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

A K Fedorov; M N Anufriev; A A Zhirnov; K V Stepanov; E T Nesterov; D E Namiot; V E Karasik; A B Pnev

doi:10.1063/1.4944417

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

Rev Sci Instrum. 2016 Mar;87(3):036107. doi: 10.1063/1.4944417.

Authors

A K Fedorov¹, M N Anufriev¹, A A Zhirnov¹, K V Stepanov¹, E T Nesterov¹, D E Namiot², V E Karasik¹, A B Pnev¹

Affiliations

¹ Bauman Moscow State Technical University, 2nd Baumanskaya St. 5, Moscow 105005, Russia.
² Lomonosov Moscow State University, Vorob'evy gory 1, Moscow 119992, Russia.

PMID: 27036840
DOI: 10.1063/1.4944417

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.