Show simple item record

dc.contributor.authorFrizzarin, M.
dc.contributor.authorGormley, I.C.
dc.contributor.authorBerry, D.P.
dc.contributor.authorMurphy, T.B.
dc.contributor.authorCasa, A.
dc.contributor.authorLynch, A.
dc.contributor.authorMcParland, S.
dc.identifier.citationM. Frizzarin, I.C. Gormley, D.P. Berry, T.B. Murphy, A. Casa, A. Lynch, S. McParland, Predicting cow milk quality traits from routinely available milk spectra using statistical machine learning methods, Journal of Dairy Science, Volume 104, Issue 7, 2021, Pages 7438-7447, ISSN 0022-0302,
dc.description.abstractNumerous statistical machine learning methods suitable for application to highly correlated features, as those that exist for spectral data, could potentially improve prediction performance over the commonly used partial least squares approach. Milk samples from 622 individual cows with known detailed protein composition and technological trait data accompanied by mid-infrared spectra were available to assess the predictive ability of different regression and classification algorithms. The regression-based approaches were partial least squares regression (PLSR), ridge regression (RR), least absolute shrinkage and selection operator (LASSO), elastic net, principal component regression, projection pursuit regression, spike and slab regression, random forests, boosting decision trees, neural networks (NN), and a post-hoc approach of model averaging (MA). Several classification methods (i.e., partial least squares discriminant analysis (PLSDA), random forests, boosting decision trees, and support vector machines (SVM)) were also used after stratifying the traits of interest into categories. In the regression analyses, MA was the best prediction method for 6 of the 14 traits investigated [curd firmness at 60 min, αS1-casein (CN), αS2-CN, κ-CN, α-lactalbumin, and β-lactoglobulin B], whereas NN and RR were the best algorithms for 3 traits each (rennet coagulation time, curd-firming time, and heat stability, and curd firmness at 30 min, β-CN, and β-lactoglobulin A, respectively), PLSR was best for pH, and LASSO was best for CN micelle size. When traits were divided into 2 classes, SVM had the greatest accuracy for the majority of the traits investigated. Although the well-established PLSR-based method performed competitively, the application of statistical machine learning methods for regression analyses reduced the root mean square error compared with PLSR from between 0.18% (κ-CN) to 3.67% (heat stability). The use of modern statistical machine learning methods for trait prediction from mid-infrared spectroscopy may improve the prediction accuracy for some traits.en_US
dc.relation.ispartofseriesJournal of Dairy Science;Vol 104
dc.rights© 2021 American Dairy Science Association®.
dc.rightsAttribution-NonCommercial-ShareAlike 4.0 International*
dc.subjectFourier-transform mid-infrared spectroscopyen_US
dc.subjectstatistical machine learningen_US
dc.subjectmilk qualityen_US
dc.titlePredicting cow milk quality traits from routinely available milk spectra using statistical machine learning methodsen_US
dc.contributor.sponsorScience Foundation Irelanden_US
dc.contributor.sponsorGovernment of Irelanden_US
dc.contributor.sponsorGrantNumber16/RC/3835 (VistaMilk)en_US
dc.source.journaltitleJournal of Dairy Science

Files in this item

Predicting-cow-milk-quality-tr ...
main article

This item appears in the following Collection(s)

Show simple item record

© 2021 American Dairy Science Association®.
Except where otherwise noted, this item's license is described as © 2021 American Dairy Science Association®.