Showing papers by "Fabien Lotte published in 2023"

16 ECoG-Based BCIs Aysegul Gunduz and Gerwin Schalk

Abstract: This chapter reviews the state of the art of brain–computer interfaces (BCIs) that use electrocorticography (ECoG) signals as an input. We first present the clinical settings and signal acquisition systems, including subdural grid electrodes, that lend themselves to ECoG data collection. Second, we discuss the current understanding of ECoG signal physiology and ECoG features that cannot be captured by noninvasive electrophysiology or imaging, and how this knowledge can be translated to signal features that can control BCIs. Next, we review ECoG-based BCIs in the literature that enable control, communication, and therapeutic neuromodulation. This is followed by a review of current implantable ECoG device technologies approved or available for investigational use in humans. Finally, we present and discuss various open questions in the field of ECoG BCIs and future research directions that may lead to the translation of these technologies into clinical practice.

Modeling complex EEG data distribution on the Riemannian manifold toward outlier detection and multimodal classification.

Abstract: OBJECTIVE The usage of Riemannian geometry for Brain-computer interfaces (BCIs) has gained momentum in re-cent years. Most of the machine learning techniques proposed for Riemannian BCIs consider the data distribution on a man-ifold to be unimodal. However, the distribution is likely to be multimodal rather than unimodal since high-data variability is a crucial limitation of electroencephalography (EEG). In this paper, we propose a novel data modeling method for considering complex data distributions on a Riemannian manifold of EEG covariance matrices, aiming to improve BCI reliability. METHODS Our method, Riemannian spectral clustering (RiSC), represents EEG covariance matrix distribution on a manifold using a graph with proposed sim-ilarity measurement based on geodesic distances, then clusters the graph nodes through spectral clustering. This allows flexibility to model both a unimodal and a multimodal distribution on a manifold. RiSC can be used as a basis to design an outlier detector named outlier detection Riemannian spectral clustering (oden-RiSC) and a multimodal classifier named multimodal classifier Riemannian spectral clustering (mcRiSC). All required parameters of odenRiSC/mcRiSC are selected in data-driven manner. More-over, there is no need to pre-set a threshold for outlier detection and the number of modes for multimodal classification. RESULTS The experimental evaluation revealed odenRiSC can detect EEG outliers more accurately than existing methods and mcRiSC out-performed the standard unimodal classifier, especially on high-variability datasets. CONCLUSION odenRiSC/mcRiSC are anticipated to contribute to making real-life BCIs outside labs and neuroer-gonomics applications more robust. SIGNIFICANCE RiSC can work as a robust EEG outlier detector and multimodal classifier.