首页 | 本学科首页   官方微博 | 高级检索  
     检索      

PLS-BP法近红外光谱定量分析研究
引用本文:齐小明,张录达,杜晓林,宋昭娟,张一,徐淑燕.PLS-BP法近红外光谱定量分析研究[J].光谱学与光谱分析,2003,23(5):870-872.
作者姓名:齐小明  张录达  杜晓林  宋昭娟  张一  徐淑燕
作者单位:1. 北京农学院基础科学系,北京,102206
2. 中国农业大学理学院,北京,100094
基金项目:北京市教委科技发展计划项目资助(01KJ-086)
摘    要:建立BP模型用于近红外光谱定量分析时,为克服所建模型与训练样本集产生“过拟合”,先用线性算法为其压缩训练数据是必要的。目前多采用主成分法(PCA)和逐步回归法(SRA)。主成分法具有极强的压缩数据能力,用它压缩成的主成分输入BP网所建模型的预测精度一般能满足要求,但它处理数据时未考虑输出变量的影响。逐步回归法根据系统输出选择变量,但所选变量具有自相关性,而且与训练集样品的排列顺序有关,很难选出最好的变量,往往难满足预测精度要求。本研究用偏最小二乘法(PLS),根据输出变量将原始数据压缩为主成分,输入BP网并用所建模型预测30个小麦样品的蛋白质含量。结果表明,与PCA-BP模型的预测决定系数(R2)从92.50提高到97.10,训练迭代次数从12 000减少到4 500。

关 键 词:偏最小二乘法  BP网络  近红外光谱  定量分析
文章编号:1000-0593(2003)05-0870-03
修稿时间:2003年1月6日

Quantitative Analysis Using NIR by Building PLS-BP Model
QI Xiao-ming,ZHANG Lu-da,DU Xiao-lin,SONG Zhao-juan,ZHANG Yi,XU Shu-yan.Quantitative Analysis Using NIR by Building PLS-BP Model[J].Spectroscopy and Spectral Analysis,2003,23(5):870-872.
Authors:QI Xiao-ming  ZHANG Lu-da  DU Xiao-lin  SONG Zhao-juan  ZHANG Yi  XU Shu-yan
Institution:QI Xiao-ming,ZHANG Lu-da,DU Xiao-lin,SONG Zhao-juan,ZHANG Yi,XU Shu-yan 1.Beijing Agricultural College,Beijing 102206,China 2.China Agricultural University,Beijing 100094,China
Abstract:It is necessary to compress the input data for Back Propagation network (BP) with linear arithmetic to avoid the model over tally with calibration set, when a quantitative analysis of biology samples using NIR by building BP model is employed. At present Principal Component Analysis (PCA) and Stepwise Regression (SRA) have been widely used. The PCA computes the scores for the Principal Components (PCs) and uses these scores as ANN input. Since PCA can compress thousands of spectral data into several scores and describe the body of spectra, the training time has been shortened significantly and the model's prediction ability can meet the needs. But the compressing does not concern the relationship between the input variables and target output. The SRA cannot transform the spectrum data, but chooses the same from them according to the sorts of components. Among the variables selected there exists relativity and the efficiency of them depends on the sequence of the samples in the calibration set. Thus it's difficult to obtain the best selection and the BP model's prediction ability cannot often meet the needs. Partial Least Square (PLS) can compute the scores for the principal components (PCs) according to the sorts of components. In this study the scores computed by PLS have been applied as BP input and this BP model has been used to predict the contents of protein in 30 wheat samples. Compared with PCA-BP the PLS-BP model's prediction deciding coefficient (R2 ) has increased from 92.50 to 97.10 with its training iteration times decreased from 12 000 to 4500.
Keywords:Partial Least Square (PLS)  Back Propagation network (BP)  Near-Infrared spectra (NIR)  Quantitative analysis
本文献已被 CNKI 维普 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