Threat Classification on Deployed Optical Networks Using MIMO Digital Fiber Sensing, Wavelets, and Machine Learning
This addresses the problem of network security and supervision for optical network operators, but it is incremental as it applies existing methods like wavelets and transfer learning to a new domain.
The paper tackled the problem of classifying mechanical threats like jackhammers and excavators on deployed optical networks, achieving 93% classification accuracy using field data from a 57-km operational link.
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.