Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.1/17105 |
Resumo: | Calibration transfer (CT) is required when a model developed on one instrument needs to be transferred and used on a new instrument. Several methods are available in the chemometrics domain to transfer the multivariate calibrations developed using modelling techniques such as partial least-square regression. However, recently deep learning (DL) models are gaining popularity to model spectral data. The traditional multivariate CT methods are not suitable to transfer a deep learning model which is based on neural networks architectures. Hence, this study presents the concept of deep calibration transfer (CT) for transferring a DL model made on one instrument onto a new instrument. The deep CT is based on the concept of transfer learning from the DL domain. To show it, two different CT cases are presented. The first case is the CT between benchtop FT-NIR (Fourier Transform Near Infrared) instruments, and the second case is the CT between handheld NIR (Near Infrared) instruments. In both the demonstrated cases, the transfer was performed standard-free i.e., no common standard samples were used to estimate any transfer function. The results showed that with deep CT, the DL models made on one instrument can be easily adapted and transferred to a new instrument. The main benefit of the deep CT is that it is a standard free approach and does not require any standard sample measurements. Such a standard free approach to transfer DL models between instruments can support a widespread sharing of chemometric DL models between the scientific practitioners. |
id |
RCAP_011cbd57f7f020bfcc5758d0e72ce412 |
---|---|
oai_identifier_str |
oai:sapientia.ualg.pt:10400.1/17105 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instrumentsTransferência profunda de calibração: Transferência de modelos de aprendizagem profunda entre instrumentos de espectroscopia infravermelhaStandard-freeSpectroscopyModel updateConvolutional neural networksCalibration transfer (CT) is required when a model developed on one instrument needs to be transferred and used on a new instrument. Several methods are available in the chemometrics domain to transfer the multivariate calibrations developed using modelling techniques such as partial least-square regression. However, recently deep learning (DL) models are gaining popularity to model spectral data. The traditional multivariate CT methods are not suitable to transfer a deep learning model which is based on neural networks architectures. Hence, this study presents the concept of deep calibration transfer (CT) for transferring a DL model made on one instrument onto a new instrument. The deep CT is based on the concept of transfer learning from the DL domain. To show it, two different CT cases are presented. The first case is the CT between benchtop FT-NIR (Fourier Transform Near Infrared) instruments, and the second case is the CT between handheld NIR (Near Infrared) instruments. In both the demonstrated cases, the transfer was performed standard-free i.e., no common standard samples were used to estimate any transfer function. The results showed that with deep CT, the DL models made on one instrument can be easily adapted and transferred to a new instrument. The main benefit of the deep CT is that it is a standard free approach and does not require any standard sample measurements. Such a standard free approach to transfer DL models between instruments can support a widespread sharing of chemometric DL models between the scientific practitioners.ElsevierSapientiaMishra, PuneetPassos, Dário2021-09-14T11:47:07Z2021-092021-09-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.1/17105eng10.1016/j.infrared.2021.1038631879-0275info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-24T10:29:13Zoai:sapientia.ualg.pt:10400.1/17105Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:07:06.550494Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments Transferência profunda de calibração: Transferência de modelos de aprendizagem profunda entre instrumentos de espectroscopia infravermelha |
title |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments |
spellingShingle |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments Mishra, Puneet Standard-free Spectroscopy Model update Convolutional neural networks |
title_short |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments |
title_full |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments |
title_fullStr |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments |
title_full_unstemmed |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments |
title_sort |
Deep calibration transfer: transferring deep learning models between infrared spectroscopy instruments |
author |
Mishra, Puneet |
author_facet |
Mishra, Puneet Passos, Dário |
author_role |
author |
author2 |
Passos, Dário |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Sapientia |
dc.contributor.author.fl_str_mv |
Mishra, Puneet Passos, Dário |
dc.subject.por.fl_str_mv |
Standard-free Spectroscopy Model update Convolutional neural networks |
topic |
Standard-free Spectroscopy Model update Convolutional neural networks |
description |
Calibration transfer (CT) is required when a model developed on one instrument needs to be transferred and used on a new instrument. Several methods are available in the chemometrics domain to transfer the multivariate calibrations developed using modelling techniques such as partial least-square regression. However, recently deep learning (DL) models are gaining popularity to model spectral data. The traditional multivariate CT methods are not suitable to transfer a deep learning model which is based on neural networks architectures. Hence, this study presents the concept of deep calibration transfer (CT) for transferring a DL model made on one instrument onto a new instrument. The deep CT is based on the concept of transfer learning from the DL domain. To show it, two different CT cases are presented. The first case is the CT between benchtop FT-NIR (Fourier Transform Near Infrared) instruments, and the second case is the CT between handheld NIR (Near Infrared) instruments. In both the demonstrated cases, the transfer was performed standard-free i.e., no common standard samples were used to estimate any transfer function. The results showed that with deep CT, the DL models made on one instrument can be easily adapted and transferred to a new instrument. The main benefit of the deep CT is that it is a standard free approach and does not require any standard sample measurements. Such a standard free approach to transfer DL models between instruments can support a widespread sharing of chemometric DL models between the scientific practitioners. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-09-14T11:47:07Z 2021-09 2021-09-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.1/17105 |
url |
http://hdl.handle.net/10400.1/17105 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1016/j.infrared.2021.103863 1879-0275 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799133315677028352 |