Riemannian geometry applied to BCI classification

Abstract : In brain-computer interfaces based on motor imagery, covariance matrices are widely used through spatial filters computation and other signal processing methods. Covariance matrices lie in the space of Symmetric Positives-Definite (SPD) matrices and therefore, fall within the Riemannian geometry domain. Using a differential geometry framework, we propose different algorithms in order to classify covariance matrices in their native space.
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00602700
Contributor : Alexandre Barachant <>
Submitted on : Thursday, June 23, 2011 - 11:39:07 AM
Last modification on : Monday, July 8, 2019 - 3:08:22 PM
Long-term archiving on : Saturday, September 24, 2011 - 2:23:48 AM

Identifiers

Citation

Alexandre Barachant, Stephane Bonnet, Marco Congedo, Christian Jutten. Riemannian geometry applied to BCI classification. 9th International Conference Latent Variable Analysis and Signal Separation (LVA/ICA 2010), Sep 2010, Saint-Malo, France. pp.629-636, ⟨10.1007/978-3-642-15995-4_78⟩. ⟨hal-00602700⟩

Share

Metrics

Record views

696

Files downloads

3278