A Brain-Switch using Riemannian Geometry

Abstract : This paper addresses the issue of asynchronous brain-switch. The detection of a specific brain pattern from the ongoing EEG activity is achieved by using the Riemannian geometry, which offers an interesting framework for EEG mental task classification, and is based on the fact that spatial covariance matrices obtained on short-time EEG segments contain all the desired information. Such a brain-switch is valuable as it is easy to set up and robust to artefacts. The performances are evaluated offline using EEG recordings collected on 6 subjects in our laboratory. The results show a good precision (Positive Predictive Value) of 92% with a sensitivity (True Positive Rate) of 91%.
Complete list of metadatas

Contributor : Alexandre Barachant <>
Submitted on : Wednesday, October 5, 2011 - 9:50:22 AM
Last modification on : Monday, July 8, 2019 - 3:08:15 PM
Long-term archiving on : Tuesday, November 13, 2012 - 3:11:26 PM


  • HAL Id : hal-00629110, version 1


Alexandre Barachant, Stephane Bonnet, Marco Congedo, Christian Jutten. A Brain-Switch using Riemannian Geometry. 5th International Brain-Computer Interface Conference 2011 (BCI 2011), Sep 2011, Graz, Austria. pp.64-67. ⟨hal-00629110⟩



Record views


Files downloads