Using data mining techniques to predict industrial wine problem fermentations

Simple item page
dc.contributor.authorUrtubia, Alejandra
dc.contributor.authorPerez Correa, J. Ricardo
dc.contributor.authorSoto, Alvaro
dc.contributor.authorPszczolkowski, Philippo
dc.date.accessioned2024-01-10T12:10:37Z
dc.date.available2024-01-10T12:10:37Z
dc.date.issued2007
dc.description.abstractWinemakers currently lack the tools to identify early signs of undesirable fermentation behavior and so are unable to take possible mitigating actions. Data collected from tracking 24 industrial fermentations of Cabernet sauvignon were used in this study to explore how useful is data mining to detect anomalous behaviors in advance. A database held periodic measurements of 29 components that included sugar, alcohols, organic acids and amino acids. Owing to the scale of the problem, we used a two-stage classification procedure. First PCA was used to reduce system dimensionality while preserving metabolite interaction information. Cluster analysis (K-Means) was then performed on the lower-dimensioned system to group fermentations into clusters of similar behavior. Numerous classifications were explored depending on the data used. Initially data from just the first three days were assessed, and then the entire data set was used. Information from the first three days' fermentation behavior provides important clues about the final classification. We also found a strong association between problematic fermentations and specific patterns found by the data mining tools. In short, data from the first three days contain sufficient information to establish the likelihood of a fermentation finishing normally. Results from this study are most encouraging. Data from many more fermentations and of different varieties needs to be collected, however, to develop a reliable and more broadly applicable diagnostic tool. (c) 2006 Elsevier Ltd. All rights reserved.
dc.fechaingreso.objetodigital25-03-2024
dc.format.extent6 páginas
dc.fuente.origenWOS
dc.identifier.doi10.1016/j.foodcont.2006.09.010
dc.identifier.eissn1873-7129
dc.identifier.issn0956-7135
dc.identifier.urihttps://doi.org/10.1016/j.foodcont.2006.09.010
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/76592
dc.identifier.wosidWOS:000248503200007
dc.information.autorucAgronomía e Ing. Forestal;Pszczolkowski PH;S/I;99169
dc.information.autorucIngeniería;Pérez-Correa J;S/I;100130
dc.information.autorucIngeniería;Soto A;S/I;73678
dc.issue.numero12
dc.language.isoen
dc.nota.accesocontenido parcial
dc.pagina.final1517
dc.pagina.inicio1512
dc.publisherELSEVIER SCI LTD
dc.revistaFOOD CONTROL
dc.rightsacceso restringido
dc.subjectPCA
dc.subjectclustering
dc.subjectK-Means
dc.subjectsluggish fermentations
dc.subjectstuck fermentations
dc.subjectHISTORICAL DATA
dc.subject.ods13 Climate Action
dc.subject.odspa13 Acción por el clima
dc.titleUsing data mining techniques to predict industrial wine problem fermentations
dc.typeartículo
dc.volumen18
sipa.codpersvinculados99169
sipa.codpersvinculados100130
sipa.codpersvinculados73678
sipa.indexWOS
sipa.indexScopus
sipa.trazabilidadCarga SIPA;09-01-2024
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2024-03-25. Using data mining techniques to predict industrial wine problem fermentations.pdf
Size:
3.1 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas