Machine and Deep Learning in the Evaluation of Selected Qualitative Characteristics of Sweet Potatoes Obtained under Different Convective Drying Conditions

cris.virtual.author-orcid0000-0002-2535-8370
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid0000-0002-6720-891X
cris.virtual.author-orcid0000-0001-6699-2987
cris.virtual.author-orcid0000-0002-3849-4435
cris.virtual.author-orcid0000-0003-3708-2890
cris.virtualsource.author-orcid898dc715-0fc1-42af-a4d7-0bc909752fee
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid7c4fb780-333e-446e-957f-1ab650ac136d
cris.virtualsource.author-orcid8989a1ba-cd61-4f60-80d5-c1b418028894
cris.virtualsource.author-orcid7583f283-39ec-4125-9e34-6f6a60d31a2d
cris.virtualsource.author-orcida0e99de6-16e7-4a8e-955e-348a7bec4f41
dc.abstract.enThis paper discusses the use of various methods to distinguish between slices of sweet potato dried in different conditions. The drying conditions varied in terms of temperature, the values were: 60 °C, 70 °C, 80 °C, and 90 °C. Examination methods included instrumental texture analysis using a texturometer and digital texture analysis based on macroscopic images. Classification of acquired data involved the use of machine learning techniques using various types of artificial neural networks, such as convolutional neural networks (CNNs) and multi-layer perceptron (MLP). As a result, in the convective drying, changes in color darkening were found in products with the following temperature values: 60 °C (L = 83.41), 70 °C (L = 81.11), 80 °C (L = 79.02), and 90 °C (L = 75.53). The best-generated model achieved an overall classification efficiency of 77%. Sweet potato dried at 90 °C proved to be completely distinguishable from other classes, among which classification efficiency varied between 61–83% depending on the class. This means that image analysis using deep convolutional artificial neural networks is a valuable tool in the context of assessing the quality of convective-dried sweet potato slices.
dc.affiliationWydział Nauk o Żywności i Żywieniu
dc.affiliation.instituteKatedra Mleczarstwa i Inżynierii Procesowej
dc.affiliation.instituteKatedra Zarządzania Jakością i Bezpieczeństwem Żywności
dc.affiliation.instituteKatedra Technologii Żywności Pochodzenia Roślinnego
dc.contributor.authorPrzybył, Krzysztof
dc.contributor.authorAdamski, Franciszek
dc.contributor.authorWawrzyniak, Jolanta
dc.contributor.authorGawrysiak-Witulska, Marzena Bernadeta
dc.contributor.authorStangierski, Jerzy
dc.contributor.authorKmiecik, Dominik
dc.date.access2026-01-26
dc.date.accessioned2026-02-05T13:05:13Z
dc.date.available2026-02-05T13:05:13Z
dc.date.copyright2022-08-04
dc.date.issued2022
dc.description.abstract<jats:p>This paper discusses the use of various methods to distinguish between slices of sweet potato dried in different conditions. The drying conditions varied in terms of temperature, the values were: 60 °C, 70 °C, 80 °C, and 90 °C. Examination methods included instrumental texture analysis using a texturometer and digital texture analysis based on macroscopic images. Classification of acquired data involved the use of machine learning techniques using various types of artificial neural networks, such as convolutional neural networks (CNNs) and multi-layer perceptron (MLP). As a result, in the convective drying, changes in color darkening were found in products with the following temperature values: 60 °C (L = 83.41), 70 °C (L = 81.11), 80 °C (L = 79.02), and 90 °C (L = 75.53). The best-generated model achieved an overall classification efficiency of 77%. Sweet potato dried at 90 °C proved to be completely distinguishable from other classes, among which classification efficiency varied between 61–83% depending on the class. This means that image analysis using deep convolutional artificial neural networks is a valuable tool in the context of assessing the quality of convective-dried sweet potato slices.</jats:p>
dc.description.accesstimeat_publication
dc.description.bibliographyil., bibliogr.
dc.description.financepublication_nocost
dc.description.financecost0,00
dc.description.if2,7
dc.description.number15
dc.description.points100
dc.description.versionfinal_published
dc.description.volume12
dc.identifier.doi10.3390/app12157840
dc.identifier.issn2076-3417
dc.identifier.urihttps://sciencerep.up.poznan.pl/handle/item/7181
dc.identifier.weblinkhttps://www.mdpi.com/2076-3417/12/15/7840
dc.languageen
dc.relation.ispartofApplied Sciences (Switzerland)
dc.relation.pagesart. 7840
dc.rightsCC-BY
dc.sciencecloudnosend
dc.share.typeOPEN_JOURNAL
dc.subject.enartificial neural networks
dc.subject.enconvolutional neural networks
dc.subject.enmachine learning
dc.subject.endeep learning
dc.subject.ensweet potato
dc.subject.enconvective drying
dc.titleMachine and Deep Learning in the Evaluation of Selected Qualitative Characteristics of Sweet Potatoes Obtained under Different Convective Drying Conditions
dc.typeJournalArticle
dspace.entity.typePublication
oaire.citation.issue15
oaire.citation.volume12