Laser-induced breakdown spectroscopy for the classification of wood materials using machine learning methods combined with feature selection

作     者：Xutai CUI Qianqian WANG Kai WEI Geer TENG Xiangjun XU 崔旭泰;王茜蒨;魏凯;腾格尔;徐向君

作者机构：School of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081People's Republic of China Key Laboratory of Photonic Information TechnologyMinistry of Industry and Information TechnologyBeijing 100081People's Republic of China 

出 版 物：《Plasma Science and Technology》 (等离子体科学和技术（英文版）)

年 卷 期：2021年第23卷第5期

页      面：117-125页

核心收录：

学科分类：12[管理学] 082902[工学-木材科学与技术] 081704[工学-应用化学] 07[理学] 08[工学] 070302[理学-分析化学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 0817[工学-化学工程与技术] 0829[工学-林业工程] 0835[工学-软件工程] 0703[理学-化学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：support from National Natural Science Foundation of China(No.62075011) Graduate Technological Innovation Project of Beijing Institute of Technology(No.2019CX20026) 

主　　题：laser-induced breakdown spectroscopy(LIBS) feature selection wood materials 

摘      要：In this paper,we explore whether a feature selection method can improve model performance by using some classical machine learning models,artificial neural network,k-nearest neighbor,partial least squares-discrimination analysis,random forest,and support vector machine(SVM),combined with the feature selection methods,distance correlation coefficient(DCC),important weight of linear discriminant analysis(IW-LDA),and Relief-F algorithms,to discriminate eight species of wood(African rosewood,Brazilian bubinga,elm,larch,Myanmar padauk,Pterocarpus erinaceus,poplar,and sycamore)based on the laser-induced breakdown spectroscopy(LIBS)*** spectral data are normalized by the maximum of line intensity and principal component analysis is applied to the exploratory data *** feature spectral lines are selected out based on the important weight assessed by DCC,IW-LDA,and *** models are built by using the different number of feature lines(sorted by their important weight)as *** relationship between the number of feature lines and the correct classification rate(CCR)of the model is *** CCRs of all models are improved by using a suitable feature *** highest CCR achieves(98.55...0.39)%when the SVM model is established from 86 feature lines selected by the IW-LDA *** result demonstrates that a suitable feature selection method can improve model recognition ability and reduce modeling time in the application of wood materials classification using LIBS.