Do the stimuli of an SSVEP-based BCI really have to be the same as the stimuli used for training it?

Andéol Évain 1 Ferran Argelaguet 1 Géry Casiez 2 Nicolas Roussel 2 Anatole Lécuyer 1
1 Hybrid - 3D interaction with virtual environments using body and mind
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
2 MJOLNIR - Computing tools to empower users
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Does the stimulation used during the training on an SSVEP-based BCI have to be similar to that of the end use? We recorded six-channel EEG data from 12 subjects in various conditions of distance between targets, and of difference in color between targets. Our analysis revealed that the stimulation configuration used for training which leads to the best classification accuracy is not always the one which is closest to the end use configuration. We found that the distance between targets during training is of little influence if the end use targets are close to each other, but that training at far distance can lead to a better accuracy for far distance end use (p < .01). Additionally, an interaction effect is observed between training and testing color (p < .001): while training with monochrome targets leads to good performance only when the test context involves monochrome targets as well, a classifier trained on colored targets can be efficient for both colored and monochrome targets. In a nutshell, in the context of SSVEP-based BCI, training using distant targets of different colors seems to lead to the best and more robust performance in all end use contexts.
Type de document :
Article dans une revue
Brain-Computer Interfaces, Taylor & Francis, 2016, 3 (2), pp.103 - 111. <10.1080/2326263X.2016.1193458>
Liste complète des métadonnées


https://hal.inria.fr/hal-01388534
Contributeur : Ferran Argelaguet Sanz <>
Soumis le : jeudi 27 octobre 2016 - 10:57:26
Dernière modification le : vendredi 17 février 2017 - 16:11:06

Fichier

article.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Andéol Évain, Ferran Argelaguet, Géry Casiez, Nicolas Roussel, Anatole Lécuyer. Do the stimuli of an SSVEP-based BCI really have to be the same as the stimuli used for training it?. Brain-Computer Interfaces, Taylor & Francis, 2016, 3 (2), pp.103 - 111. <10.1080/2326263X.2016.1193458>. <hal-01388534>

Partager

Métriques

Consultations de
la notice

488

Téléchargements du document

97