Development of an Intelligent Monitoring System Based on the Use of Fiber-Optic Sensors and Deep Learning

Alexandr V. Neftissov, Assiya Sarinova, Ilyas Kazambayev, Lalita Kirichenko, Sergiy Bronin

2023

Closed access Metadata (CSL-JSON)
DOI 10.1109/sist58284.2023.10223520
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Fiber-optic sensors are commonly used in modern monitoring systems. This article discusses a monitoring system using a fiber-optic sensor built using a camera. As the study showed, the newly proposed method requires a machine learning system to determine the displacement of stone slabs accurately. However, this system needs to have higher accuracy in determining the distance to the damage. This work aims to develop a deep learning system that considers external disturbances affecting a light spot's image.