Title
Determination of Tartaric Acid of Fruit Vinegars Using Near Infrared Spectroscopy and Chemometrics
Abstract
Near infrared (NIR) spectroscopy combined with chemometrics was investigated for the determination of tartaric acid of fruit vinegars. A total of 180 samples were prepared, and 135 samples were selected for the calibration set, whereas the remaining 45 samples for the validation set. Partial least squares (PLS) analysis was the calibration method as well as extraction method for latent variables (LVs) which were employed as the inputs of least squares-support vector machine (LS-SVM) model. Simultaneously, the effective wavelengths (EWs) were selected by regression coefficients. The EW-LSSVM model was better than both PLS and LV-LS-SVM model. The correlation coefficient (r), root mean square error of prediction (RMSEP) and bias for validation set were 0.998, 0.210 and 0.003 by EW-LS-SVM, respectively. The results indicated that NIR spectroscopy combined with LS-SVM method could be utilized as a high precision and fast way for the determination of tartaric acid of fruit vinegars.
Year
DOI
Venue
2008
10.1109/ICNC.2008.591
ICNC
Keywords
Field
DocType
tartaric acid,validation set,calibration set,extraction method,calibration method,ew-lssvm model,lv-ls-svm model,fruit vinegar,infrared spectroscopy,ls-svm method,nir spectroscopy,least squares support vector machine,support vector machines,near infrared,latent variable,near infrared spectroscopy,latent variables,mathematical model,calibration,kernel,infrared spectra,predictive models,chemometrics,regression analysis,root mean square error,spectroscopy,correlation
Tartaric acid,Computer science,Partial least squares regression,Artificial intelligence,Chemometrics,Linear regression,Correlation coefficient,Analytical chemistry,Near-infrared spectroscopy,Infrared spectroscopy,Spectroscopy,Statistics,Machine learning
Conference
Citations 
PageRank 
References 
0
0.34
2
Authors
3
Name
Order
Citations
PageRank
Fei Liu1155.27
Li Wang241.68
Yong He348765.25