Chen Quansheng, Zhao Jiewen, Fang C H, Wang Dongmei
Department of Food Engineering, School of food and Biological Engineering, Jiangsu University, 212013 Zhenjiang, PR China.
Spectrochim Acta A Mol Biomol Spectrosc. 2007 Mar;66(3):568-74. doi: 10.1016/j.saa.2006.03.038. Epub 2006 Apr 18.
Near-infrared (NIR) spectroscopy has been successfully utilized for the rapid identification of green, black and Oolong teas. The spectral features of each category are reasonably differentiated in the NIR region, and the spectral differences provided enough qualitative spectral information for identification. Support vector machine as a pattern recognition was applied to attain the differentiation of the three tea categories in this study. The top five latent variables are extracted by principal component analysis as the input of SVM classifiers. The identification results of the three tea categories were achieved by the RBF SVM classifiers and the polynomial SVM classifiers in different parameters. The best identification accuracies were up to 90%, 100% and 93.33%, respectively, when training, while, 90%, 100% and 95% when test. It was obtained using the RBF SVM classifier with sigma=0.5. The overall results ensure that NIR spectroscopy combined with SVM discrimination method can be efficiently utilized for rapid and simple identification of the different tea categories.
近红外（NIR）光谱已成功用于绿茶、红茶和乌龙茶的快速鉴别。在近红外区域，各类茶叶的光谱特征有合理区分，光谱差异提供了足够的定性光谱信息用于鉴别。本研究应用支持向量机作为模式识别方法来实现这三种茶叶类别的区分。通过主成分分析提取前五个潜在变量作为支持向量机分类器的输入。不同参数下，径向基函数支持向量机（RBF SVM）分类器和多项式支持向量机分类器实现了三种茶叶类别的鉴别。训练时，最佳识别准确率分别高达90%、100%和93.33%，测试时分别为90%、100%和95%。这是使用σ=0.5的径向基函数支持向量机分类器得到的结果。总体结果表明，近红外光谱结合支持向量机判别方法可有效用于不同茶叶类别的快速、简易鉴别。
