EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

From data to decision: a multi-stage framework for class imbalance mitigation in optical network failure analysis

Yousuf Moiz Ali, Jaroslaw E. Prilepsky, Nicola Sambo, João Pedro, Mohammad M. Hosseini, Antonio Napoli, Sergei K. Turitsyn, Pedro Freire

Journal of Optical Communications and Networking · 01.01.2026 · 18 (1) · 42

DOI: 10.1364/jocn.576774 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Optical Communications and Networking, online erschienen am 23.12.2025. Verfasst von Yousuf Moiz Ali und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: HORIZON EUROPE Framework Programme, Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning-based failure management in optical networks has gained significant attention in recent years, but severe class imbalance, where normal instances far outnumber failure cases, remains a considerable challenge. While pre- and in-processing techniques have been widely studied, post-processing methods are largely unexplored. We present a direct comparison of pre-, in-, and post-processing approaches for class imbalance mitigation in failure detection and identification using an experimental dataset. For failure detection, post-processing, particularly threshold adjustment, yields the highest F1 score improvement of up to 15.3%, while random under-sampling offers the fastest inference. In failure identification, generative AI methods deliver the most significant performance gains up to 24.2%, whereas post-processing has a limited impact in multi-class settings. When class overlap exists and latency is critical, over-sampling methods like synthetic minority over-sampling technique (SMOTE) are most effective; without latency constraints, meta-learning excels. In low-overlap scenarios, generative AI approaches provide the best performance with minimal inference time.

Förderung

  • HORIZON EUROPE Framework Programme
  • Engineering and Physical Sciences Research Council

Zitieren

APA

Ali, Y. M., Prilepsky, J. E., Sambo, N., Pedro, J., Hosseini, M. M., Napoli, A., Turitsyn, S. K., & Freire, P. (2026). From data to decision: a multi-stage framework for class imbalance mitigation in optical network failure analysis. Journal of Optical Communications and Networking, 18(1), 42. https://doi.org/10.1364/jocn.576774

Vancouver

Ali YM, Prilepsky JE, Sambo N, Pedro J, Hosseini MM, Napoli A, et al. From data to decision: a multi-stage framework for class imbalance mitigation in optical network failure analysis. Journal of Optical Communications and Networking. 2026;18(1):42. doi:10.1364/jocn.576774

BibTeX
@article{Ali2026,
  author = {Ali, Yousuf Moiz and Prilepsky, Jaroslaw E. and Sambo, Nicola and Pedro, João and Hosseini, Mohammad M. and Napoli, Antonio and Turitsyn, Sergei K. and Freire, Pedro},
  title = {From data to decision: a multi-stage framework for class imbalance mitigation in optical network failure analysis},
  journal = {Journal of Optical Communications and Networking},
  year = {2026},
  volume = {18},
  number = {1},
  pages = {42},
  doi = {10.1364/jocn.576774}
}
Kostenlos starten →