Spatially Regularized Common Spatial Patterns for EEG Classification

Abstract : In this paper, we propose a new algorithm for Brain- Computer Interface (BCI): the Spatially Regularized Common Spatial Patterns (SRCSP). SRCSP is an extension of the famous CSP algorithm which includes spatial a priori in the learning process, by adding a regularization term which penalizes spatially non smooth filters. We compared SRCSP and CSP algorithms on data of 14 subjects from BCI competitions. Results suggested that SRCSP can improve performances, around 10% more in classification accuracy, for subjects with poor CSP performances. They also suggested that SRCSP leads to more physiologically relevant filters than CSP
Type de document :
Communication dans un congrès
International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. pp.3712-3715, 2010
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00447435
Contributeur : Fabien Lotte <>
Soumis le : jeudi 29 avril 2010 - 13:15:50
Dernière modification le : lundi 16 juillet 2012 - 18:32:19
Document(s) archivé(s) le : jeudi 23 septembre 2010 - 18:04:35

Fichier

icpr10.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00447435, version 3

Citation

Fabien Lotte, Cuntai Guan. Spatially Regularized Common Spatial Patterns for EEG Classification. International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. pp.3712-3715, 2010. 〈inria-00447435v3〉

Partager

Métriques

Consultations de la notice

103

Téléchargements de fichiers

174