Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat

Detalhes bibliográficos
Autor(a) principal: Pinto,Luiz Alberto
Data de Publicação: 2011
Outros Autores: Galvão,Roberto K. H., Araújo,Mário César U.
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Journal of the Brazilian Chemical Society (Online)
Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0103-50532011000100025
Resumo: This paper investigates the influence of wavelet family, length and number of resolution levels on the performance of multivariate calibration models obtained in the wavelet domain. Twenty-one physical and chemical properties of diesel, gasoline, corn and wheat were determined by near/mid infrared spectrometry employing partial least-squares (PLS) and stepwise regression (SR) in the original and wavelet domains. Through proper selection of the wavelet transform settings, average RMSEP reductions of 8.2% (PLS) and 27.0% (SR) were obtained with respect to the original domain. However, the SR models presented considerable sensitivity with respect to the choice of transform settings. In this case, an analysis of variance indicated that the number of resolution levels is the most important factor to be considered.
id SBQ-2_b98dc9f1fe314e2e4efdf64ae5c3c59e
oai_identifier_str oai:scielo:S0103-50532011000100025
network_acronym_str SBQ-2
network_name_str Journal of the Brazilian Chemical Society (Online)
repository_id_str
spelling Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheatmultivariate calibrationwavelet transformanalysis of variancemid and near infrared spectrometryfood and fuel analysisThis paper investigates the influence of wavelet family, length and number of resolution levels on the performance of multivariate calibration models obtained in the wavelet domain. Twenty-one physical and chemical properties of diesel, gasoline, corn and wheat were determined by near/mid infrared spectrometry employing partial least-squares (PLS) and stepwise regression (SR) in the original and wavelet domains. Through proper selection of the wavelet transform settings, average RMSEP reductions of 8.2% (PLS) and 27.0% (SR) were obtained with respect to the original domain. However, the SR models presented considerable sensitivity with respect to the choice of transform settings. In this case, an analysis of variance indicated that the number of resolution levels is the most important factor to be considered.Sociedade Brasileira de Química2011-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0103-50532011000100025Journal of the Brazilian Chemical Society v.22 n.1 2011reponame:Journal of the Brazilian Chemical Society (Online)instname:Sociedade Brasileira de Química (SBQ)instacron:SBQ10.1590/S0103-50532011000100025info:eu-repo/semantics/openAccessPinto,Luiz AlbertoGalvão,Roberto K. H.Araújo,Mário César U.eng2011-02-10T00:00:00Zoai:scielo:S0103-50532011000100025Revistahttp://jbcs.sbq.org.brONGhttps://old.scielo.br/oai/scielo-oai.php||office@jbcs.sbq.org.br1678-47900103-5053opendoar:2011-02-10T00:00Journal of the Brazilian Chemical Society (Online) - Sociedade Brasileira de Química (SBQ)false
dc.title.none.fl_str_mv Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
title Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
spellingShingle Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
Pinto,Luiz Alberto
multivariate calibration
wavelet transform
analysis of variance
mid and near infrared spectrometry
food and fuel analysis
title_short Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
title_full Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
title_fullStr Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
title_full_unstemmed Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
title_sort Influence of wavelet transform settings on NIR and MIR spectrometric analyses of diesel, gasoline, corn and wheat
author Pinto,Luiz Alberto
author_facet Pinto,Luiz Alberto
Galvão,Roberto K. H.
Araújo,Mário César U.
author_role author
author2 Galvão,Roberto K. H.
Araújo,Mário César U.
author2_role author
author
dc.contributor.author.fl_str_mv Pinto,Luiz Alberto
Galvão,Roberto K. H.
Araújo,Mário César U.
dc.subject.por.fl_str_mv multivariate calibration
wavelet transform
analysis of variance
mid and near infrared spectrometry
food and fuel analysis
topic multivariate calibration
wavelet transform
analysis of variance
mid and near infrared spectrometry
food and fuel analysis
description This paper investigates the influence of wavelet family, length and number of resolution levels on the performance of multivariate calibration models obtained in the wavelet domain. Twenty-one physical and chemical properties of diesel, gasoline, corn and wheat were determined by near/mid infrared spectrometry employing partial least-squares (PLS) and stepwise regression (SR) in the original and wavelet domains. Through proper selection of the wavelet transform settings, average RMSEP reductions of 8.2% (PLS) and 27.0% (SR) were obtained with respect to the original domain. However, the SR models presented considerable sensitivity with respect to the choice of transform settings. In this case, an analysis of variance indicated that the number of resolution levels is the most important factor to be considered.
publishDate 2011
dc.date.none.fl_str_mv 2011-01-01
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=S0103-50532011000100025
url http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0103-50532011000100025
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 10.1590/S0103-50532011000100025
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 Química
publisher.none.fl_str_mv Sociedade Brasileira de Química
dc.source.none.fl_str_mv Journal of the Brazilian Chemical Society v.22 n.1 2011
reponame:Journal of the Brazilian Chemical Society (Online)
instname:Sociedade Brasileira de Química (SBQ)
instacron:SBQ
instname_str Sociedade Brasileira de Química (SBQ)
instacron_str SBQ
institution SBQ
reponame_str Journal of the Brazilian Chemical Society (Online)
collection Journal of the Brazilian Chemical Society (Online)
repository.name.fl_str_mv Journal of the Brazilian Chemical Society (Online) - Sociedade Brasileira de Química (SBQ)
repository.mail.fl_str_mv ||office@jbcs.sbq.org.br
_version_ 1750318171879899136

Registros relacionados