Feature Selection and Interpretation in Infrared Quantitative Models of   Liquiritin and Glycyrrhizin in Radix Glycyrrhizae

doi:10.3964/3.issn.1000-0593(2015)09-2530-06

CORC > 北京大学 > 化学与分子工程学院

	Feature Selection and Interpretation in Infrared Quantitative Models of Liquiritin and Glycyrrhizin in Radix Glycyrrhizae
	Zhan Xue-yan ; Lin Zhao-zhou ; Sun Yang ; Yuan Rui-juan ; Yang Zhan-lan ; Duan Tian-xuan
刊名	SPECTROSCOPY AND SPECTRAL ANALYSIS
	2015
关键词	Infrared quantitative models Variable selection Chemical characteristics Variable interpretation Radix Glycyrrhizae MULTIVARIATE CALIBRATION VARIABLES SPECTROSCOPY SPECTRA
DOI	10.3964/3.issn.1000-0593(2015)09-2530-06
英文摘要	Feature selection can improve the interpretation of the modeling variables to a certain extent by selecting variables from the complex spectra backgrounds. However, the improvement of models interpretation does not mean that the modeling variables have the exact physical or chemical significance. In this paper, We explore the relation between the chemical characteristics of target components and the spectrum variables selected with 3 kinds of variables selection methods which are moving window partial least squares regression (mwPLS), synergy interval partial least squares regression (siPLS) and competitive adaptive reweighted sampling(CARS), and compare the interpretation difference of the variables selected with the above variables selection methods. The results show that the variables selected with mwPLS accord with nu(phi)C=C of liquiritin and delta(CH3) or delta(CH2) of glycyrrhizin, which are the obvious spectra differences between the flavonoids and saponins in Radix Glycyrrhizae, and the variables selected with siPLS are the characteristic intervals combinations of the flavonoids or saponins in Radix Glycyrrhizae, which is the combination of nu(phi) nu(o) o nu(o)(C-H) of flavonoids or the combination of nu c-o nu c H, O-H of saponins while the variables selected with CARS can better accord with most of the characteristic peaks from 1 000 to 4 000 cm(-1) of liquiritin or glycyrrhizin in Radix Glycyrrhizae, and the predict performance of the infrared quantitative model established on the spectroscopic variables selected with CARS can be improved. Therefore, most of the variables selected with CARS can be interpreted by the characteristic peaks in the infrared characteristic region of the target components, which is beneficial to improve the interpretation of the quantitative model.; SCI(E); 中文核心期刊要目总览(PKU); 中国科技核心期刊(ISTIC); ARTICLE; 9; 2530-2535; 35
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/459257]
专题	化学与分子工程学院
推荐引用方式 GB/T 7714	Zhan Xue-yan,Lin Zhao-zhou,Sun Yang,et al. Feature Selection and Interpretation in Infrared Quantitative Models of Liquiritin and Glycyrrhizin in Radix Glycyrrhizae[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS,2015.
APA	Zhan Xue-yan,Lin Zhao-zhou,Sun Yang,Yuan Rui-juan,Yang Zhan-lan,&Duan Tian-xuan.(2015).Feature Selection and Interpretation in Infrared Quantitative Models of Liquiritin and Glycyrrhizin in Radix Glycyrrhizae.SPECTROSCOPY AND SPECTRAL ANALYSIS.
MLA	Zhan Xue-yan,et al."Feature Selection and Interpretation in Infrared Quantitative Models of Liquiritin and Glycyrrhizin in Radix Glycyrrhizae".SPECTROSCOPY AND SPECTRAL ANALYSIS (2015).