Abstract
Soluble solids content (SSC) and pH are two major characteristic used for assessing quality of red wine, and they are also two important quality indexes in the manufacture of red wine. For rapid detection of SSC and pH in red wine, visible and near infrared (Vis/NIR) transmittance spectroscopy technique combined with partial least squares (PLS) and least squares support vector machines (LS-SVM) were used in this study. First, the near infrared transmittance spectra of 175 red wine samples were obtained using Vis/NIR spectroradiometer, then, PLS was applied for reducing the dimensionality of the original spectra, latent variables (LVs) selected by PLS could be used to replace the complex spectral data. All samples were randomly separated into calibration set and validation set. The LVs (selected by PLS) of each sample in calibration set was used as the inputs to train the LS-SVM model, then the optimal model was used to predict the SSC and pH values of samples in validation set based on their LVs. Standard error prediction (SEP) and determination coefficient (<i>r</i><sup>2</sup>) were used as the evaluation standards, and the results indicated that the SEP and <i>r</i><sup>2</sup> for the prediction of SSC were 0.2313 and 0.9348; while 0.0071 and 0.9986 for pH. This prediction model was more accurate compared with the related research.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.