Channel Selection Procedure using Riemannian distance for BCI applications - Archive ouverte HAL Access content directly
Conference Papers Year : 2011

Channel Selection Procedure using Riemannian distance for BCI applications

Abstract

This article describes a new algorithm to select a subset of electrodes in BCI experiments. It is illustrated on a two-class motor imagery paradigm. The proposed approach is based on the Riemannian distance between spatial covariance matrices which allows to indirectly assess the discriminability between classes. Sensor selection is automatically done using a backward elimination principle. The method is tested on the dataset IVa from BCI competition III. The identified subsets are both consistent with neurophysiological principles and effective, achieving optimal performances with a reduced number of channels.
Fichier principal
Vignette du fichier
NER11_0016_FI.pdf (287.12 Ko) Télécharger le fichier
Origin Publisher files allowed on an open archive
Loading...

Dates and versions

hal-00602707 , version 1 (23-06-2011)

Identifiers

  • HAL Id : hal-00602707 , version 1

Cite

Alexandre Barachant, Stephane Bonnet. Channel Selection Procedure using Riemannian distance for BCI applications. The 5th International IEEE EMBS Conference on Neural Engineering, Apr 2011, Cancun, Mexico. pp.TBA. ⟨hal-00602707⟩
229 View
1338 Download

Share

Gmail Mastodon Facebook X LinkedIn More