Threat Classification on Deployed Optical Networks Using MIMO Digital Fiber Sensing, Wavelets, and Machine Learning

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.

Optimal Probing Sequences for Polarization-Multiplexed Coherent Phase OTDR

We introduce dual-polarization probing codes based on two circularly shifted frequency sweep signals enabling perfect channel estimation. This is achieved with a probing length equal to at least twice the fiber round-trip propagation time.

Towards Polarization-Insensitive Coherent Coded Phase OTDR

We explore the alternatives for interrogating a fiber sensor from the polarization point of view, and demonstrate a better accuracy with dual polarization probing for coherent phi-OTDR compared with single polarization probing.