Identification of Wine According to Grape Variety Using Near-Infrared Spectroscopy Based on Radial Basis Function Neural Networks and Least-Squares Support Vector Machines
- 320 Downloads
This paper describes how near-infrared (NIR) spectroscopy combined with radial basis function neural networks (RBFNN) and least-squares support vector machines (LS-SVMs) based on principal component analysis (PCA) can be used to classify wines from grape varieties. The effects of different preprocessing methods (standard normal variate (SNV) and multiplicative scattering correction (MSC)) on classification results were also compared. The results show that the use of NIR preprocessing spectral data with optimum RBFNN parameters produced a very high level of correct classification rate, 90.16–98.36%. For RBF LS-SVM, identification rates were from 91.80 to 98.36%. The results demonstrate that, combined with chemometrics with appropriate spectral data pretreatment, NIR spectroscopy has potential to rapidly and nondestructively differentiate wine according to grape variety. The results of this study are helpful to develop a more rapid and nondestructive detection method of wine.
KeywordsNear-infrared spectroscopy Wine Discrimination Radial basis function neural networks Least-squares support vector machines
Compliance with Ethical Standards
This study was funded by the National “Twelfth Five-Year” Plan for Science and Technology Support (2016YFD0400504).
Conflict of Interest
Jing Yu declares that she has no conflict of interest. Weidong Huang declares that he has no conflict of interest. Jicheng Zhan declares that he has no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed consent was obtained from all individual participants included in the study.
- Belousov AI, Verzakov SA, von Frese J (2002) A flexible classification approach with optimal generalization performance: support vector machines. Chemom Intell Lab Syst 64:15–25Google Scholar
- de Villiers A, Alberts F, Lynen F et al (2003) Evaluation of liquid chromatography and capillary electrophoresis for the elucidation of the artificial colorants brilliant blue and azorubine in red wines. Chromatographia 57:393–397Google Scholar
- Gierlinger N, Schwanninger M, Wammer R (2004) Characteristics and classification of Fourier-transform near infrared spectra of the heartwood of different larch species (Larix sp.). J Near Infrared Spectrosc 12:113–119Google Scholar
- Martens H, Naes T (1989) Multivariate calibration, 2nd edn. Wiley., ChichesterGoogle Scholar
- Mouazen AM, Karoui R, De Baerdemaeker J, Ramon H (2006) Classification of soils into different moisture content levels based on VIS-NIR spectra, Written for presentation at the 2006 ASABE Annual International Meeting Sponsored by ASABE. Oregon Convention Center, Portland, OregonGoogle Scholar
- Schölkopf B, Burges C, Smola A (1999) Three remarks on the support vector method of function estimation in advanced in kernel methods: support vector learning. the MIT Press, CambridgeGoogle Scholar
- Yan Y (2005) Foundation of NIR spectral analysis and its application. China Light Industry Press, BeijingGoogle Scholar