Smarter Decoding Through Richer Information

Better algorithms alone won’t solve BCI’s biggest challenges, we also need better features. I develop decoding approaches that combine multiple signal types and measurement modalities, painting a fuller picture of a user’s mental state and improving the reliability and accuracy of neural interfaces.

Last updated on Apr 17, 2026
Marie-Constance Corsi
Marie-Constance Corsi
Research scientist

My research interests include bridging the gap between biomedical engineering and neurosciences to propose new tools to improve closed-loop systems.

Publications

Neurophysiological screening of individual variability for robust decoding in c-VEP-based BCI

Code-modulated visual evoked-potential (c-VEP) based reactive brain-computer interfaces (BCIs) deliver high information-transfer rates …
Sébastien Velut, Jordy Thielen, Sylvain Chevallier, Marie-Constance Corsi, Frédéric Dehais
Project Project DOI URL

Low-Frequency Textured Gabor Flicker Enhances SSVEP Entrainment and Visual Comfort for BCI Control

Steady-state visual evoked potentials (SSVEPs) are widely used in cognitive neuroscience and brain-computer interfaces (BCIs), but the …
Jules Gomel, Frederic Dehais, Marie-Constance Corsi
Project DOI URL

Interpretability of Riemannian tools used in brain computer interfaces

Riemannian methods have established themselves as stateof-the-art approaches in Brain-Computer Interfaces (BCI) in terms of …
Thibault de Surrel, Tristan Venot, Marie-Constance Corsi, Florian Yger
Project DOI URL

Automatic Ocular Artifact Correction in Electroencephalography for Neurofeedback

Ocular artifacts can significantly impact electroencephalography (EEG) signals, potentially compromising the performance of …
Cassandra Dumas, Marie-Constance Corsi, Claire Dussard, Fanny Grosselin, Nathalie George
Project DOI URL

Deep Riemannian Neural Architectures for Domain Adaptation in Burst cVEP-based Brain Computer Interface

textlessdivtextgreatertextlessptextgreaterCode modulated Visually Evoked Potentials (cVEP) is an emerging paradigm for Brain-Computer …
Sébastien Velut, Sylvain Chevallier, Marie-Constance Corsi, Frédéric Dehais
Project DOI URL

Neuronal avalanches for eeg-based motor imagery BCI

Current features used in motor imagery-based Brain-Computer Interfaces (BCI) rely on local measurements that miss the interactions …
Camilla Mannino, Pierpaolo Sorrentino, Mario Chavez, Marie-Constance Corsi
Project Project URL

Geometric Neural Network based on Phase Space for BCI decoding

The integration of Deep Learning (DL) algorithms on brain signal analysis is still in its nascent stages compared to their success in …
Igor Carrara, Bruno Aristimunha, Marie-Constance Corsi, Raphael de Camargo, Sylvain Chevallier, Théodore Papadopoulo
Project URL

HappyFeat—An interactive and efficient BCI framework for clinical applications

Brain–Computer Interface (BCI) systems allow to perform actions by translating brain activity into commands. Such systems require …
Arthur Desbois, Tristan Venot, Fabrizio De Vico Fallani, Marie-Constance Corsi
Project DOI URL
HappyFeat—An interactive and efficient BCI framework for clinical applications

Functional connectivity ensemble method to enhance BCI performance (FUCONE)

Objective: Relying on the idea that functional connectivity provides important insights on the underlying dynamic of neuronal …
Marie-Constance Corsi, Sylvain Chevallier, Fabrizio De Vico Fallani, Florian Yger
Project DOI
Functional connectivity ensemble method to enhance BCI performance (FUCONE)

Riemannian geometry for combining functional connectivity metrics and covariance in BCI

Sylvain Chevallier, Marie-Constance Corsi, Florian Yger, Fabrizio De Vico Fallani
PDF Project DOI

Ensemble learning based on functional connectivity and Riemannian geometry for robust workload estimation

Context Passive Brain-Computer Interface (pBCI) has recently gained in popularity through its applications, e.g. workload and attention …
Marie-Constance Corsi, Sylvain Chevallier, Quentin Barthélemy, Isabelle Hoxha, Florian Yger
PDF Project

Riemannian Geometry on Connectivity for Clinical BCI

Riemannian BCI based on EEG covariance have won many data competitions and achieved very high classification results on BCI datasets. …
Marie-Constance Corsi, Florian Yger, Sylvain Chevallier, Camille Noûs
Project DOI
Riemannian Geometry on Connectivity for Clinical BCI

Network-based brain–computer interfaces: principles and applications

Brain–computer interfaces (BCIs) make possible to interact with the external environment by decoding the mental intention of …
Juliana Gonzalez-Astudillo, Tiziana Cattai, Giulia Bassignana, Marie-Constance Corsi, Fabrizio De Vico Fallani
Project DOI URL

Phase/Amplitude Synchronization of Brain Signals During Motor Imagery BCI Tasks

In the last decade, functional connectivity (FC) has been increasingly adopted based on its ability to capture statistical dependencies …
Tiziana Cattai, Stefania Colonnese, Marie-Constance Corsi, Danielle S. Bassett, Gaetano Scarano, Fabrizio De Vico Fallani
Project Project DOI

Extending Riemannian Brain-Computer Interface to Functional Connectivity Estimators

This abstract describes a novel approach for handling brain-computer interfaces (BCI), that could be used for robotic applications. …
Sylvain Chevallier, Marie-Constance Corsi, Florian Yger, Camille Noûs
Project URL

Integrating EEG and MEG Signals to Improve Motor Imagery Classification in Brain-Computer Interface

We adopted a fusion approach that combines features from simultaneously recorded electroencephalogram (EEG) and magnetoencephalogram …
Marie-Constance Corsi, Mario Chavez, Denis Schwartz, Laurent Hugueville, Ankit N. Khambhati, Danielle S. Bassett, Fabrizio De Vico Fallani
Project DOI

Characterization of Mental States through Node Connectivity between Brain Signals

Discriminating mental states from brain signals is crucial for many applications in cognitive and clinical neuroscience. Most of the …
Tiziana Cattai, Stefania Colonnese, Marie-Constance Corsi, Danielle S. Bassett, Gaetano Scarano, Fabrizio De Vico Fallani
Project Project DOI