Oct 2024, Bruges (Belgium) and online, France. pp.571-576, ⟨10.14428/esann/2024.ES2024-112⟩. ⟨hal-04720928⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More