Image de couverture de livre

Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Abdelli, Khouloud, Lonardi, Matteo, Gripp, Jurgen, Olsson, Samuel, Boitier, Fabien, Layec, Patricia
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Signal Processing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

_version_	1866910591203934208
author	Abdelli, Khouloud Lonardi, Matteo Gripp, Jurgen Olsson, Samuel Boitier, Fabien Layec, Patricia
author_facet	Abdelli, Khouloud Lonardi, Matteo Gripp, Jurgen Olsson, Samuel Boitier, Fabien Layec, Patricia
contents	We propose a novel unsupervised anomaly detection approach using generative adversarial networks and SOP-derived spectrograms. Demonstrating remarkable efficacy, our method achieves over 97% accuracy on SOP datasets from both submarine and terrestrial fiber links, all achieved without the need for labelled data.
format	Preprint
id	arxiv_https___arxiv_org_abs_2409_03657
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks Abdelli, Khouloud Lonardi, Matteo Gripp, Jurgen Olsson, Samuel Boitier, Fabien Layec, Patricia Machine Learning Signal Processing We propose a novel unsupervised anomaly detection approach using generative adversarial networks and SOP-derived spectrograms. Demonstrating remarkable efficacy, our method achieves over 97% accuracy on SOP datasets from both submarine and terrestrial fiber links, all achieved without the need for labelled data.
title	Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks
topic	Machine Learning Signal Processing
url	https://arxiv.org/abs/2409.03657