Real-Time Anomaly Detection in Underwater Gliders: Anomaly Detection Algorithm

Written by oceanography | Published 2024/05/22
Tech Story Tags: data-analysis | machine-learning | underwater-gliders | anomaly-detection | oceanography | glider-navigation | ocean-data | marine-robotics

TLDRThe pipeline of anomaly detection and false alarm elimination is shown in Fig. 1. The algorithm assumes no anomaly if the estimate is within the normal speed range. The flow speed estimate is checked against the glider-estimated flow speed to circumvent any false alarm. This paper is available on arxiv(https://arxiv.org/pdf/2308.00180.pdf) under CC 4.0 license.via the TL;DR App

Authors:

(1) Ruochu Yang;

(2) Chad Lembke;

(3) Fumin Zhang;

(4) Catherine Edwards.

Table of Links

Abstract and Intro

Anomaly Detection Algorithm

Experimental Evaluation

Conclusion and References

II. ANOMALY DETECTION ALGORITHM

The pipeline of anomaly detection and false alarm elimination is shown in Fig. 1. By generating the glider speed estimate, the algorithm assumes no anomaly if the estimate is within the normal speed range. Otherwise, the glider may be encountering issues. The flow speed estimate is checked against the glider-estimated flow speed to circumvent any false alarm.

We model the glider dynamics as follows:

where θ is the unknown parameter to be estimated,

This paper is available on arxiv under CC 4.0 license.


Written by oceanography | From the abyssal plain to zooplankton, we cover the best academic & internet content ever about the study of the ocean
Published by HackerNoon on 2024/05/22