Publication:
Vector-based pattern recognition algorithm for interferometric fiber sensor-signals analysis

Date

2025-01-15

Authors

Valentín-Coronado, Luis M.
Martínez Manuel, Rodolfo
Esquivel-Hernández, Jonathan
Martínez-Guerrero, María de Los Ángeles
LaRochelle, Sophie

Director

Publisher

IEEE
Acceso abierto / Sarbide irekia
Artículo / Artikulua
Versión aceptada / Onetsi den bertsioa

Project identifier

Impacto
OpenAlexGoogle Scholar
cited by count

Abstract

A vector-based pattern recognition algorithm (V-PRA) for interferometric fiber sensor (IFS) signals is introduced. The proposed V-PRA transforms sensed interferometric signals into vectors to identify them by calculating the angular similarity with reference database vectors. This process accurately recognizes sensing patterns and assigns corresponding physical parameter values. The algorithm’s performance was tested in various IFS systems, including Fabry-Perot interferometers for refractive index measurement, multimode IFS for bending and strain monitoring, and multicore IFS for temperature monitoring. Experimental results confirm the effectiveness of the V-PRA as a specialized tool for IFSs.

Description

Keywords

Optical fiber sensors, Interferometric signals, Vector-based algorithm, Pattern recognition

Department

Institute of Smart Cities - ISC

Faculty/School

Degree

Doctorate program

item.page.cita

Valentín-Coronado, L. M., Martínez-Manuel, R., Esquivel-Hernández, J., Díaz, S., Martínez-Guerrero, M. Á., Armendáriz, M. Á., LaRochelle, S. (2025) Vector-based pattern recognition algorithm for interferometric fiber sensor-signals analysis. IEEE Photonic Technology Letters, 37(4), 207-210. https://doi.org/10.1109/LPT.2025.3530299.

item.page.rights

© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other work.

Los documentos de Academica-e están protegidos por derechos de autor con todos los derechos reservados, a no ser que se indique lo contrario.