We demonstrate mechanical threats classification including jackhammers and excavators, leveraging wavelet transform of MIMO-DFS output data across a 57-km operational network link. Our machine learning framework incorporates transfer learning and shows 93% classification accuracy from field data, with benefits for optical network supervision.
@article{arxiv.2409.03667,
title = {Threat Classification on Deployed Optical Networks Using MIMO Digital Fiber Sensing, Wavelets, and Machine Learning},
author = {Khouloud Abdelli and Henrique Pavani and Christian Dorize and Sterenn Guerrier and Haik Mardoyan and Patricia Layec and Jeremie Renaudier},
journal= {arXiv preprint arXiv:2409.03667},
year = {2024}
}