首页 | 本学科首页   官方微博 | 高级检索  
     

基于烟叶近红外光谱主成分数据的投影方法研究及其在复烤配方中的应用
引用本文:陶帅,马翔,李军会,张文娟,赵龙莲,温亚东,王毅,张录达. 基于烟叶近红外光谱主成分数据的投影方法研究及其在复烤配方中的应用[J]. 光谱学与光谱分析, 2009, 29(11): 2970-2974. DOI: 10.3964/j.issn.1000-0593(2009)11-2970-05
作者姓名:陶帅  马翔  李军会  张文娟  赵龙莲  温亚东  王毅  张录达
作者单位:1. 中国农业大学信息与电气工程学院,北京,100083
2. 玉溪红塔集团技术中心,云南,玉溪,653100
3. 中国农业大学理学院,北京,100193
基金项目:国家"十一五"科技支撑计划项目,红塔集团科技项目资助 
摘    要:对近红外技术在烟草中的应用作了简要的概述,报道了两种基于近红外光谱主成分的投影矢量求解方法,分别简称为PPF_PCA和PPF_Eig,并对两种方法在复烤配方中的应用与评价做了比较研究.对9类烟叶工业分级样品光谱进行一维投影分析的结果表明:PPF_PCA方法得到的一维投影值的类间差异性和类内差异性均大于PPF_Eig方法,其中各类间投影均值的平均绝对偏差前者约为后者的1.26倍.同时应用第一维投影值所占贡献率的情况对此结果进行了解释,PPF_PCA方法一维投影值所占贡献率为93%,PPF_Eig方法一维投影值所占贡献率为77%,前者约为后者的1.21倍,因此,PPF_PCA方法得到的一维投影值中包含更多类间和类内的差异性信息.应用烟叶各类工业分级样品的一维投影图能客观的评价各类样品之间的相似性及各类内样品之间的差异性,可方便的作为烟叶复烤配方的参考依据,同时在其他农产品(如中药等)配方中也具有较好的应用前景.

关 键 词:烟叶  近红外  主成分  投影  复烤配方
收稿时间:2008-11-06

Study on the Projection Method Based on Principal Component of Tobacco Near-Infrared Spectrum and Application in Redrying Model
TAO Shuai,MA Xiang,LI Jun-hui,ZHANG Wen-juan,ZHAO Long-lian,WEN Ya-dong,WANG Yi,ZHANG Lu-da. College of Information , Electrical Engineering,China Agricultural University,Beijing ,China. Technology Center of Yuxi Hongta Group,Yuxi ,China. College of Science,China. Study on the Projection Method Based on Principal Component of Tobacco Near-Infrared Spectrum and Application in Redrying Model[J]. Spectroscopy and Spectral Analysis, 2009, 29(11): 2970-2974. DOI: 10.3964/j.issn.1000-0593(2009)11-2970-05
Authors:TAO Shuai  MA Xiang  LI Jun-hui  ZHANG Wen-juan  ZHAO Long-lian  WEN Ya-dong  WANG Yi  ZHANG Lu-da. College of Information    Electrical Engineering  China Agricultural University  Beijing   China. Technology Center of Yuxi Hongta Group  Yuxi   China. College of Science  China
Affiliation:TAO Shuai1,MA Xiang2,LI Jun-hui1,ZHANG Wen-juan1,ZHAO Long-lian1,WEN Ya-dong2,WANG Yi2,ZHANG Lu-da31. College of Information and Electrical Engineering,China Agricultural University,Beijing 100193,China2. Technology Center of Yuxi Hongta Group,Yuxi 653100,China3. College of Science,China
Abstract:The present paper briefly describes the application of near-infrared spectroscopy technology in tobacco. Two methods for solving projection vector based on the principal component of near-infrared spectrum are reported. They are named as projection of basing on principal component and Fisher criterion by principal component analysis method (PPF_PCA for short) and projection of basing on principal component and Fisher criterion by solving eigenvalue (PPF_Eig for short),and they are studied and compared in th...
Keywords:Tobacco leaf  Near-infrared  Principal component  Projection  Redrying model  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号