Energy-based Generative Models for Distributed Acoustic Sensing Event Classification in Telecom Networks

/in /by

Publication Date: 10/1/2025

Event: ECOC 2025 – The 51st European Conference on Optical Communication

Reference: M.03.08.5:1-4, 2025

Authors: Shaobo Han, NEC Laboratories America, Inc.; Ming-Fang Huang, NEC Laboratories America, Inc.; Tingfeng Li, NEC Laboratories America, Inc.; Scott Kotrla, Verizon; Jeffrey A Mundt, Verizon; Ting Wang, NEC Laboratories America, Inc.; Yoshiaki Aono, NEC Corporation

Abstract: Distributed fiber-optic sensing combined with machine learning enables continuous monitoring of telecom infrastructure. We employ generative modeling for event classification, supporting semi­ supervised learning, uncertainty calibration, and noise resilience. Our approach offers a scalable, data-efficient solution for real-world deployment in complex environments.

Publication Link: