English

Gaussian mixture model for event recognition in optical time-domain reflectometry based sensing systems

Optics 2016-03-22 v2 Data Analysis, Statistics and Probability Instrumentation and Detectors

Abstract

We propose a novel approach to the recognition of particular classes of non-conventional events in signals from phase-sensitive optical time-domain-reflectometry-based sensors. Our algorithmic solution has two main features: filtering aimed at the de-nosing of signals and a Gaussian mixture model to cluster them. We test the proposed algorithm using experimentally measured signals. The results show that two classes of events can be distinguished with the best-case recognition probability close to 0.9 at sufficient numbers of training samples.

Keywords

Cite

@article{arxiv.1509.05998,
  title  = {Gaussian mixture model for event recognition in optical time-domain reflectometry based sensing systems},
  author = {Aleksey Fedorov and Maxim Anufriev and Andrey Zhirnov and Konstantin Stepanov and Evgeniy Nesterov and Dmitry Namiot and Valery Karasik and Alexey Pnev},
  journal= {arXiv preprint arXiv:1509.05998},
  year   = {2016}
}

Comments

4 pages; published version

R2 v1 2026-06-22T11:00:53.747Z