A Unified Siamese Learning Framework for Zero-Day Anomaly Detection and Classification in Optical Networks
Paper i proceeding, 2025
A multi-similarity Siamese neural network unifies zero-day anomaly detection and one-shot classification in optical networks, achieving over 99% accuracy and instant adaptability across lightpaths and unseen anomaly types without any retraining.
Optical networks
Anomaly detection
Machine learning
Artificial intelligence
Contrastive learning
Anomaly classification
Författare
Carlos Natalino Da Silva
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
Flávia Pessoa Monteiro
Universidade Federal do Oeste do Pará (UFOPA)
Paolo Monti
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
Proceedings of the Optical Fiber Communication Conference (OFC) 2026
M3A.2
Optical Fiber Communication Conference (OFC) 2026
Los Angeles, CA, USA,
Los Angeles, CA, USA,
Styrkeområden
Informations- och kommunikationsteknik
Ämneskategorier (SSIF 2025)
Kommunikationssystem
Datavetenskap (datalogi)
Telekommunikation
Relaterade dataset
Optical network soft failure dataset [dataset]
DOI: 10.17632/y3pspy7j83.1 URI: https://data.mendeley.com/datasets/y3pspy7j83/1