LGSep 5, 2024
Unsupervised Anomaly Detection and Localization with Generative Adversarial NetworksKhouloud Abdelli, Matteo Lonardi, Jurgen Gripp et al.
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.
NISep 5, 2024
Weather-Adaptive Multi-Step Forecasting of State of Polarization Changes in Aerial Fibers Using Wavelet Neural NetworksKhouloud Abdelli, Matteo Lonardi, Jurgen Gripp et al.
We introduce a novel weather-adaptive approach for multi-step forecasting of multi-scale SOP changes in aerial fiber links. By harnessing the discrete wavelet transform and incorporating weather data, our approach improves forecasting accuracy by over 65% in RMSE and 63% in MAPE compared to baselines.