Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor
This paper demonstrates a comparative analysis of five machine learning (ML) algorithms for improving the signal processing time and temperature prediction accuracy in Brillouin optical time domain analysis (BOTDA) fiber sensor. The algorithms analyzed were generalized linear model (GLM), deep learn...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Photonics |
Subjects: | |
Online Access: | https://www.mdpi.com/2304-6732/7/4/79 |
_version_ | 1797552879148466176 |
---|---|
author | Nur Dalilla Nordin Mohd Saiful Dzulkefly Zan Fairuz Abdullah |
author_facet | Nur Dalilla Nordin Mohd Saiful Dzulkefly Zan Fairuz Abdullah |
author_sort | Nur Dalilla Nordin |
collection | DOAJ |
description | This paper demonstrates a comparative analysis of five machine learning (ML) algorithms for improving the signal processing time and temperature prediction accuracy in Brillouin optical time domain analysis (BOTDA) fiber sensor. The algorithms analyzed were generalized linear model (GLM), deep learning (DL), random forest (RF), gradient boosted trees (GBT), and support vector machine (SVM). In this proof-of-concept experiment, the performance of each algorithm was investigated by pairing Brillouin gain spectrum (BGS) with its corresponding temperature reading in the training dataset. It was found that all of the ML algorithms have significantly reduced the signal processing time to be between 3.5 and 655 times faster than the conventional Lorentzian curve fitting (LCF) method. Furthermore, the temperature prediction accuracy and temperature measurement precision made by some algorithms were comparable, and some were even better than the conventional LCF method. The results obtained from the experiments would provide some general idea in deploying ML algorithm for characterizing the Brillouin-based fiber sensor signals. |
first_indexed | 2024-03-10T16:07:18Z |
format | Article |
id | doaj.art-176b0f6a897a4f1a9eebd8f55439ea9e |
institution | Directory Open Access Journal |
issn | 2304-6732 |
language | English |
last_indexed | 2024-03-10T16:07:18Z |
publishDate | 2020-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Photonics |
spelling | doaj.art-176b0f6a897a4f1a9eebd8f55439ea9e2023-11-20T14:43:51ZengMDPI AGPhotonics2304-67322020-09-01747910.3390/photonics7040079Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber SensorNur Dalilla Nordin0Mohd Saiful Dzulkefly Zan1Fairuz Abdullah2Institute of Power Engineering, Universiti Tenaga Nasional, Selangor 43000, MalaysiaDepartment of Electrical, Electronic & Systems Engineering, Faculty of Engineering & Built Environment, Universiti Kebangsaan Malaysia, Selangor 43600, MalaysiaInstitute of Power Engineering, Universiti Tenaga Nasional, Selangor 43000, MalaysiaThis paper demonstrates a comparative analysis of five machine learning (ML) algorithms for improving the signal processing time and temperature prediction accuracy in Brillouin optical time domain analysis (BOTDA) fiber sensor. The algorithms analyzed were generalized linear model (GLM), deep learning (DL), random forest (RF), gradient boosted trees (GBT), and support vector machine (SVM). In this proof-of-concept experiment, the performance of each algorithm was investigated by pairing Brillouin gain spectrum (BGS) with its corresponding temperature reading in the training dataset. It was found that all of the ML algorithms have significantly reduced the signal processing time to be between 3.5 and 655 times faster than the conventional Lorentzian curve fitting (LCF) method. Furthermore, the temperature prediction accuracy and temperature measurement precision made by some algorithms were comparable, and some were even better than the conventional LCF method. The results obtained from the experiments would provide some general idea in deploying ML algorithm for characterizing the Brillouin-based fiber sensor signals.https://www.mdpi.com/2304-6732/7/4/79BOTDAmachine learningdistributed sensor |
spellingShingle | Nur Dalilla Nordin Mohd Saiful Dzulkefly Zan Fairuz Abdullah Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor Photonics BOTDA machine learning distributed sensor |
title | Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor |
title_full | Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor |
title_fullStr | Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor |
title_full_unstemmed | Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor |
title_short | Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor |
title_sort | comparative analysis on the deployment of machine learning algorithms in the distributed brillouin optical time domain analysis botda fiber sensor |
topic | BOTDA machine learning distributed sensor |
url | https://www.mdpi.com/2304-6732/7/4/79 |
work_keys_str_mv | AT nurdalillanordin comparativeanalysisonthedeploymentofmachinelearningalgorithmsinthedistributedbrillouinopticaltimedomainanalysisbotdafibersensor AT mohdsaifuldzulkeflyzan comparativeanalysisonthedeploymentofmachinelearningalgorithmsinthedistributedbrillouinopticaltimedomainanalysisbotdafibersensor AT fairuzabdullah comparativeanalysisonthedeploymentofmachinelearningalgorithmsinthedistributedbrillouinopticaltimedomainanalysisbotdafibersensor |