主成分——逐步回归——BP算法在近红外光谱定量分析中应用的研究  

Study of Near-Infrared Spectra for Quantitative AnalysisUsing Principal Component-stepwise Regression-BP Algorithm

作　　者：齐小明[1,2] 张录达[1,2] 柴丽娜[1,2] 严衍禄[1,2] 潘大志 

机构地区：[1]北京农学院基础科学系 [2]中国农业大学

出　　处：《北京农学院学报》1999年第3期47-52,共6页Journal of Beijing University of Agriculture

摘　　要：本文提出一种新的Ｂ－Ｐ算法：主成分—逐步回归—ＢＰ算法．用于近红外光谱定量分析中，其所建模型的预测精度明显高于以往的逐步回归—ＢＰ算法和主成分—ＢＰ算法．Back Propagation network (B-P) has been used in Near-Infrared spectra (NIR) for many years.But the important thing is how to improve its prediction precision.In this study,we put forward Principal component-stepwise regression-BP algorithm(PCR-SRA-BP).It is superior to SRA-BP and PCR-BP algorithm in prediction and the speed of learning.

关 键 词：主成分 逐步回归 BP算法 近红外光谱 定量分析 

分 类 号：O657.33[理学—分析化学]