Repository logo
 
Publication

Feature discovery in NIR spectroscopy based Rocha pear classification

2021Journal article Restricted
Simple item page
dc.contributor.authorDaniel, Mariana
dc.contributor.authorGuerra, Rui Manuel Farinha das Neves
dc.contributor.authorBrazio, António
dc.contributor.authorRodrigues, Daniela
dc.contributor.authorM. Cavaco, A.
dc.contributor.authorAntunes, Maria Dulce
dc.contributor.authorValente de Oliveira, JOSÉ
dc.date.accessioned2021-07-07T21:10:30Z
dc.date.available2021-07-07T21:10:30Z
dc.date.issued2021
dc.description.abstractNon-invasive techniques for automatic fruit classification are gaining importance in the global agro-industry as they allow for optimizing harvesting, storage, management, and distribution decisions. Visible, near infra-red (NIR) diffuse reflectance spectroscopy is one of the most employed techniques in such fruit classification. Typically, after the acquisition of a fruit reflectance spectrum the wavelength domain signal is preprocessed and a classifier is designed. Up to now, little or no work considered the problem of feature generation and selection of the reflectance spectrum. This work aims at filling this gap, by exploiting a feature engineering phase before the classifier. The usual approach where the classifier is fed directly with the reflectances measured at each wavelength is contrasted with the proposed division of the spectra into bands and their characterization in wavelength, frequency, and wavelength-frequency domains. Feature selection is also applied for optimizing efficiency, predictive accuracy, and for mitigating over-training. A total of 3050 Rocha pear samples from different origins and harvest years are considered. Statistical tests of hypotheses on classification results of soluble solids content - a predictor of both fruit sweetness and ripeness - show that the proposed preliminary phase of feature engineering outperforms the usual direct approach both in terms of accuracy and in the number of necessary features. Moreover, the method allows for the identification of features that are physical chemistry meaningful.pt_PT
dc.description.sponsorshipFCT - Fundacao para a Ciencia e a Tecnologia, Portugal, through the CEOT strategic projects UID/Multi/00631/2019; UIDB/50022/2020pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1016/j.eswa.2021.114949pt_PT
dc.identifier.issn0957-4174
dc.identifier.urihttp://hdl.handle.net/10400.1/16744
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherElsevierpt_PT
dc.subjectFeature extractionpt_PT
dc.subjectFeature selectionpt_PT
dc.subjectData analysispt_PT
dc.subjectClassificationpt_PT
dc.subjectMachine learningpt_PT
dc.titleFeature discovery in NIR spectroscopy based Rocha pear classificationpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5876/UID%2FMulti%2F00631%2F2013/PT
oaire.citation.startPage114949pt_PT
oaire.citation.titleExpert Systems with Applicationspt_PT
oaire.citation.volume177pt_PT
oaire.fundingStream5876
person.familyNameDaniel
person.familyNameGuerra
person.familyNameBrazio
person.familyNameRodrigues
person.familyNameCavaco Guerra
person.familyNameAntunes
person.familyNameLUÍS VALENTE DE OLIVEIRA
person.givenNameMariana
person.givenNameRui
person.givenNameAntónio
person.givenNameDaniela
person.givenNameAna Margarida
person.givenNameMaria Dulce
person.givenNameJOSÉ
person.identifierC-1285-2012
person.identifier177556
person.identifier.ciencia-id3D16-5067-D6BB
person.identifier.ciencia-id8515-87B4-C511
person.identifier.ciencia-idC91E-B434-E327
person.identifier.ciencia-idC11B-9B05-217E
person.identifier.ciencia-id1F12-C1D3-7717
person.identifier.orcid0000-0003-4434-2910
person.identifier.orcid0000-0002-8642-5792
person.identifier.orcid0000-0002-7675-0719
person.identifier.orcid0000-0003-3659-099X
person.identifier.orcid0000-0003-2708-5991
person.identifier.orcid0000-0002-8913-6136
person.identifier.orcid0000-0001-5337-5699
person.identifier.ridV-3842-2018
person.identifier.ridA-4683-2012
person.identifier.scopus-author-id57194445681
person.identifier.scopus-author-id6602899707
person.identifier.scopus-author-id7102645075
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsrestrictedAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationdd5bbba5-3fb5-4134-8b48-9d06b7cdbd61
relation.isAuthorOfPublicationeff7071e-e676-465b-bae3-983f522acd98
relation.isAuthorOfPublicationb99d8e71-1ebc-460c-bb2f-353c21c2cce7
relation.isAuthorOfPublicationc5ca43cb-937b-4b90-80b6-85c68dac3d96
relation.isAuthorOfPublication18ad736f-b1f3-4a19-9636-e7a80248cf94
relation.isAuthorOfPublication7947cc50-4ae0-4ada-8ddf-081f247adc90
relation.isAuthorOfPublicationbb726e73-690c-4a33-822e-c47bdac3035b
relation.isAuthorOfPublication.latestForDiscoverybb726e73-690c-4a33-822e-c47bdac3035b
relation.isProjectOfPublication093114eb-daa5-4e3d-98ce-bebbf4dde4b8
relation.isProjectOfPublication.latestForDiscovery093114eb-daa5-4e3d-98ce-bebbf4dde4b8

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Expert Systems with Applications.pdf
Size:
1.73 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)