Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy

Detalhes bibliográficos
Autor(a) principal: Chen,Cun-wu
Data de Publicação: 2014
Outros Autores: Yan,Hui, Han,Bang-xing
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Revista Brasileira de Farmacognosia (Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-695X2014000100033
Resumo: A total of 139 batches of Chrysanthemum samples were randomly divided into calibration set (92 batches) and prediction set (47 batches). The near infrared diffuses reflectance spectra of Chrysanthemum varieties were preprocessed by a first order derivative (D1) and autoscaling, and a modelwas built using partial least squares analysis. In this study, three Chrysanthemum varieties were identified, the accuracy rates in calibration sets of Dabaiju, Huju, and Xiaobaiju are 97.60, 96.65, and 94.70%, respectively; And 95.16, 86.11, and 93.46% accuracy rate in prediction sets was obtained. The research results demonstrate that the qualitative analysis can be conducted by machine learning combined with Near-Infrared Spectroscopy, which provides a new method for rapid and non-invasive identification of Chrysanthemum varieties.
id SBFGNOSIA-1_8ad2c3d1ae1ef0bbd1db4c16d69d3c41
oai_identifier_str oai:scielo:S0102-695X2014000100033
network_acronym_str SBFGNOSIA-1
network_name_str Revista Brasileira de Farmacognosia (Online)
repository_id_str
spelling Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopyChrysanthemum morifoliumNear infrared spectroscopyRapid detectionA total of 139 batches of Chrysanthemum samples were randomly divided into calibration set (92 batches) and prediction set (47 batches). The near infrared diffuses reflectance spectra of Chrysanthemum varieties were preprocessed by a first order derivative (D1) and autoscaling, and a modelwas built using partial least squares analysis. In this study, three Chrysanthemum varieties were identified, the accuracy rates in calibration sets of Dabaiju, Huju, and Xiaobaiju are 97.60, 96.65, and 94.70%, respectively; And 95.16, 86.11, and 93.46% accuracy rate in prediction sets was obtained. The research results demonstrate that the qualitative analysis can be conducted by machine learning combined with Near-Infrared Spectroscopy, which provides a new method for rapid and non-invasive identification of Chrysanthemum varieties.Sociedade Brasileira de Farmacognosia2014-02-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-695X2014000100033Revista Brasileira de Farmacognosia v.24 n.1 2014reponame:Revista Brasileira de Farmacognosia (Online)instname:Sociedade Brasileira de Farmacognosia (SBFgnosia)instacron:SBFGNOSIA10.1590/0102-695X20142413387info:eu-repo/semantics/openAccessChen,Cun-wuYan,HuiHan,Bang-xingeng2015-08-27T00:00:00Zoai:scielo:S0102-695X2014000100033Revistahttp://www.sbfgnosia.org.br/revista/https://old.scielo.br/oai/scielo-oai.phprbgnosia@ltf.ufpb.br1981-528X0102-695Xopendoar:2015-08-27T00:00Revista Brasileira de Farmacognosia (Online) - Sociedade Brasileira de Farmacognosia (SBFgnosia)false
dc.title.none.fl_str_mv Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
title Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
spellingShingle Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
Chen,Cun-wu
Chrysanthemum morifolium
Near infrared spectroscopy
Rapid detection
title_short Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
title_full Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
title_fullStr Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
title_full_unstemmed Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
title_sort Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy
author Chen,Cun-wu
author_facet Chen,Cun-wu
Yan,Hui
Han,Bang-xing
author_role author
author2 Yan,Hui
Han,Bang-xing
author2_role author
author
dc.contributor.author.fl_str_mv Chen,Cun-wu
Yan,Hui
Han,Bang-xing
dc.subject.por.fl_str_mv Chrysanthemum morifolium
Near infrared spectroscopy
Rapid detection
topic Chrysanthemum morifolium
Near infrared spectroscopy
Rapid detection
description A total of 139 batches of Chrysanthemum samples were randomly divided into calibration set (92 batches) and prediction set (47 batches). The near infrared diffuses reflectance spectra of Chrysanthemum varieties were preprocessed by a first order derivative (D1) and autoscaling, and a modelwas built using partial least squares analysis. In this study, three Chrysanthemum varieties were identified, the accuracy rates in calibration sets of Dabaiju, Huju, and Xiaobaiju are 97.60, 96.65, and 94.70%, respectively; And 95.16, 86.11, and 93.46% accuracy rate in prediction sets was obtained. The research results demonstrate that the qualitative analysis can be conducted by machine learning combined with Near-Infrared Spectroscopy, which provides a new method for rapid and non-invasive identification of Chrysanthemum varieties.
publishDate 2014
dc.date.none.fl_str_mv 2014-02-01
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=S0102-695X2014000100033
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0102-695X2014000100033
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/0102-695X20142413387
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 Sociedade Brasileira de Farmacognosia
publisher.none.fl_str_mv Sociedade Brasileira de Farmacognosia
dc.source.none.fl_str_mv Revista Brasileira de Farmacognosia v.24 n.1 2014
reponame:Revista Brasileira de Farmacognosia (Online)
instname:Sociedade Brasileira de Farmacognosia (SBFgnosia)
instacron:SBFGNOSIA
instname_str Sociedade Brasileira de Farmacognosia (SBFgnosia)
instacron_str SBFGNOSIA
institution SBFGNOSIA
reponame_str Revista Brasileira de Farmacognosia (Online)
collection Revista Brasileira de Farmacognosia (Online)
repository.name.fl_str_mv Revista Brasileira de Farmacognosia (Online) - Sociedade Brasileira de Farmacognosia (SBFgnosia)
repository.mail.fl_str_mv rbgnosia@ltf.ufpb.br
_version_ 1752122468811669504

Registros relacionados