文献类型：期刊文献

英文题名：Prediction of wood property in Chinese Fir based on visible/near-infrared spectroscopy and least square-support vector machine

作者：Zhu, Xiangrong[2] Shan, Yang[2,3] Li, Gaoyang[2] Huang, Anmin[4] Zhang, Zhuoyong[1]

第一作者：Zhu, Xiangrong

通信作者：Zhang, ZY[1]

机构：[1]Capital Normal Univ, Dept Chem, Beijing 100048, Peoples R China;[2]Hunan Agr Prod Proc Inst, Changsha 410125, Hunan, Peoples R China;[3]Cent S Univ, Coll Chem & Chem Engn, Changsha 410083, Peoples R China;[4]Chinese Acad Forestry, Res Inst Wood Ind, Beijing 100091, Peoples R China

年份：2009

卷号：74

期号：2

起止页码：344-348

外文期刊名：SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY

收录：;EI(收录号：20093612289314);Scopus(收录号：2-s2.0-69249219235);WOS:【SCI-EXPANDED(收录号:WOS:000270109300006)】；

基金：This work was supported by Key Technology R&D Program in the 11th Five-year Plan of Hunan Province (No.: 2006NK1002), the Science and Technology Program, Beijing Municipal Education Committee (No.: KM2007110028009) and Beijing Natural Science Foundation (Project No: 6092021).

语种：英文

外文关键词：Wood density; Visible/near-infrared spectrometry; Least squares-support vector machines; Partitioning based on joint x-y distances algorithm

摘要：A method for the quantification of density of Chinese Fir samples based on visible/near-infrared (vis-NIR) spectrometry and least squares-support vector machine (LS-SVM) was proposed. Sample set partitioning based on joint x-y distances (SPXY) algorithm was used for dividing calibration and prediction samples, it is of value for prediction of property involving complex matrices. A stepwise procedure is employed to select samples according to their differences in both x (instrumental responses) and y (predicted parameter) spaces. For comparison, the models were also constructed by Kennard-Stone method. as well as by using the duplex and random sampling methods for subset partitioning. The results revealed that the SPXY algorithm may be an advantageous alternative to the other three strategies. To validate the reliability of LS-SVM, comparisons were made among other modeling methods such as support vector machine (SVM) and partial least squares (PLS) regression. Satisfactory models were built using LS-SVM, with lower prediction errors and superior performance in relation to SVM and PLS. These results showed possibility of building robust models to quantify the density of Chinese Fir using near-infrared spectroscopy and LS-SVM combined SPXY algorithm as a nonlinear multivariate calibration procedure. (C) 2009 Elsevier B.V. All rights reserved.