Artificial neural network and regression models to evaluate rheological properties of selected brazilian honeys

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.creatorSilva, Vanelle M. D.-
Autor(es): dc.creatorLacerda, Wilian S.-
Autor(es): dc.creatorResende, Jaime V. de-
Data de aceite: dc.date.accessioned2026-02-09T12:33:52Z-
Data de disponibilização: dc.date.available2026-02-09T12:33:52Z-
Data de envio: dc.date.issued2021-05-25-
Data de envio: dc.date.issued2021-05-25-
Data de envio: dc.date.issued2019-
Fonte completa do material: dc.identifierhttps://repositorio.ufla.br/handle/1/46364-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/capes/1163820-
Descrição: dc.descriptionThe relationships between physico-chemical and rheological properties are considered complex nonlinear systems. Thus, the artificial neural network (ANN) and regression models were used for the rheological characterization of Brazilian honeys, based on lowcost measurements of water content and temperature. The steady shear viscosity (η) performed well when measured in the test phase in a 2-12-1 neuron multilayer perceptron (MLP) ANN (model 1) with a root mean square error (RMSE) and correlation coefficient (r) equal to 0.0430 and 0.9681, respectively. The parameter loss modulus (G’’), storage modulus (G’) and complex viscosity (η*) were predicted in the temperature sweep test by small amplitude oscillatory shear (SAOS) measurements during heating and cooling, and the MLP ANNs with architectures of 2-9-3 (model 2) and 2-3-3 (model 3) showed RMSE values equal to 0.0261 and 0.0387 in the test phase, respectively. For all the determined parameters, non-linear exponential models showed similar results to models 1, 2 and 3. An ANN with 3-9-3 architecture (model 4) showed RMSE and r for G’ equal to 0.0158 and 0.7301, for G’’ equal to 0.0176 and 0.9581, and for η* equal to 0.0407 and 0.9647, respectively, in the test phase for date of the frequency sweep test obtained by SAOS. These results were far superior to those obtained by second-order multiple linear models. The acquisition of all models is an important application for the processing of honey and honey-based products, since these properties are essential in engineering calculations and quality control of products.-
Formato: dc.formatapplication/pdf-
Idioma: dc.languageen-
Publicador: dc.publisherResearch Institute of Horticulture and Apicultural Research Association-
Direitos: dc.rightsAttribution 4.0 International-
Direitos: dc.rightsAttribution 4.0 International-
Direitos: dc.rightsacesso aberto-
Direitos: dc.rightshttp://creativecommons.org/licenses/by/4.0/-
Direitos: dc.rightshttp://creativecommons.org/licenses/by/4.0/-
???dc.source???: dc.sourceJournal of Apicultural Science-
Palavras-chave: dc.subjectApicultura - Modelos matemáticos-
Palavras-chave: dc.subjectMel - Propriedades físico-químicas-
Palavras-chave: dc.subjectMel - Propriedades reológicas-
Palavras-chave: dc.subjectMel - Viscosidade-
Palavras-chave: dc.subjectRedes neurais (Neurobiologia)-
Palavras-chave: dc.subjectRegressão não linear-
Palavras-chave: dc.subjectBee culture - Mathematical models-
Palavras-chave: dc.subjectHoney - Physical and chemical properties-
Palavras-chave: dc.subjectHoney - Rheological properties-
Palavras-chave: dc.subjectHoney - Viscosity-
Palavras-chave: dc.subjectNeural networks (Neurobiology)-
Palavras-chave: dc.subjectNon-linear regression-
Título: dc.titleArtificial neural network and regression models to evaluate rheological properties of selected brazilian honeys-
Tipo de arquivo: dc.typeArtigo-
Aparece nas coleções:Repositório Institucional da Universidade Federal de Lavras (RIUFLA)

Não existem arquivos associados a este item.