期刊
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
卷 72, 期 4, 页码 845-850出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.saa.2008.12.002
关键词
FT-NIR spectroscopy; Supervised pattern recognition; Green tea; Geographical origin; Discrimination
类别
资金
- National Natural and Science Foundation of China [30800666]
- Natural Science Foundation for Colleges and Universities in Jiangsu Province [08KJB550003]
- Advanced Talents Science Foundation of Jiangsu University [08JDG007]
Rapid discrimination of roast green tea according to geographical origin is crucial to quality control. Fourier transform near-infrared (FT-NIR) spectroscopy and supervised pattern recognition was attempted to discriminate Chinese green tea according to geographical origins (i.e. Anhui Province, Henan Province, Jiangsu Province, and Zhejiang Province) in this work. Four supervised pattern recognitions methods were used to construct the discrimination models based on principal component analysis (PCA), respectively. The number of principal components factors (PCs) and model parameters were optimized by cross-validation in the constructing model. The performances of four discrimination models were compared. Experimental results showed that the performance of SVM model is the best among four models. The optimal SVM model was achieved when 4 PCs were used, discrimination rates being all 100% in the training and prediction set. The overall results demonstrated that FT-NIR spectroscopy with supervised pattern recognition could be successfully applied to discriminate green tea according to geographical origins. (C) 2008 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据