Application of Least Squares-Support Vector Machine for Measurement of Soluble Solids Content of Rice Vinegars Using Vis/NIR Spectroscopy
Authors:
- Fei LiuFei Liu
- Yong HeYHYong He
- Li WangLWLi Wang
- 1 December 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1044-1047
Abstract
Visible and near infrared (Vis/NIR) spectroscopy was investigated to predict soluble solids content (SSC) of rice vinegars based on least squares-support vector machine (LS-SVM). Five varieties of rice vinegars and 300 samples were prepared. After some preprocessing, PLS was implemented for calibration as well as the extraction of principal components (PCs). Wavelet transform (WT) was use to compress the variables. The selected PCs and compressed variables were applied as the inputs to develop PC-LS-SVM and WT-LS-SVM models. The correlation coefficient (r), root mean square error of prediction (RMSEP) and bias for prediction were 0.958, 1216, and -0.310 for PLS, 0.997, 0.357 and 0.121 for PC-LS-SVM, whereas 0.999, 0.199 and 0.030 for WT-LS-SVM, respectively. A high and excellent precision was achieved by LS-SVM models. The results indicated that Vis/NIR spectroscopy could be successfully applied as a fast and high precision method for the measurement of SSC of rice vinegars.Keywords
This publication has 7 references indexed in Scilit:
- Identification and quantification of the main organic components of vinegars by high resolution 1H NMR spectroscopyAnalytica Chimica Acta, 2007
- Characterization of Chinese vinegars by electronic noseSensors and Actuators B: Chemical, 2006
- Prediction of organic acids and other quality parameters of wine vinegar by near-infrared spectroscopy. A feasibility studyFood Chemistry, 2006
- Application of wavelet transforms to improve prediction precision of near infrared spectraJournal of Food Engineering, 2005
- Application of LS-SVM to non-linear phenomena in NIR spectroscopy: development of a robust and portable sensor for acidity prediction in grapesChemometrics and Intelligent Laboratory Systems, 2004
- Application of wavelet transform in infrared spectrometry: spectral compression and library searchChemometrics and Intelligent Laboratory Systems, 1998
- Characterisation of Italian vinegar by pyrolysis–mass spectrometry and a sensor device (‘electronic nose’)Food Chemistry, 1998