EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Embedded One-Class Classification for Deep Neural Network Representations

Edgard M. Maboudou-Tchao, Poorna Sandamini Senaratne, Randyll Pandohie, Jongik Chung

Mathematics · 10.08.2026 · 14 (16) · 2887

DOI: 10.3390/math14162887 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 10.08.2026. Verfasst von Edgard M. Maboudou-Tchao und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial neural networks (ANNs) make predictions based on patterns learned during training; however, their reliability may deteriorate when the data distribution or the trained model changes. This paper proposes an Embedded One-Class Classification (EOCC) framework for monitoring task-informed neural network representations. The predictive network is first trained using its original classification or regression objective and then fixed. Embedded Support Vector Data Description (ESVDD) or Embedded Least Squares Support Vector Data Description (ELS-SVDD) is subsequently fitted to embeddings extracted from a selected hidden layer. The framework is evaluated through classification and regression simulations involving mean, covariance, and mixed distributional shifts. Additional experiments examine embedding layer and activation choices, direct neural network weight perturbations, and model changes induced by altered training conditions. Comparisons with depth-based, density-based, covariance-based, isolation-based, and end-to-end deep one-class methods show that EOCC is competitive and frequently achieves low Type II error while maintaining the nominal in-control acceptance probability, although no method is uniformly superior across all settings. Illustrative applications involving the Internet Firewall, ELEC2, and SINE1 datasets demonstrate how the framework can identify changes reflected in neural network representations. The present framework performs change detection only; adaptation and automatic model updating remain directions for future research.

Zitieren

APA

Maboudou-Tchao, E. M., Senaratne, P. S., Pandohie, R., & Chung, J. (2026). Embedded One-Class Classification for Deep Neural Network Representations. Mathematics, 14(16), 2887. https://doi.org/10.3390/math14162887

Vancouver

Maboudou-Tchao EM, Senaratne PS, Pandohie R, Chung J. Embedded One-Class Classification for Deep Neural Network Representations. Mathematics. 2026;14(16):2887. doi:10.3390/math14162887

BibTeX
@article{MaboudouTchao2026,
  author = {Maboudou-Tchao, Edgard M. and Senaratne, Poorna Sandamini and Pandohie, Randyll and Chung, Jongik},
  title = {Embedded One-Class Classification for Deep Neural Network Representations},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {16},
  pages = {2887},
  doi = {10.3390/math14162887}
}
Kostenlos starten →