000151601 001__ 151601
000151601 005__ 20251017144609.0
000151601 0247_ $$2doi$$a10.1016/j.foodqual.2025.105494
000151601 0248_ $$2sideral$$a143239
000151601 037__ $$aART-2025-143239
000151601 041__ $$aeng
000151601 100__ $$aSáenz-Navajas, María-Pilar
000151601 245__ $$aBagging and boosting machine learning algorithms for modelling sensory perception from simple chemical variables: Wine mouthfeel as a case study
000151601 260__ $$c2025
000151601 5060_ $$aAccess copy available to the general public$$fUnrestricted
000151601 5203_ $$aAiming to predict sensory properties from chemical data, the application of bagging and boosting machine learning (ML) algorithms was comprehensively investigated and applied to modelling of red wine mouthfeel from simple chemical measurements. A panel of 15 Australian winemakers described the mouthfeel properties of a total of 30 commercial red wines from Australia and Spain using rate-all-that-apply sensory methodology. In parallel, linear sweep voltammetry signals and excitation-emission matrix (EEM) and absorbance data were acquired for the wines. Data were analysed following unsupervised statistical strategies including principal component analysis (PCA with varimax rotation) to simplify the interpretation of sensory variables, along with supervised regression models based on ML, namely random forest (RF) and extreme gradient boosting (XGBoost). PCA results showed that four independent and uncorrelated sensory dimensions mainly related to perceptions of ‘drying’, ‘full body’, ‘velvety’, and ‘gummy’ differentiated among the wines. The RF and XGBoost algorithms yielded superior validated regression models compared to classical PLS modelling. The ML algorithms exhibited strong predictive performance on test data, with an average value exceeding 80 % accuracy for any of the three sets of chemical variables employed. Although XGBoost provided slightly better models, the low computational effort required by RF is advantageous. Key variables included in the models are discussed along with the importance of controlling overfitting. Overall, absorbance, voltammetric or EEM signals coupled with RF or XGBoost algorithms are presented as cheap, easy-to-use, and rapid approaches to predicting sensory properties from chemical signals in complex matrices such as wine.
000151601 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PID2021-126031OB-C22
000151601 540__ $$9info:eu-repo/semantics/embargoedAccess$$aby-nc-nd$$uhttps://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
000151601 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000151601 700__ $$0(orcid)0000-0002-3698-6719$$aFerreira, Chelo$$uUniversidad de Zaragoza
000151601 700__ $$aBastian, Susan E.P.
000151601 700__ $$aJeffery, David W.
000151601 7102_ $$12005$$2595$$aUniversidad de Zaragoza$$bDpto. Matemática Aplicada$$cÁrea Matemática Aplicada
000151601 773__ $$g129 (2025), 105494 [13 pp.]$$pFood qual. prefer.$$tFood Quality and Preference$$x0950-3293
000151601 8564_ $$s1241834$$uhttps://zaguan.unizar.es/record/151601/files/texto_completo.pdf$$yPostprint$$zinfo:eu-repo/date/embargoEnd/2026-08-01
000151601 8564_ $$s645922$$uhttps://zaguan.unizar.es/record/151601/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint$$zinfo:eu-repo/date/embargoEnd/2026-08-01
000151601 909CO $$ooai:zaguan.unizar.es:151601$$particulos$$pdriver
000151601 951__ $$a2025-10-17-14:16:21
000151601 980__ $$aARTICLE