Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/219473 |
Resumo: | It is widely accepted that feature selection is an essential step in predictive modeling. There are several approaches to feature selection, from filter techniques to meta-heuristics wrapper methods. In this paper, we propose a compilation of tools to optimize the fitting of black-box linear models. The proposed AnTSbe algorithm combines Ant Colony Optimization and Tabu Search memory list for the selection of features and uses l1 and l2 regularization norms to fit the linear models. In addition, a polynomial combination of input features was introduced to further explore the information contained in the original data. As a case study, excitation-emission matrix fluorescence data were used as the primary measurements to predict total sulfur concentration in diesel fuel samples. The sample dataset was divided into S10 (less than 10 ppm of total sulfur), and S100 (mean sulfur content of 100 ppm) groups and local linear models were fit with AnTSbe. For the Diesel S100 local models, using only 5 out of the original 1467 fluorescence pairs, combined with bases expansion, we were able to satisfactorily predict total sulfur content in samples with MAPE of less than 4% and RMSE of 4.68 ppm, for the test subset. For the Diesel S10 local models, the use of 4 Ex/Em pairs was sufficient to predict sulfur content with MAPE 0.24%, and RMSE of 0.015 ppm, for the test subset. Our experimental results demonstrate that the proposed methodology was able to satisfactorily optimize the fitting of linear models to predict sulfur content in diesel fuel samples without need of chemical of physical pre-treatment, and was superior to classic PLS regression methods and also to our previous results with ant colony optimization studies in the same dataset. The proposed AnTSbe can be directly applied to data from other sources without need for adaptations. |
id |
UFRGS-2_b7c2cc15b8c672af0fd0c4bad0c7476e |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/219473 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Ranzan, LucasTrierweiler, Luciane FerreiraTrierweiler, Jorge Otávio2021-04-06T04:19:42Z20200169-7439http://hdl.handle.net/10183/219473001123274It is widely accepted that feature selection is an essential step in predictive modeling. There are several approaches to feature selection, from filter techniques to meta-heuristics wrapper methods. In this paper, we propose a compilation of tools to optimize the fitting of black-box linear models. The proposed AnTSbe algorithm combines Ant Colony Optimization and Tabu Search memory list for the selection of features and uses l1 and l2 regularization norms to fit the linear models. In addition, a polynomial combination of input features was introduced to further explore the information contained in the original data. As a case study, excitation-emission matrix fluorescence data were used as the primary measurements to predict total sulfur concentration in diesel fuel samples. The sample dataset was divided into S10 (less than 10 ppm of total sulfur), and S100 (mean sulfur content of 100 ppm) groups and local linear models were fit with AnTSbe. For the Diesel S100 local models, using only 5 out of the original 1467 fluorescence pairs, combined with bases expansion, we were able to satisfactorily predict total sulfur content in samples with MAPE of less than 4% and RMSE of 4.68 ppm, for the test subset. For the Diesel S10 local models, the use of 4 Ex/Em pairs was sufficient to predict sulfur content with MAPE 0.24%, and RMSE of 0.015 ppm, for the test subset. Our experimental results demonstrate that the proposed methodology was able to satisfactorily optimize the fitting of linear models to predict sulfur content in diesel fuel samples without need of chemical of physical pre-treatment, and was superior to classic PLS regression methods and also to our previous results with ant colony optimization studies in the same dataset. The proposed AnTSbe can be directly applied to data from other sources without need for adaptations.application/pdfengChemometrics and Intelligent Laboratory Systems [recurso eletrônico]. Amsterdam. Vol. 206 (Nov. 2019), art. 104161, 11 p.FluorescênciaÓleo dieselOtimização de processosEspectroscopiaAnt colony optimizationTabu searchPolynomial combinationEEM FluorescenceDieselSulfurPrediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansionEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001123274.pdf.txt001123274.pdf.txtExtracted Texttext/plain68243http://www.lume.ufrgs.br/bitstream/10183/219473/2/001123274.pdf.txt8de4b66cb3327bdb9ec282b40eab9336MD52ORIGINAL001123274.pdfTexto completo (inglês)application/pdf1351980http://www.lume.ufrgs.br/bitstream/10183/219473/1/001123274.pdff22675ae74928bec7bf927ef6102a4d7MD5110183/2194732021-05-07 04:55:10.356553oai:www.lume.ufrgs.br:10183/219473Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2021-05-07T07:55:10Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion |
title |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion |
spellingShingle |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion Ranzan, Lucas Fluorescência Óleo diesel Otimização de processos Espectroscopia Ant colony optimization Tabu search Polynomial combination EEM Fluorescence Diesel Sulfur |
title_short |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion |
title_full |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion |
title_fullStr |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion |
title_full_unstemmed |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion |
title_sort |
Prediction of sulfur content in diesel fuel using fluorescence spectroscopy and a hybrid ant colony : Tabu Search algorithm with polynomial bases expansion |
author |
Ranzan, Lucas |
author_facet |
Ranzan, Lucas Trierweiler, Luciane Ferreira Trierweiler, Jorge Otávio |
author_role |
author |
author2 |
Trierweiler, Luciane Ferreira Trierweiler, Jorge Otávio |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Ranzan, Lucas Trierweiler, Luciane Ferreira Trierweiler, Jorge Otávio |
dc.subject.por.fl_str_mv |
Fluorescência Óleo diesel Otimização de processos Espectroscopia |
topic |
Fluorescência Óleo diesel Otimização de processos Espectroscopia Ant colony optimization Tabu search Polynomial combination EEM Fluorescence Diesel Sulfur |
dc.subject.eng.fl_str_mv |
Ant colony optimization Tabu search Polynomial combination EEM Fluorescence Diesel Sulfur |
description |
It is widely accepted that feature selection is an essential step in predictive modeling. There are several approaches to feature selection, from filter techniques to meta-heuristics wrapper methods. In this paper, we propose a compilation of tools to optimize the fitting of black-box linear models. The proposed AnTSbe algorithm combines Ant Colony Optimization and Tabu Search memory list for the selection of features and uses l1 and l2 regularization norms to fit the linear models. In addition, a polynomial combination of input features was introduced to further explore the information contained in the original data. As a case study, excitation-emission matrix fluorescence data were used as the primary measurements to predict total sulfur concentration in diesel fuel samples. The sample dataset was divided into S10 (less than 10 ppm of total sulfur), and S100 (mean sulfur content of 100 ppm) groups and local linear models were fit with AnTSbe. For the Diesel S100 local models, using only 5 out of the original 1467 fluorescence pairs, combined with bases expansion, we were able to satisfactorily predict total sulfur content in samples with MAPE of less than 4% and RMSE of 4.68 ppm, for the test subset. For the Diesel S10 local models, the use of 4 Ex/Em pairs was sufficient to predict sulfur content with MAPE 0.24%, and RMSE of 0.015 ppm, for the test subset. Our experimental results demonstrate that the proposed methodology was able to satisfactorily optimize the fitting of linear models to predict sulfur content in diesel fuel samples without need of chemical of physical pre-treatment, and was superior to classic PLS regression methods and also to our previous results with ant colony optimization studies in the same dataset. The proposed AnTSbe can be directly applied to data from other sources without need for adaptations. |
publishDate |
2020 |
dc.date.issued.fl_str_mv |
2020 |
dc.date.accessioned.fl_str_mv |
2021-04-06T04:19:42Z |
dc.type.driver.fl_str_mv |
Estrangeiro 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://hdl.handle.net/10183/219473 |
dc.identifier.issn.pt_BR.fl_str_mv |
0169-7439 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001123274 |
identifier_str_mv |
0169-7439 001123274 |
url |
http://hdl.handle.net/10183/219473 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Chemometrics and Intelligent Laboratory Systems [recurso eletrônico]. Amsterdam. Vol. 206 (Nov. 2019), art. 104161, 11 p. |
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.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/219473/2/001123274.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/219473/1/001123274.pdf |
bitstream.checksum.fl_str_mv |
8de4b66cb3327bdb9ec282b40eab9336 f22675ae74928bec7bf927ef6102a4d7 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801225012188807168 |