LS-SVM: a new chemometric tool for multivariate regression. Comparison of LS-SVM and pls regression for determination of common adulterants in powdered milk by nir spectroscopy

Química Nova

Maretto, Danilo A.¹  Mello, Cesar¹  Poppi, Ronei J.¹  Borin, Alessandra¹  Ferrão, Marco F.¹ 

关键词: support vector machines;    multivariate regression;    powdered milk.;   

DOI  :  10.1590/S0100-40422007000400018

学科分类：化学（综合）

来源: Sociedade Brasileira de Quimica

【 摘 要 】

Least-squares support vector machines (LS-SVM) were used as an alternative multivariate calibration method for the simultaneous quantification of some common adulterants found in powdered milk samples, using near-infrared spectroscopy. Excellent models were built using LS-SVM for determining R2, RMSECV and RMSEP values. LS-SVMs show superior performance for quantifying starch, whey and sucrose in powdered milk samples in relation to PLSR. This study shows that it is possible to determine precisely the amount of one and two common adulterants simultaneously in powdered milk samples using LS-SVM and NIR spectra.

【 授权许可】

Unknown