Prediction of fatty acid content in sheep milk by Mid-Infrared spectrometry with a selection of wavelengths by Genetic Algorithms. (January 2016)

• Record Type: Journal Article
• Authors: Caredda, Marco; Addis, Margherita; Ibba, Ignazio; Leardi, Riccardo; Scintu, Maria Francesca; Piredda, Giovanni; Sanna, Gavino
• Is Part Of: Lebensmittel-Wissenschaft + Technologie =. Volume 65(2016)
• Page Start: 503
• Page End: 510
• Publication Date: 2016-01
• Subjects: Sheep milk -- Fatty acids -- Mid-Infrared spectroscopy -- Genetic Algorithms -- Partial Least Square regression; PDO Protected Designation of Origin -- FT-MIR Fourier-Transform Mid-InfraRed spectroscopy -- FA fatty acids -- PLS Partial Least Squares -- GA Genetic Algorithms -- FAME Fatty Acid Methyl Esters -- CLA Conjugated Linoleic Acid -- MUFA monounsaturated fatty acids -- SFA saturated fatty acids -- UFA unsaturated fatty acids -- PUFA polyunsaturated fatty acids -- RMSECV Root Mean Square Error in Cross-Validation -- RMSEP Root Mean Square Error in Prediction; Food industry and trade -- Periodicals; Food -- Composition -- Periodicals; Microbiology -- Periodicals; Nutrition -- Periodicals; 664.005
• DOI: 10.1016/j.lwt.2015.08.048
• Languages: English
• ISSNs: 0023-6438

Abstract

Abstract: Sheep breeding is one of the most widespread activities in Sardinia (Italy), and milk produced here is of crucial economic importance for the region. In order to make the milk payment system used in Sardinia more rewarding to the quality of milk, we developed Partial Least Square regression models to predict the concentration of the major fatty acids (measured with a GC-FID reference method) from the Mid-Infrared spectra of hundreds of Sardinian sheep milk samples collected in the period 2011–2013. Genetic Algorithms were used in order to select the most informative spectral subsets and therefore reduce the complexity of the model and in many cases also reduce the prediction error. Models obtained had a good predictive ability, with errors in the range of tenths of a gram of fatty acid on Kg of milk, and an acceptable precision for an immediate introduction on sheep milk payment in Sardinia. Highlights: Predictive models for fatty acids in sheep milk by FT-MIR spectroscopy were built. PLS regressions were computed between milk spectra and fatty acid reference values. Genetic Algorithms were used to select the informative spectral subsets. Validated models show low prediction errors in comparison to reference values. Validated models may be useful as evaluation tools for sheep milk payment purposes.