S
Stéphane Bonnet
Researcher at University of Paris
Publications - 119
Citations - 2409
Stéphane Bonnet is an academic researcher from University of Paris. The author has contributed to research in topics: Nonlinear system & Riemannian geometry. The author has an hindex of 19, co-authored 108 publications receiving 1918 citations. Previous affiliations of Stéphane Bonnet include Alternatives & Commissariat à l'énergie atomique et aux énergies alternatives.
Papers
More filters
Journal ArticleDOI
Multiclass Brain–Computer Interface Classification by Riemannian Geometry
TL;DR: A new classification framework for brain-computer interface (BCI) based on motor imagery using spatial covariance matrices as EEG signal descriptors and relying on Riemannian geometry to directly classify these matrices using the topology of the manifold of symmetric and positive definite matrices.
Journal ArticleDOI
Classification of covariance matrices using a Riemannian-based kernel for BCI applications
TL;DR: A new kernel is derived by establishing a connection with the Riemannian geometry of symmetric positive definite matrices, effectively replacing the traditional spatial filtering approach for motor imagery EEG-based classification in brain-computer interface applications.
Book ChapterDOI
Riemannian geometry applied to BCI classification
TL;DR: In this article, the authors proposed different algorithms to classify covariance matrices in their native space using a differential geometry framework, which is used for brain-computer interfaces based on motor imagery.
Proceedings ArticleDOI
Mental fatigue and working memory load estimation: Interaction and implications for EEG-based passive BCI
TL;DR: Analysis of the influence of WKL and TOT on EEG band power features, as well as their interaction and its impact on classification performance, reveals opposite changes in alpha power distribution between WKl and Tot conditions.
Journal ArticleDOI
Dynamic X-ray computed tomography
Stéphane Bonnet,Anne Koenig,Sébastien Roux,Patrick Hugonnard,Régis Guillemaud,Pierre Grangeat +5 more
TL;DR: A new reconstruction algorithm based on a voxel-specific dynamic evolution compensation is presented, which provides four-dimensional image sequences with accurate spatio-temporal information and permits to reduce the dose delivered per rotation while keeping the same signal to noise ratio for every frame using an adaptive motion-compensated temporal averaging.