EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Representation and Geometric Collapse in Spatiotemporal EEG Classifiers: A Mathematical Diagnostic Framework

Ahmed El Badaoui, Hicham Ben Alla, Manal Hilali, Said Ben Alla, Abdellah Ezzati

Signals · 04.08.2026 · 7 (4) · 76

DOI: 10.3390/signals7040076 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Signals, online erschienen am 04.08.2026. Verfasst von Ahmed El Badaoui und 4 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Spatiotemporal deep learning models, like Graph Neural Networks (GNNs), Transformers, and selective State Space Models (Mamba), have achieved impressive performance in electroencephalogram (EEG) decoding and affective computing. However, their generalization performance often degrades severely under subject-independent Leave-One-Subject-Out (LOSO) cross-validation protocols. This generalization drop is often attributed to generic domain shifts in standard Brain–Computer Interface (BCI) literature, and is tackled by parameter-heavy adaptations. In contrast, this paper proposes a unified mathematical diagnostic framework to audit and measure the underlying representation and geometric collapse in spatiotemporal brain–computer interfaces. More concretely, we formalize: (1) Topological over-smoothing under volume conduction through Graph Dirichlet Energy bounds indicating GCNs as low-pass filters that smooth localized electrode variations; (2) representation collapse through the Normalized Rank Uniformity Index (NRUI) based on the Shannon Entropy of latent covariance eigenvalues, that distinguishes between dimensional and semantic collapse; and (3) geometric manifold distortions under subject domain shifts on the Symmetric Positive Definite (SPD) Riemannian manifold under the Affine-Invariant Riemannian Metric (AIRM) projection. Auditing these diagnostic metrics on canonical models across DEAP, DREAMER, and SEED, we demonstrate why standard spatiotemporal architectures suffer from performance collapse in cross-subject configurations. We provide BCI engineers with a tangible mathematical blueprint to design robust, collapse-resistant decoders.

Zitieren

APA

Badaoui, A. E., Alla, H. B., Hilali, M., Alla, S. B., & Ezzati, A. (2026). Representation and Geometric Collapse in Spatiotemporal EEG Classifiers: A Mathematical Diagnostic Framework. Signals, 7(4), 76. https://doi.org/10.3390/signals7040076

Vancouver

Badaoui AE, Alla HB, Hilali M, Alla SB, Ezzati A. Representation and Geometric Collapse in Spatiotemporal EEG Classifiers: A Mathematical Diagnostic Framework. Signals. 2026;7(4):76. doi:10.3390/signals7040076

BibTeX
@article{Badaoui2026,
  author = {Badaoui, Ahmed El and Alla, Hicham Ben and Hilali, Manal and Alla, Said Ben and Ezzati, Abdellah},
  title = {Representation and Geometric Collapse in Spatiotemporal EEG Classifiers: A Mathematical Diagnostic Framework},
  journal = {Signals},
  year = {2026},
  volume = {7},
  number = {4},
  pages = {76},
  doi = {10.3390/signals7040076}
}
Kostenlos starten →