作者: Caili Fu , Ying Li , Wu Wang , Bin Qiu , Zhenyu Lin
DOI: 10.1039/C7AY00936D
关键词: Biological system 、 Sampling (statistics) 、 Fourier transform 、 Variable (computer science) 、 Tetrastigma hemsleyanum 、 Relevance vector machine 、 Near-infrared spectroscopy 、 Mathematics 、 Wavelength 、 Analytical chemistry 、 Spectroscopy
摘要: Few studies have been carried out on the discrimination of precious Tetrastigma hemsleyanum, also known as Sanyeqing in China. Fourier transform near-infrared (FT-NIR) spectroscopy coupled with chemometric class-modelling techniques to rapidly and effectively discriminate T. hemsleyanum was investigated this study. A relevance vector machine (RVM) used build a stable accurate model. Furthermore, competitive adaptive reweighted sampling (CARS) employed extract effective wavelength variables. The results indicated that accuracy RVM model satisfactory due good rate. Additionally, variable number CARS validly improved 26, RVM-CARS were effective. suggested CARS-RVM is suitable efficiently hemsleyanum.