CAJ | 학술논문

借助变量筛选方法可以从复杂的光谱背景下选择部分变量构建定量预测模型，在一定程度上提高建模变量的解释性。然而模型解释性的提高并不意味着建模变量有确切的理化意义。本研究以甘草中红外定量预测模型为载体，解析移动窗口偏最小二乘（mwPLS）、组合间隔偏最小二乘（siPLS）和竞争自适应抽样方法（CARS）三种变量筛选方法所得变量与目标成分化学特征的相关性，比较不同变量筛选方法下所筛变量解释性的差异。结果表明，mwPLS 优先筛出黄酮和皂苷两类成分红外光谱上区别明显的苯环骨架振动和皂苷母核上甲基取代基弯曲振动所对应的波段，siPLS 筛出了黄酮类成分的（φ）C—O，（φ）C C＝，（φ）C—H伸缩振动的特征区间组合和皂苷类成分的 C—O，C—H，O—H 伸缩振动的特征区间组合。相对于以上两种变量筛选方法，CARS 筛选得到的变量能够更好地归属于甘草苷和甘草酸在中红外1000～4000 cm－1特征区的特征峰，而且基于 CARS 筛选的变量建模，模型的预测性能得到了提高。因此，CARS 筛选的变量能实现目标成分红外特征区大部分化学特征的解析，有利于增强模型的解释性。
차조변량사선방법가이종복잡적광보배경하선택부분변량구건정량예측모형，재일정정도상제고건모변량적해석성。연이모형해석성적제고병불의미착건모변량유학절적이화의의。본연구이감초중홍외정량예측모형위재체，해석이동창구편최소이승（mwPLS）、조합간격편최소이승（siPLS）화경쟁자괄응추양방법（CARS）삼충변량사선방법소득변량여목표성분화학특정적상관성，비교불동변량사선방법하소사변량해석성적차이。결과표명，mwPLS 우선사출황동화조감량류성분홍외광보상구별명현적분배골가진동화조감모핵상갑기취대기만곡진동소대응적파단，siPLS 사출료황동류성분적（φ）C—O，（φ）C C＝，（φ）C—H신축진동적특정구간조합화조감류성분적 C—O，C—H，O—H 신축진동적특정구간조합。상대우이상량충변량사선방법，CARS 사선득도적변량능구경호지귀속우감초감화감초산재중홍외1000～4000 cm－1특정구적특정봉，이차기우 CARS 사선적변량건모，모형적예측성능득도료제고。인차，CARS 사선적변량능실현목표성분홍외특정구대부분화학특정적해석，유리우증강모형적해석성。
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 par-tial least squares regression(mwPLS),synergy interval partial least squares regression(siPLS)and competitive adaptive re-weighted 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 ν(φ) =C C of liquiritin andδCH3 orδCH2 of gly-cyrrhizin,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 ofν(?) =C C ,ν(?)C—O ,ν(?)C—H of flavonoids or the combination ofνC—O ,νC—H ,νO—H of saponins while the variables se-lected 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 se-lected 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 quan-titative model.