Support Vector Machines In Tandem With Infrared Spectroscopy For Geographical Classification Of Green Arabica Coffee

dc.creatorBona
dc.creatorEvandro; Marquetti
dc.creatorIzabele; Link
dc.creatorJade Varaschim; Figueiredo Makimori
dc.creatorGustavo Yasuo; Arca
dc.creatorVinicius da Costa; Guimaraes Lemes
dc.creatorAndre Luis; Garcia Ferreira
dc.creatorJuliana Mendes; dos Santos Scholz
dc.creatorMaria Brigida; Valderrama
dc.creatorPatricia; Poppi
dc.creatorRonei Jesus
dc.date2017
dc.datemar
dc.date2017-11-13T11:33:13Z
dc.date2017-11-13T11:33:13Z
dc.date.accessioned2018-03-29T05:47:42Z
dc.date.available2018-03-29T05:47:42Z
dc.identifierLwt-food Science And Technology. Elsevier Science Bv, v. 76, p. 330 - 336, 2017.
dc.identifier0023-6438
dc.identifier1096-1127
dc.identifierWOS:000393359500021
dc.identifier10.1016/j.lwt.2016.04.048
dc.identifierhttp://www-sciencedirect-com.ez88.periodicos.capes.gov.br/science/article/pii/S0023643816302328?via%3Dihub
dc.identifierhttp://repositorio.unicamp.br/jspui/handle/REPOSIP/326223
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1363229
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.descriptionThe coffee is an important commodity to Brazil. Species, climate, genotypes, cultivation practices and industrialization are critical to final quality of the beverage. Thus, the development of analytical methods for coffee authentication is important to ensure the origin of the bean. The purpose of this study was to develop a methodology for geographical classification of different genotypes of arabica coffee using infrared spectroscopy and support vector machines (SVM). The spectra were collected in the range of near infrared (NIRS) and mid infrared (FTIR). For the data analysis, a SVM was built using radial basis as kernel function and the one-versus-all multiclass approach. The C and gamma parameters of SVM were optimized using the genetic algorithm. With the application of the NIRS-SVM approach all test samples were correctly classified with a sensitivity and specificity of 100%, while FTIR-SVM had a slightly lower performance. Therefore, it was possible to confirm that infrared spectroscopy is a fast and effective method for geographic certification with little sample preparation, and without the production of chemical wastes. Furthermore, the SVM can be a chemometric alternative in tandem with infrared spectroscopy for another classification problems. (C) 2016 Elsevier Ltd. All rights reserved.
dc.description76
dc.description330
dc.description336
dc.descriptionCAPES
dc.descriptionCNPq [307483/2015-0]
dc.descriptionFundacao Araucaria [383/2014]
dc.descriptionCoordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
dc.descriptionConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
dc.description11th Latin American Symposium on Food Science (SLACA)
dc.descriptionNOV 08-11, 2015
dc.descriptionCampinas, BRAZIL
dc.languageEnglish
dc.publisherElsevier Science BV
dc.publisherAmsterdam
dc.relationLWT-Food Science and Technology
dc.rightsfechado
dc.sourceWOS
dc.subjectMachine Learning
dc.subjectNear Infrared
dc.subjectMid Infrared
dc.subjectGenetic Algorithm
dc.titleSupport Vector Machines In Tandem With Infrared Spectroscopy For Geographical Classification Of Green Arabica Coffee
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución