Simple item page
 

Machine Learning in Sensory Analysis of Mead—A Case Study: Ensembles of Classifiers

cris.virtual.author-orcid0000-0002-2535-8370
cris.virtual.author-orcid0000-0001-5324-5982
cris.virtual.author-orcid0000-0003-4234-7881
cris.virtual.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtualsource.author-orcid898dc715-0fc1-42af-a4d7-0bc909752fee
cris.virtualsource.author-orcidad6302d1-4126-47ee-bfde-d3636e0b6d0a
cris.virtualsource.author-orcid4ee23ba3-eef2-455b-bf2c-1c2dcfc4df21
cris.virtualsource.author-orcid#PLACEHOLDER_PARENT_METADATA_VALUE#
dc.abstract.enThe aim was to explore using machine learning (including cluster mapping and k-means methods) to classify types of mead based on sensory analysis and aromatic compounds. Machine learning is a modern tool that helps with detailed analysis, especially because verifying aromatic compounds is challenging. In the first stage, a cluster map analysis was conducted, allowing for the exploratory identification of the most characteristic features of mead. Based on this, k-means clustering was performed to evaluate how well the identified sensory features align with logically consistent groups of observations. In the next stage, experiments were carried out to classify the type of mead using algorithms such as Random Forest (RF), adaptive boosting (AdaBoost), Bootstrap aggregation (Bagging), K-Nearest Neighbors (KNN), and Decision Tree (DT). The analysis revealed that the RF and KNN algorithms were the most effective in classifying mead based on sensory characteristics, achieving the highest accuracy. In contrast, the AdaBoost algorithm consistently produced the lowest accuracy results. However, the Decision Tree algorithm achieved the highest accuracy value (0.909), demonstrating its potential for precise classification based on aroma characteristics. The error matrix analysis also indicated that acacia mead was easier for the algorithms to identify than tilia or buckwheat mead. The results show the potential of combining an exploratory approach (cluster map with the k-means method) with machine learning. It is also important to focus on selecting and optimizing classification models used in practice because, as the results so far indicate, choosing the right algorithm greatly affects the success of mead identification.
dc.affiliationWydział Nauk o Żywności i Żywieniu
dc.affiliation.instituteKatedra Mleczarstwa i Inżynierii Procesowej
dc.affiliation.instituteKatedra Technologii Żywności Pochodzenia Roślinnego
dc.contributor.authorPrzybył, Krzysztof
dc.contributor.authorCicha-Wojciechowicz Daria
dc.contributor.authorDrabińska, Natalia
dc.contributor.authorMajcher, Małgorzata Anna
dc.date.access2025-08-04
dc.date.accessioned2025-08-04T10:07:13Z
dc.date.available2025-08-04T10:07:13Z
dc.date.copyright2025-07-30
dc.date.issued2025
dc.description.abstract<jats:p>The aim was to explore using machine learning (including cluster mapping and k-means methods) to classify types of mead based on sensory analysis and aromatic compounds. Machine learning is a modern tool that helps with detailed analysis, especially because verifying aromatic compounds is challenging. In the first stage, a cluster map analysis was conducted, allowing for the exploratory identification of the most characteristic features of mead. Based on this, k-means clustering was performed to evaluate how well the identified sensory features align with logically consistent groups of observations. In the next stage, experiments were carried out to classify the type of mead using algorithms such as Random Forest (RF), adaptive boosting (AdaBoost), Bootstrap aggregation (Bagging), K-Nearest Neighbors (KNN), and Decision Tree (DT). The analysis revealed that the RF and KNN algorithms were the most effective in classifying mead based on sensory characteristics, achieving the highest accuracy. In contrast, the AdaBoost algorithm consistently produced the lowest accuracy results. However, the Decision Tree algorithm achieved the highest accuracy value (0.909), demonstrating its potential for precise classification based on aroma characteristics. The error matrix analysis also indicated that acacia mead was easier for the algorithms to identify than tilia or buckwheat mead. The results show the potential of combining an exploratory approach (cluster map with the k-means method) with machine learning. It is also important to focus on selecting and optimizing classification models used in practice because, as the results so far indicate, choosing the right algorithm greatly affects the success of mead identification.</jats:p>
dc.description.accesstimeat_publication
dc.description.bibliographyil., bibliogr.
dc.description.financeother
dc.description.financecost6202,71
dc.description.if4,6
dc.description.number15
dc.description.points140
dc.description.versionfinal_published
dc.description.volume30
dc.identifier.doi10.3390/molecules30153199
dc.identifier.issn1420-3049
dc.identifier.urihttps://sciencerep.up.poznan.pl/handle/item/4063
dc.identifier.weblinkhttps://www.mdpi.com/1420-3049/30/15/3199
dc.languageen
dc.pbn.affiliationfood and nutrition technology
dc.relation.ispartofMolecules
dc.relation.pagesart. 3199
dc.rightsCC-BY
dc.sciencecloudsend
dc.share.typeOPEN_JOURNAL
dc.subject.enmachine learning
dc.subject.enensembles of classifiers
dc.subject.enmead aroma
dc.subject.ensensory analysis
dc.subject.enodor-active compounds
dc.titleMachine Learning in Sensory Analysis of Mead—A Case Study: Ensembles of Classifiers
dc.title.volumeSpecial Issue Analytical Technologies and Intelligent Applications in Future Food
dc.typeJournalArticle
dspace.entity.typePublication
oaire.citation.issue15
oaire.citation.volume30
project.funder.namePREIDUB