高等学校化学学报 ›› 2000, Vol. 21 ›› Issue (1): 49.

• 论文 • 上一篇    下一篇

线性神经网络应用于维生素B族4组分同时测定

印春生1, 沈阳1, 刘树深2, 李志良2, 潘忠孝1   

  1. 1. 中国科学技术大学应用化学系, 合肥 230026;
    2. 重庆大学环境与化学化工学院, 重庆 400044
  • 收稿日期:1999-06-16 出版日期:2000-01-24 发布日期:2000-01-24
  • 通讯作者: 印春生(1963年出生),男,博士,讲师,主要从事计算机化学和分子设计研究.
  • 基金资助:

    国家自然科学基金(批准号:29775001)资助

Application of Linear Neural Network to Simultaneous Determination of Four B-group Vitamins

YIN Chun-Sheng1, SHEN Yang1, LIU Shu-Sheng2, LI Zhi-Liang2, PAN Zhong-Xiao1   

  1. 1. Department of Applied Chemistry, University of Science and Technology of China, Hefei 230026, China;
    2. Collegeof Environment, Chemistry & Chemical Engineering, Chongqing University, Chongqing 400044, China
  • Received:1999-06-16 Online:2000-01-24 Published:2000-01-24

摘要: 报道了一种基于卡尔曼滤波的线性神经网络用于B族维生素混合组分的定量同时测定,用相关系数和标准偏差从原始紫外光谱数据中挑选11个波长点供线性神经网络处理,以极少的迭代次数达到较高的精度,预测结果较好,相关系数大于0.99983,标准偏差0.11301.

关键词: 线性神经网络, 卡尔曼滤波, 多组分同时测定, 维生素B族4组分

Abstract: Simultaneous determination of the multicomponents of four B-group vitamins with a novel Linear Neural Network (LNN) algorithm was reported. Based on the data correlation coefficient and standard deviation, 11 representative wavelength points were selected from the original UV spectral data (240 points) as the original input patterns for FLN to build an NN model. The results obtained by LNN is satisfactory, with a correlation coefficient 0.999 83 and a standard deviation 0.113 01.

Key words: Linear neural network (LNN), Kalman filtering, Multicomponent simultaneous determination, Four B-group vitamins

中图分类号: 

TrendMD: