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

TL;DR

This paper introduces a Gaussian mixture model-based method for recognizing specific non-conventional events in optical time-domain reflectometry sensor signals, combining denoising and clustering to improve event classification accuracy.

Contribution

The paper presents a novel combination of denoising and Gaussian mixture modeling for event recognition in optical sensing signals, validated with experimental data.

Findings

Recognition probability up to 0.9 with sufficient training data

Effective denoising improves clustering accuracy

Two event classes successfully distinguished

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.