Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/app13084881 http://hdl.handle.net/11449/247287 |
Resumo: | This work demonstrates the application of an electronic nose (e-nose) for discrimination between authentic and adulterated honey. The developed e-nose is based on electrodes covered with ionogel (ionic liquid + gelatin + Fe3O4 nanoparticle) films. Authentic and adulterated honey samples were submitted to e-nose analysis, and the capacity of the sensors for discrimination between authentic and adulterated honey was evaluated using principal component analysis (PCA) based on average relative response data. From the PCA biplot, it was possible to note two well-defined clusters and no intersection was observed. To evaluate the relative response data as input for autonomous classification, different machine learning algorithms were evaluated, namely instance based (IBK), Kstar, Trees-J48 (J48), random forest (RF), multilayer perceptron (MLP), naive Bayes (NB), and sequential minimal optimization (SMO). Considering the average data, the highest accuracy was obtained for Kstar: 100% (k-fold = 3). Additionally, this algorithm was also compared regarding its sensitivity and specificity, both being 100% for both features. Thus, due to the rapidity, simplicity, and accuracy of the developed methodology, the technology based on e-noses has the potential to be applied to honey quality control. |
id |
UNSP_623c5c2f193c24eb68ef9b2ee1fae3a3 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/247287 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honeyelectronic nosehoney adulterationhoney quality controlmachine learningmultivariate analysissensorsThis work demonstrates the application of an electronic nose (e-nose) for discrimination between authentic and adulterated honey. The developed e-nose is based on electrodes covered with ionogel (ionic liquid + gelatin + Fe3O4 nanoparticle) films. Authentic and adulterated honey samples were submitted to e-nose analysis, and the capacity of the sensors for discrimination between authentic and adulterated honey was evaluated using principal component analysis (PCA) based on average relative response data. From the PCA biplot, it was possible to note two well-defined clusters and no intersection was observed. To evaluate the relative response data as input for autonomous classification, different machine learning algorithms were evaluated, namely instance based (IBK), Kstar, Trees-J48 (J48), random forest (RF), multilayer perceptron (MLP), naive Bayes (NB), and sequential minimal optimization (SMO). Considering the average data, the highest accuracy was obtained for Kstar: 100% (k-fold = 3). Additionally, this algorithm was also compared regarding its sensitivity and specificity, both being 100% for both features. Thus, due to the rapidity, simplicity, and accuracy of the developed methodology, the technology based on e-noses has the potential to be applied to honey quality control.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Instituto de Química Universidade de São Paulo, SPFaculdade de Medicina Veterinária e Zootecnia Universidade Estadual Paulista “Júlio de Mesquita Filho” (UNESP), SPInstituto de Matemática e Estatística Universidade de São Paulo, SPFaculdade de Medicina Veterinária e Zootecnia Universidade Estadual Paulista “Júlio de Mesquita Filho” (UNESP), SPCNPq: 165186/2015-1CNPq: 307501/2019-1CNPq: 424027/2018-6Universidade de São Paulo (USP)Universidade Estadual Paulista (UNESP)Gonçalves, Wellington BelarminoTeixeira, Wanderson Sirley Reis [UNESP]Cervantes, Evelyn PerezMioni, Mateus de Souza Ribeiro [UNESP]Sampaio, Aryele Nunes da Cruz Encide [UNESP]Martins, Otávio Augusto [UNESP]Gruber, JonasPereira, Juliano Gonçalves [UNESP]2023-07-29T13:11:56Z2023-07-29T13:11:56Z2023-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/app13084881Applied Sciences (Switzerland), v. 13, n. 8, 2023.2076-3417http://hdl.handle.net/11449/24728710.3390/app130848812-s2.0-85156114554Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengApplied Sciences (Switzerland)info:eu-repo/semantics/openAccess2023-07-29T13:11:56Zoai:repositorio.unesp.br:11449/247287Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-07-29T13:11:56Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey |
title |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey |
spellingShingle |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey Gonçalves, Wellington Belarmino electronic nose honey adulteration honey quality control machine learning multivariate analysis sensors |
title_short |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey |
title_full |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey |
title_fullStr |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey |
title_full_unstemmed |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey |
title_sort |
Application of an Electronic Nose as a New Technology for Rapid Detection of Adulteration in Honey |
author |
Gonçalves, Wellington Belarmino |
author_facet |
Gonçalves, Wellington Belarmino Teixeira, Wanderson Sirley Reis [UNESP] Cervantes, Evelyn Perez Mioni, Mateus de Souza Ribeiro [UNESP] Sampaio, Aryele Nunes da Cruz Encide [UNESP] Martins, Otávio Augusto [UNESP] Gruber, Jonas Pereira, Juliano Gonçalves [UNESP] |
author_role |
author |
author2 |
Teixeira, Wanderson Sirley Reis [UNESP] Cervantes, Evelyn Perez Mioni, Mateus de Souza Ribeiro [UNESP] Sampaio, Aryele Nunes da Cruz Encide [UNESP] Martins, Otávio Augusto [UNESP] Gruber, Jonas Pereira, Juliano Gonçalves [UNESP] |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade de São Paulo (USP) Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Gonçalves, Wellington Belarmino Teixeira, Wanderson Sirley Reis [UNESP] Cervantes, Evelyn Perez Mioni, Mateus de Souza Ribeiro [UNESP] Sampaio, Aryele Nunes da Cruz Encide [UNESP] Martins, Otávio Augusto [UNESP] Gruber, Jonas Pereira, Juliano Gonçalves [UNESP] |
dc.subject.por.fl_str_mv |
electronic nose honey adulteration honey quality control machine learning multivariate analysis sensors |
topic |
electronic nose honey adulteration honey quality control machine learning multivariate analysis sensors |
description |
This work demonstrates the application of an electronic nose (e-nose) for discrimination between authentic and adulterated honey. The developed e-nose is based on electrodes covered with ionogel (ionic liquid + gelatin + Fe3O4 nanoparticle) films. Authentic and adulterated honey samples were submitted to e-nose analysis, and the capacity of the sensors for discrimination between authentic and adulterated honey was evaluated using principal component analysis (PCA) based on average relative response data. From the PCA biplot, it was possible to note two well-defined clusters and no intersection was observed. To evaluate the relative response data as input for autonomous classification, different machine learning algorithms were evaluated, namely instance based (IBK), Kstar, Trees-J48 (J48), random forest (RF), multilayer perceptron (MLP), naive Bayes (NB), and sequential minimal optimization (SMO). Considering the average data, the highest accuracy was obtained for Kstar: 100% (k-fold = 3). Additionally, this algorithm was also compared regarding its sensitivity and specificity, both being 100% for both features. Thus, due to the rapidity, simplicity, and accuracy of the developed methodology, the technology based on e-noses has the potential to be applied to honey quality control. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T13:11:56Z 2023-07-29T13:11:56Z 2023-04-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.3390/app13084881 Applied Sciences (Switzerland), v. 13, n. 8, 2023. 2076-3417 http://hdl.handle.net/11449/247287 10.3390/app13084881 2-s2.0-85156114554 |
url |
http://dx.doi.org/10.3390/app13084881 http://hdl.handle.net/11449/247287 |
identifier_str_mv |
Applied Sciences (Switzerland), v. 13, n. 8, 2023. 2076-3417 10.3390/app13084881 2-s2.0-85156114554 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Applied Sciences (Switzerland) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1803046732498468864 |