A novel NIRS modelling method with OPLS-SPA and MIX-PLS for timber evaluation

作     者：Jinhao Chen Huilig Yu Dapeng Jiang Yizhuo Zhang Keqi Wang Jinhao Chen;Huilig Yu;Dapeng Jiang;Yizhuo Zhang;Keqi Wang

作者机构：College of Mechanical and Electrical EngineeringNortheast Forestry UniversityHarbin 150040People’s Republic of China College of Information and Computer EngineeringNortheast Forestry UniversityHarbin 150040People’s Republic of China 

出 版 物：《Journal of Forestry Research》 (林业研究（英文版）)

年 卷 期：2022年第33卷第1期

页      面：369-376页

核心收录：

学科分类：082902[工学-木材科学与技术] 08[工学] 0829[工学-林业工程] 

基　　金：supported financially by the China State Forestry Administration“948”projects(2015-4-52) Heilongjiang Natural Science Foundation(C2017005) 

主　　题：NIR prediction Orthogonal partial least squares(OPLS) Successive projections algorithm(SPA) Mix partial least squares(MIX-PLS)modulus of elasticity 

摘      要：The identification of timber properties is important for safe *** Infrared Spectroscopy(NIRS)technology is widely-used because of its simplicity,efficiency,and positive environmental ***,in its application,weak signals are extracted from complex,overlapping and changing *** study focused on the stability of NIR *** Orthogonal Partial Least Squares(OPLS)and Successive Projections Algorithm(SPA)eliminates noise and extracts effective spectra,and an ensemble learning method MIX-PLS,is applied to establish the *** elastic modulus of timber is taken as an example,and 201 wood samples of three species,Xylosmacongesta(Lour.)Merr.,Acer pictum ***,and Betula pendula,samples were divided into three groups to investigate modelling *** results show that OPLS can preprocess the near-infrared spectroscopy information according to the target object in the face of the system error and reduce errors to *** finally selects 13 spectral bands,simplifies the NIR spectral data and improves model *** Pearson s correlation coefficient of Calibration(Rc)and the Pearson s correlation coefficient of Prediction(Rp)of Mix Partial Least Squares(MIX-PLS)were 0.95 and 0.90,and Root Mean Square Error of Calibration(RMSEC)and Root Mean Square Error of Prediction(RMSEP)are 2.075 and 6.001,respectively,which shows the model has good generalization abilities.