Machine learning for sensing with a multimode exposed core fiber specklegram sensor

Files

hdl_135076.pdf (3.18 MB)
  (Published version)

Date

2022

Authors

SMITH, D.L.
NGUYEN, L.V.
OTTAWAY, D.J.
CABRAL, T.D.
Fujiwara, E.
CORDEIRO, C.M.B.
WARREN-SMITH, S.C.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

Optics Express, 2022; 30(7):1-13

Statement of Responsibility

Darcy L. Smith, Linh V. Nguyen, David J Ottoway, Thiago D. Cabral, Eric Fujiwara, Cristiano M.B. Cordeiro, Stephen C. Warren-Smith

Conference Name

Abstract

Fiber specklegram sensors (FSSs) traditionally use statistical methods to analyze specklegrams obtained from fibers for sensing purposes, but can suffer from limitations such as vulnerability to noise and lack of dynamic range. In this paper we demonstrate that deep learning improves the analysis of specklegrams for sensing, which we show here for both air temperature and water immersion length measurements. Two deep neural networks (DNNs); a convolutional neural network and a multi-layer perceptron network, are used and compared to a traditional correlation technique on data obtained from a multimode fiber exposed-core fiber. The ability for the DNNs to be trained against a random noise source such as specklegram translations is also demonstrated.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

License

Call number

Persistent link to this record