Comparing quality parameters obtained using destructive and optical methods in grading tomatoes
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Revista ciência agronômica (Online) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902021000300423 |
Resumo: | ABSTRACT Optical methods for analysing fruit quality have various advantages compared to conventional methods, including not destroying the sample and the possibility of automating the quality control process. The aim of this study was to compare artificial neural networks developed from biological activity indices obtained using the biospeckle laser optical technique, and from physico-chemical variables obtained by conventional destructive techniques, through an evaluation of their precision in classifying ripe tomatoes, using as a reference an earlier classification carried out by visual inspection. A total of 150 tomatoes were used in the experiment, divided into three ripening stages. Multivariate principal component analysis was used to evaluate interaction of the variance within the groups of data obtained using the biospeckle laser technique and destructive laboratory methods. Two artificial neural networks were developed, the first generated using biological activity indices as input vectors, and the second using physico-chemical variables. The precision of the two neural networks was compared using the Kappa index and overall accuracy, and was based on a reference classification. The variation in ripening as a function of the biological activity indices was explained by the first principal component. The neural network generated from the biological activity indices showed the best performance in classifying the tomatoes into the three ripening stages, with a significant Kappa index and an overall accuracy of 67.5%. |
id |
UFC-2_8b1f001043e69b7ae216c2a9bf912172 |
---|---|
oai_identifier_str |
oai:scielo:S1806-66902021000300423 |
network_acronym_str |
UFC-2 |
network_name_str |
Revista ciência agronômica (Online) |
repository_id_str |
|
spelling |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoesBiospeckle laserArtificial neural networksPhysico-chemical variablesFruit ripeningABSTRACT Optical methods for analysing fruit quality have various advantages compared to conventional methods, including not destroying the sample and the possibility of automating the quality control process. The aim of this study was to compare artificial neural networks developed from biological activity indices obtained using the biospeckle laser optical technique, and from physico-chemical variables obtained by conventional destructive techniques, through an evaluation of their precision in classifying ripe tomatoes, using as a reference an earlier classification carried out by visual inspection. A total of 150 tomatoes were used in the experiment, divided into three ripening stages. Multivariate principal component analysis was used to evaluate interaction of the variance within the groups of data obtained using the biospeckle laser technique and destructive laboratory methods. Two artificial neural networks were developed, the first generated using biological activity indices as input vectors, and the second using physico-chemical variables. The precision of the two neural networks was compared using the Kappa index and overall accuracy, and was based on a reference classification. The variation in ripening as a function of the biological activity indices was explained by the first principal component. The neural network generated from the biological activity indices showed the best performance in classifying the tomatoes into the three ripening stages, with a significant Kappa index and an overall accuracy of 67.5%.Universidade Federal do Ceará2021-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902021000300423Revista Ciência Agronômica v.52 n.3 2021reponame:Revista ciência agronômica (Online)instname:Universidade Federal do Ceará (UFC)instacron:UFC10.5935/1806-6690.20210066info:eu-repo/semantics/openAccessSilva,Thainara Rebelo daCosta,Anderson GomidePaes,Juliana LoboOliveira,Marcus Vinícius Morais dePinto,Francisco de Assis de Carvalhoeng2021-09-24T00:00:00Zoai:scielo:S1806-66902021000300423Revistahttp://www.ccarevista.ufc.br/PUBhttps://old.scielo.br/oai/scielo-oai.php||alekdutra@ufc.br|| ccarev@ufc.br1806-66900045-6888opendoar:2021-09-24T00:00Revista ciência agronômica (Online) - Universidade Federal do Ceará (UFC)false |
dc.title.none.fl_str_mv |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes |
title |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes |
spellingShingle |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes Silva,Thainara Rebelo da Biospeckle laser Artificial neural networks Physico-chemical variables Fruit ripening |
title_short |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes |
title_full |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes |
title_fullStr |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes |
title_full_unstemmed |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes |
title_sort |
Comparing quality parameters obtained using destructive and optical methods in grading tomatoes |
author |
Silva,Thainara Rebelo da |
author_facet |
Silva,Thainara Rebelo da Costa,Anderson Gomide Paes,Juliana Lobo Oliveira,Marcus Vinícius Morais de Pinto,Francisco de Assis de Carvalho |
author_role |
author |
author2 |
Costa,Anderson Gomide Paes,Juliana Lobo Oliveira,Marcus Vinícius Morais de Pinto,Francisco de Assis de Carvalho |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Silva,Thainara Rebelo da Costa,Anderson Gomide Paes,Juliana Lobo Oliveira,Marcus Vinícius Morais de Pinto,Francisco de Assis de Carvalho |
dc.subject.por.fl_str_mv |
Biospeckle laser Artificial neural networks Physico-chemical variables Fruit ripening |
topic |
Biospeckle laser Artificial neural networks Physico-chemical variables Fruit ripening |
description |
ABSTRACT Optical methods for analysing fruit quality have various advantages compared to conventional methods, including not destroying the sample and the possibility of automating the quality control process. The aim of this study was to compare artificial neural networks developed from biological activity indices obtained using the biospeckle laser optical technique, and from physico-chemical variables obtained by conventional destructive techniques, through an evaluation of their precision in classifying ripe tomatoes, using as a reference an earlier classification carried out by visual inspection. A total of 150 tomatoes were used in the experiment, divided into three ripening stages. Multivariate principal component analysis was used to evaluate interaction of the variance within the groups of data obtained using the biospeckle laser technique and destructive laboratory methods. Two artificial neural networks were developed, the first generated using biological activity indices as input vectors, and the second using physico-chemical variables. The precision of the two neural networks was compared using the Kappa index and overall accuracy, and was based on a reference classification. The variation in ripening as a function of the biological activity indices was explained by the first principal component. The neural network generated from the biological activity indices showed the best performance in classifying the tomatoes into the three ripening stages, with a significant Kappa index and an overall accuracy of 67.5%. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902021000300423 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902021000300423 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.5935/1806-6690.20210066 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Universidade Federal do Ceará |
publisher.none.fl_str_mv |
Universidade Federal do Ceará |
dc.source.none.fl_str_mv |
Revista Ciência Agronômica v.52 n.3 2021 reponame:Revista ciência agronômica (Online) instname:Universidade Federal do Ceará (UFC) instacron:UFC |
instname_str |
Universidade Federal do Ceará (UFC) |
instacron_str |
UFC |
institution |
UFC |
reponame_str |
Revista ciência agronômica (Online) |
collection |
Revista ciência agronômica (Online) |
repository.name.fl_str_mv |
Revista ciência agronômica (Online) - Universidade Federal do Ceará (UFC) |
repository.mail.fl_str_mv |
||alekdutra@ufc.br|| ccarev@ufc.br |
_version_ |
1750297490307940352 |