TY - JOUR
T1 - Prediction of enological parameters and discrimination of rice wine age using least-squares support vector machines and near infrared spectroscopy
AU - Yu, Haiyan
AU - Lin, Hongjian
AU - Xu, Huirong
AU - Ying, Yibin
AU - Li, Bobin
AU - Pan, Xingxiang
PY - 2008/1/23
Y1 - 2008/1/23
N2 - The use of least-squares support vector machines (LS-SVM) combined with near-infrared (NIR) spectra for prediction of enological parameters and discrimination of rice wine age is proposed. The scores of the first ten principal components (PCs) derived from PC analysis (PCA) and radial basis function (RBF) were used as input feature subset and kernel function of LS-SVM models, respectively. The optimal parameters, the relative weight of the regression error γ and the kernel parameter σ2, were found from grid search and leave-one-out cross-validation. As compared to partial least-squares (PLS) regression, the performance of LS-SVM was slightly better, with higher determination coefficients for validation (R val2) and lower root-mean-square error of validation (RMSEP) for alcohol content, titratable acidity, and pH, respectively. When used to discriminate rice wine age, LS-SVM gave better results than discriminant analysis (DA). On the basis of the results, it was concluded that LS-SVM together with NIR spectroscopy was a reliable and accurate method for rice wine quality estimation.
AB - The use of least-squares support vector machines (LS-SVM) combined with near-infrared (NIR) spectra for prediction of enological parameters and discrimination of rice wine age is proposed. The scores of the first ten principal components (PCs) derived from PC analysis (PCA) and radial basis function (RBF) were used as input feature subset and kernel function of LS-SVM models, respectively. The optimal parameters, the relative weight of the regression error γ and the kernel parameter σ2, were found from grid search and leave-one-out cross-validation. As compared to partial least-squares (PLS) regression, the performance of LS-SVM was slightly better, with higher determination coefficients for validation (R val2) and lower root-mean-square error of validation (RMSEP) for alcohol content, titratable acidity, and pH, respectively. When used to discriminate rice wine age, LS-SVM gave better results than discriminant analysis (DA). On the basis of the results, it was concluded that LS-SVM together with NIR spectroscopy was a reliable and accurate method for rice wine quality estimation.
KW - Enological parameter
KW - Least-squares support vector machines
KW - Near-infrared spectroscopy
KW - Rice wine age
UR - http://www.scopus.com/inward/record.url?scp=38949118597&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=38949118597&partnerID=8YFLogxK
U2 - 10.1021/jf0725575
DO - 10.1021/jf0725575
M3 - Article
C2 - 18167072
AN - SCOPUS:38949118597
SN - 0021-8561
VL - 56
SP - 307
EP - 313
JO - Journal of agricultural and food chemistry
JF - Journal of agricultural and food chemistry
IS - 2
ER -