A Brain-Switch using Riemannian Geometry

Alexandre Barachant (1) , Stephane Bonnet (1) , Marco Congedo (2) , Christian Jutten (2)

1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 GIPSA-VIBS - GIPSA - Vision and Brain Signal Processing

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%.

Mots clés: classification; Riemannian geometry; EEG; BCI; Brain Computer interface

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

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