文献类型：期刊文献

英文题名：A Modified Moving-Window Partial Least-Squares Method by Coupling with Sampling Error Profile Analysis for Variable Selection in Near-Infrared Spectral Analysis

作者：Yang, Wuye[1];Wang, Wenming[1];Zhang, Ruoqiu[1];Zhang, Feiyu[1];Xiong, Yinran[1];Wu, Ting[1];Chen, Wanchao[2];Du, Yiping[1]

机构：[1]East China Univ Sci & Technol, Sch Chem & Mol Engn, Shanghai Key Lab Funct Mat Chem, Shanghai 200237, Peoples R China;[2]Shanghai Acad Agr Sci, Natl Engn Res Ctr Edible Fungi, Inst Edible Fungi, Minist Agr,Key Lab Edible Fungi Resources & Utili, Shanghai 201403, Peoples R China

年份：2020

卷号：36

期号：3

起止页码：303

外文期刊名：ANALYTICAL SCIENCES

收录：;EI(收录号：20201308357644);WOS:【SCI-EXPANDED(收录号:WOS:000518800400004)】；

基金：This work was supported by Technology Center, Shanghai Tobacco Group Corporation, Key Laboratory of Cigarette Smoke Research of CNTC (K2018-1-056P).L

语种：英文

外文关键词：Moving-window partial least-squares; sampling error profile analysis; variable selection; near infrared spectroscopy

摘要：In this study, a new variable selection method, named moving-window partial least-squares coupled with sampling error profile analysis (SEPA-MWPLS), is developed. With a moving window, moving-window partial least-squares (MWPLS) is used to find window intervals which show low residual sums of squares (RSS) of a calibration set. Sampling error profile analysis (SEPA) is a useful method based on Monte-Carlo Sampling and profile analysis for cross validation (CV). By combining MWPLS with SEPA, we can obtain more stable and reliable results. Besides, we simplify the plot of the RSS line so that it is easier to determine the informative intervals. In addition, a backward elimination strategy is used to optimize the combination of subintervals. The performance of SEPA-MWPLS was tested with two near-infrared (NIR) spectra datasets and was compared with PLS, MWPLS and Monte Carlo uninformative variable elimination (MC-UVE). The results show that SEPA-MWPLS can improve model performances significantly compared with MWPLS in the number of variables, root-mean-squared errors of CV, calibration and prediction (RMSECVs, RMSECs and RMSEPs). Meanwhile it also exhibits better performances than MC-UVE.