Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture

Detalhes bibliográficos
Autor(a) principal: Martins, J. A
Data de Publicação: 2023
Outros Autores: Rodrigues, Daniela, Cavaco, A. M., Antunes, Maria Dulce, Guerra, Rui Manuel Farinha das Neves
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.1/19722
Resumo: Spectra-based methods are becoming increasingly important in Precision Agriculture as they offer non-destructive, quick tools for measuring the quality of produce. This study introduces a novel approach for esti-mating the soluble solids content (SSC) of 'Rocha' pears using the SpectraNet-32 deep learning architecture, which operates on 1D fruit spectra in the visible to near-infrared region (Vis-NIRS). This method was also able to estimate fruit temperatures, which improved the SSC prediction performance. The dataset consisted of 3300 spectra from 1650 'Rocha' pears collected from local markets over several weeks during the 2010 and 2011 seasons, which had varying edaphoclimatic conditions. Two types of partial least squares (PLS) feature selection methods, under various configurations, were applied to the input spectra to identify the most significant wavelengths for training SpectraNet-32. The model's robustness was also compared to a similar state-of-the-art deep learning architecture, DeepSpectra, as well as four other classical machine learning algorithms: PLS, multiple linear regression (MLR), support vector machine (SVM), and multi-layer perceptron (MLP). In total, 23 different experimental method configurations were assessed, with 150 neural networks each. SpectraNet-32 consistently outperformed other methods in several metrics. On average, it was 6.1% better than PLS in terms of the root mean square error of prediction (RMSEP, 1.08 vs. 1.15%), 7.7% better in prediction gain (PG, 1.67 vs. 1.55), 3.6% better in the coefficient of determination (R2, 0.58 vs. 0.56) and 5.8% better in the coefficient of variation (CV%, 8.35 vs. 8.86).
id RCAP_e81f0a5d8ee6e92ad0975cf3ca0e0382
oai_identifier_str oai:sapientia.ualg.pt:10400.1/19722
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architectureDeep learningResidual networkNear-infraredSpectroscopyPear fruitSpectra-based methods are becoming increasingly important in Precision Agriculture as they offer non-destructive, quick tools for measuring the quality of produce. This study introduces a novel approach for esti-mating the soluble solids content (SSC) of 'Rocha' pears using the SpectraNet-32 deep learning architecture, which operates on 1D fruit spectra in the visible to near-infrared region (Vis-NIRS). This method was also able to estimate fruit temperatures, which improved the SSC prediction performance. The dataset consisted of 3300 spectra from 1650 'Rocha' pears collected from local markets over several weeks during the 2010 and 2011 seasons, which had varying edaphoclimatic conditions. Two types of partial least squares (PLS) feature selection methods, under various configurations, were applied to the input spectra to identify the most significant wavelengths for training SpectraNet-32. The model's robustness was also compared to a similar state-of-the-art deep learning architecture, DeepSpectra, as well as four other classical machine learning algorithms: PLS, multiple linear regression (MLR), support vector machine (SVM), and multi-layer perceptron (MLP). In total, 23 different experimental method configurations were assessed, with 150 neural networks each. SpectraNet-32 consistently outperformed other methods in several metrics. On average, it was 6.1% better than PLS in terms of the root mean square error of prediction (RMSEP, 1.08 vs. 1.15%), 7.7% better in prediction gain (PG, 1.67 vs. 1.55), 3.6% better in the coefficient of determination (R2, 0.58 vs. 0.56) and 5.8% better in the coefficient of variation (CV%, 8.35 vs. 8.86).ElsevierSapientiaMartins, J. ARodrigues, DanielaCavaco, A. M.Antunes, Maria DulceGuerra, Rui Manuel Farinha das Neves2023-06-21T10:30:44Z20232023-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.1/19722eng0925-521410.1016/j.postharvbio.2023.112281info: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:RCAAP2023-07-24T10:32:11Zoai:sapientia.ualg.pt:10400.1/19722Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T20:09:16.674895Repositório 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 Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
title Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
spellingShingle Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
Martins, J. A
Deep learning
Residual network
Near-infrared
Spectroscopy
Pear fruit
title_short Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
title_full Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
title_fullStr Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
title_full_unstemmed Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
title_sort Estimation of soluble solids content and fruit temperature in 'rocha' pear using Vis-NIR spectroscopy and the spectraNet–32 deep learning architecture
author Martins, J. A
author_facet Martins, J. A
Rodrigues, Daniela
Cavaco, A. M.
Antunes, Maria Dulce
Guerra, Rui Manuel Farinha das Neves
author_role author
author2 Rodrigues, Daniela
Cavaco, A. M.
Antunes, Maria Dulce
Guerra, Rui Manuel Farinha das Neves
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Sapientia
dc.contributor.author.fl_str_mv Martins, J. A
Rodrigues, Daniela
Cavaco, A. M.
Antunes, Maria Dulce
Guerra, Rui Manuel Farinha das Neves
dc.subject.por.fl_str_mv Deep learning
Residual network
Near-infrared
Spectroscopy
Pear fruit
topic Deep learning
Residual network
Near-infrared
Spectroscopy
Pear fruit
description Spectra-based methods are becoming increasingly important in Precision Agriculture as they offer non-destructive, quick tools for measuring the quality of produce. This study introduces a novel approach for esti-mating the soluble solids content (SSC) of 'Rocha' pears using the SpectraNet-32 deep learning architecture, which operates on 1D fruit spectra in the visible to near-infrared region (Vis-NIRS). This method was also able to estimate fruit temperatures, which improved the SSC prediction performance. The dataset consisted of 3300 spectra from 1650 'Rocha' pears collected from local markets over several weeks during the 2010 and 2011 seasons, which had varying edaphoclimatic conditions. Two types of partial least squares (PLS) feature selection methods, under various configurations, were applied to the input spectra to identify the most significant wavelengths for training SpectraNet-32. The model's robustness was also compared to a similar state-of-the-art deep learning architecture, DeepSpectra, as well as four other classical machine learning algorithms: PLS, multiple linear regression (MLR), support vector machine (SVM), and multi-layer perceptron (MLP). In total, 23 different experimental method configurations were assessed, with 150 neural networks each. SpectraNet-32 consistently outperformed other methods in several metrics. On average, it was 6.1% better than PLS in terms of the root mean square error of prediction (RMSEP, 1.08 vs. 1.15%), 7.7% better in prediction gain (PG, 1.67 vs. 1.55), 3.6% better in the coefficient of determination (R2, 0.58 vs. 0.56) and 5.8% better in the coefficient of variation (CV%, 8.35 vs. 8.86).
publishDate 2023
dc.date.none.fl_str_mv 2023-06-21T10:30:44Z
2023
2023-01-01T00:00:00Z
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/10400.1/19722
url http://hdl.handle.net/10400.1/19722
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0925-5214
10.1016/j.postharvbio.2023.112281
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_ 1799133340442296320