Simple item page
 

The application of convolutional neural networks, LF-NMR, and texture for microparticle analysis in assessing the quality of fruit powders: Case study – blackcurrant powders

cris.virtual.author-orcid0000-0002-2535-8370
cris.virtual.author-orcid0000-0002-8244-2763
cris.virtual.author-orcid0000-0001-6597-0858
cris.virtual.author-orcid0000-0002-1365-8130
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid898dc715-0fc1-42af-a4d7-0bc909752fee
cris.virtualsource.author-orcidb06a0b04-dd89-4025-a198-6d97db2079f2
cris.virtualsource.author-orcid08c06993-c96b-41bb-a5f9-551434fdd7df
cris.virtualsource.author-orcid8cd4c9a5-da42-46f1-bc14-052a2b2dec7d
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid4ddc81ce-066b-4d2e-a9f3-015a6c34a525
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
dc.abstract.enIt can be observed that dynamic developments in artificial intelligence contributing to the evolution of existing techniques used in food research. Currently, innovative methods are being sought to support unit processes such as food drying, while at the same time monitoring quality and extending their shelf life. The development of innovative technology using convolutional neural networks (CNNs) to assess the quality of fruit powders seems highly desirable. This will translate into obtaining homogeneous batches of powders based on the specific morphological structure of the obtained microparticles. The research aims to apply convolutional networks to assess the quality, consistency, and homogeneity of blackcurrant powders supported by comparative physical methods of low-field nuclear magnetic resonance (LF-NMR) and texture analysis. The results show that maltodextrin, inulin, whey milk proteins, microcrystalline cellulose, and gum arabic are effective carriers when identifying morphological structure using CNNs. The use of CNNs, texture analysis, and the effect of LF-NMR relaxation time together with statistical elaboration shows that maltodextrin as well as milk whey proteins in combination with inulin achieve the most favorable results. The best results were obtained for a sample containing 50% maltodextrin and 50% maltodextrin (MD50-MD70). The CNN model for this combination had the lowest mean squared error in the test set at 2.5741 × 10−4, confirming its high performance in the classification of blackcurrant powder microstructures.
dc.affiliationWydział Nauk o Żywności i Żywieniu
dc.affiliationWydział Inżynierii Środowiska i Inżynierii Mechanicznej
dc.affiliation.instituteKatedra Mleczarstwa i Inżynierii Procesowej
dc.affiliation.instituteKatedra Inżynierii Biosystemów
dc.affiliation.instituteKatedra Fizyki i Biofizyki
dc.affiliation.instituteKatedra Technologii Żywności Pochodzenia Roślinnego
dc.contributor.authorPrzybył, Krzysztof
dc.contributor.authorSamborska, Katarzyna
dc.contributor.authorJedlińska, Aleksandra
dc.contributor.authorKoszela, Krzysztof
dc.contributor.authorBaranowska, Hanna Maria
dc.contributor.authorMasewicz, Łukasz
dc.contributor.authorKowalczewski, Przemysław
dc.date.access2025-09-11
dc.date.accessioned2025-09-11T06:05:45Z
dc.date.available2025-09-11T06:05:45Z
dc.date.copyright2025-08-22
dc.date.issued2025
dc.description.abstract<jats:title>Abstract</jats:title> <jats:p>It can be observed that dynamic developments in artificial intelligence contributing to the evolution of existing techniques used in food research. Currently, innovative methods are being sought to support unit processes such as food drying, while at the same time monitoring quality and extending their shelf life. The development of innovative technology using convolutional neural networks (CNNs) to assess the quality of fruit powders seems highly desirable. This will translate into obtaining homogeneous batches of powders based on the specific morphological structure of the obtained microparticles. The research aims to apply convolutional networks to assess the quality, consistency, and homogeneity of blackcurrant powders supported by comparative physical methods of low-field nuclear magnetic resonance (LF-NMR) and texture analysis. The results show that maltodextrin, inulin, whey milk proteins, microcrystalline cellulose, and gum arabic are effective carriers when identifying morphological structure using CNNs. The use of CNNs, texture analysis, and the effect of LF-NMR relaxation time together with statistical elaboration shows that maltodextrin as well as milk whey proteins in combination with inulin achieve the most favorable results. The best results were obtained for a sample containing 50% maltodextrin and 50% maltodextrin (MD50-MD70). The CNN model for this combination had the lowest mean squared error in the test set at 2.5741 × 10<jats:sup>−4</jats:sup>, confirming its high performance in the classification of blackcurrant powder microstructures.</jats:p>
dc.description.accesstimeat_publication
dc.description.bibliographyil., bibliogr.
dc.description.financeother
dc.description.financecost4757,03
dc.description.if3,9
dc.description.number1
dc.description.points100
dc.description.versionfinal_published
dc.description.volume64
dc.identifier.doi10.1515/rams-2025-0132
dc.identifier.eissn1605-8127
dc.identifier.issn1606-5131
dc.identifier.urihttps://sciencerep.up.poznan.pl/handle/item/4724
dc.identifier.weblinkhttps://www.degruyterbrill.com/document/doi/10.1515/rams-2025-0132/html
dc.languageen
dc.relation.ispartofReviews on Advanced Materials Science
dc.relation.pagesart. 20250132
dc.rightsCC-BY
dc.sciencecloudsend
dc.share.typeOPEN_JOURNAL
dc.subject.enconvolutional neural networks
dc.subject.enlow-field nuclear magnetic resonance
dc.subject.entexture analysis
dc.subject.enscanning electron microscopy
dc.subject.enfruit powders
dc.subject.enblackcurrant
dc.titleThe application of convolutional neural networks, LF-NMR, and texture for microparticle analysis in assessing the quality of fruit powders: Case study – blackcurrant powders
dc.typeJournalArticle
dspace.entity.typePublication
oaire.citation.issue1
oaire.citation.volume64
project.funder.namePREIDUB