J4

• • 上一篇    下一篇

近红外光谱分析中人工神经网络法的应用

左平1,2, 马驷良1, 马捷3   

  1. 1. 吉林大学 数学研究所, 长春 130012; 2. 空军航空大学 数学系, 长春 130022; 3. 吉林大学 软件学院, 长春 130012
  • 收稿日期:2005-02-23 修回日期:1900-01-01 出版日期:2006-01-26 发布日期:2006-01-26
  • 通讯作者: 马驷良

Application of Neural Network in the Analysis of Nearinfrared Spectra

ZUO Ping1,2, MA Si-liang1, MA Jie3   

  1. 1. Institute of Mathematics, Jilin University, Changchun 130012, China; 2. Department of Mathematics, PLA Air Force Aerotechnical University, Changchun 130022;3. College of Software, Jilin University, Changchun 130012, China
  • Received:2005-02-23 Revised:1900-01-01 Online:2006-01-26 Published:2006-01-26
  • Contact: MA Si-liang

摘要: 设计了实用的人工神经网络模型进行定标并预测. 用误差反向传播算法, 构造了三层的神经网络结构, 用于解决光谱分析中谱峰重叠严重、 噪声较大等问题. 在定标样本数量较大的情况下, 应用人工神经网络方法对玉米的蛋白质含量和近红外吸收光谱进行了分析和讨论. 实验结果表明, 人工神经网络方法优于线形回归法和偏最小二乘方法.

关键词: 光谱分析, 定标并预测, 人工神经网络法

Abstract: A practical manual neural network model was designed to make the location of target and predication. We used error backward direction propagation calculation method and established three-layer neural network to solve the problems of serious overlap of spectral peaks and big noise in the spectrum analysis. When the quantity of samples to be located is significant, We employed manual neural network method to analyze and discuss the corn’s protein content and nearinfrared spectrum. By analyzing the experimental result it is concluded that manual neural network method is superior to linear regression method and partial leastsquares method.

Key words: spectrum analysis, location and predication, manual neural network method

中图分类号: 

  • TP183