Determining Levels of Affective States with Riemannian Geometry Applied to EEG Signals
Applied Sciences · 24.09.2025 · 15 (19) · 10370
DOI: 10.3390/app151910370 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 24.09.2025. Verfasst von Agnieszka Wosiak und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Emotion recognition from electroencephalography (EEG) often relies on Euclidean features that ignore the curved geometry of covariance matrices. We introduce a Riemannian-manifold pipeline which, combined with the Fisher Geodesic Minimum Distance to Mean (FgMDM) classifier, leverages the full geometry of symmetric positive-definite (SPD) EEG covariances. The approach applies an additional geodesic-mean contraction that stabilizes trial covariances before tangent space projection. Experiments on the five-class SEED-V dataset show high accuracy, robustness to session-to-session variability and improved interpretability relative to baselines. These results highlight Riemannian geometry as a powerful framework for emotion recognition with high-dimensional, non-stationary EEG.
Zitieren
APA
Wosiak, A., Tereszczuk, A., & Żykwińska, K. (2025). Determining Levels of Affective States with Riemannian Geometry Applied to EEG Signals. Applied Sciences, 15(19), 10370. https://doi.org/10.3390/app151910370
Vancouver
Wosiak A, Tereszczuk A, Żykwińska K. Determining Levels of Affective States with Riemannian Geometry Applied to EEG Signals. Applied Sciences. 2025;15(19):10370. doi:10.3390/app151910370
BibTeX
@article{Wosiak2025,
author = {Wosiak, Agnieszka and Tereszczuk, Anita and Żykwińska, Katarzyna},
title = {Determining Levels of Affective States with Riemannian Geometry Applied to EEG Signals},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {19},
pages = {10370},
doi = {10.3390/app151910370}
}
EUVIMED