Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography

Electrical tomography is a non-invasive method of monitoring the interior of objects, which is used in various industries. In particular, it is possible to monitor industrial processes inside reactors and tanks using tomography. Tomography enables real-time observation of crystals or gas bubbles gro...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Grzegorz Kłosowski, Tomasz Rymarczyk, Konrad Niderla, Magdalena Rzemieniak, Artur Dmowski, Michał Maj
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	electrical tomography industrial tomography machine learning neural networks long short-term memory (LSTM) networks Technology T
Acceso en línea:	https://doaj.org/article/825b2602f3fb4e5c98256a043769b9d5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:825b2602f3fb4e5c98256a043769b9d5
record_format	dspace
spelling	oai:doaj.org-article:825b2602f3fb4e5c98256a043769b9d52021-11-11T16:01:25ZComparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography10.3390/en142172691996-1073https://doaj.org/article/825b2602f3fb4e5c98256a043769b9d52021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7269https://doaj.org/toc/1996-1073Electrical tomography is a non-invasive method of monitoring the interior of objects, which is used in various industries. In particular, it is possible to monitor industrial processes inside reactors and tanks using tomography. Tomography enables real-time observation of crystals or gas bubbles growing in a liquid. However, obtaining high-resolution tomographic images is problematic because it involves solving the so-called ill-posed inverse problem. Noisy input data cause problems, too. Therefore, the use of appropriate hardware solutions to eliminate this phenomenon is necessary. An important cause of obtaining accurate tomographic images may also be the incorrect selection of algorithmic methods used to convert the measurements into the output images. In a dynamically changing environment of a tank reactor, selecting the optimal algorithmic method used to create a tomographic image becomes an optimization problem. This article presents the machine learning method’s original concept of intelligent selection depending on the reconstructed case. The long short-term memory network was used to classify the methods to choose one of the five homogenous methods—elastic net, linear regression with the least-squares learner, linear regression with support vector machine learner, support vector machine model, or artificial neural networks. In the presented research, tomographic images of selected measurement cases, reconstructed using five methods, were compared. Then, the selection methods’ accuracy was verified thanks to the long short-term memory network used as a classifier. The results proved that the new concept of long short-term memory classification ensures better tomographic reconstructions efficiency than imaging all measurement cases with single homogeneous methods.Grzegorz KłosowskiTomasz RymarczykKonrad NiderlaMagdalena RzemieniakArtur DmowskiMichał MajMDPI AGarticleelectrical tomographyindustrial tomographymachine learningneural networkslong short-term memory (LSTM) networksTechnologyTENEnergies, Vol 14, Iss 7269, p 7269 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	electrical tomography industrial tomography machine learning neural networks long short-term memory (LSTM) networks Technology T
spellingShingle	electrical tomography industrial tomography machine learning neural networks long short-term memory (LSTM) networks Technology T Grzegorz Kłosowski Tomasz Rymarczyk Konrad Niderla Magdalena Rzemieniak Artur Dmowski Michał Maj Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography
description	Electrical tomography is a non-invasive method of monitoring the interior of objects, which is used in various industries. In particular, it is possible to monitor industrial processes inside reactors and tanks using tomography. Tomography enables real-time observation of crystals or gas bubbles growing in a liquid. However, obtaining high-resolution tomographic images is problematic because it involves solving the so-called ill-posed inverse problem. Noisy input data cause problems, too. Therefore, the use of appropriate hardware solutions to eliminate this phenomenon is necessary. An important cause of obtaining accurate tomographic images may also be the incorrect selection of algorithmic methods used to convert the measurements into the output images. In a dynamically changing environment of a tank reactor, selecting the optimal algorithmic method used to create a tomographic image becomes an optimization problem. This article presents the machine learning method’s original concept of intelligent selection depending on the reconstructed case. The long short-term memory network was used to classify the methods to choose one of the five homogenous methods—elastic net, linear regression with the least-squares learner, linear regression with support vector machine learner, support vector machine model, or artificial neural networks. In the presented research, tomographic images of selected measurement cases, reconstructed using five methods, were compared. Then, the selection methods’ accuracy was verified thanks to the long short-term memory network used as a classifier. The results proved that the new concept of long short-term memory classification ensures better tomographic reconstructions efficiency than imaging all measurement cases with single homogeneous methods.
format	article
author	Grzegorz Kłosowski Tomasz Rymarczyk Konrad Niderla Magdalena Rzemieniak Artur Dmowski Michał Maj
author_facet	Grzegorz Kłosowski Tomasz Rymarczyk Konrad Niderla Magdalena Rzemieniak Artur Dmowski Michał Maj
author_sort	Grzegorz Kłosowski
title	Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography
title_short	Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography
title_full	Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography
title_fullStr	Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography
title_full_unstemmed	Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography
title_sort	comparison of machine learning methods for image reconstruction using the lstm classifier in industrial electrical tomography
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/825b2602f3fb4e5c98256a043769b9d5
work_keys_str_mv	AT grzegorzkłosowski comparisonofmachinelearningmethodsforimagereconstructionusingthelstmclassifierinindustrialelectricaltomography AT tomaszrymarczyk comparisonofmachinelearningmethodsforimagereconstructionusingthelstmclassifierinindustrialelectricaltomography AT konradniderla comparisonofmachinelearningmethodsforimagereconstructionusingthelstmclassifierinindustrialelectricaltomography AT magdalenarzemieniak comparisonofmachinelearningmethodsforimagereconstructionusingthelstmclassifierinindustrialelectricaltomography AT arturdmowski comparisonofmachinelearningmethodsforimagereconstructionusingthelstmclassifierinindustrialelectricaltomography AT michałmaj comparisonofmachinelearningmethodsforimagereconstructionusingthelstmclassifierinindustrialelectricaltomography
_version_	1718432424898068480

Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography

Ejemplares similares