中国中药杂志

2004, (11)

[打印本页] [关闭]
本期目录(Current Issue) | 过刊浏览(Past Issue) | 高级检索(Advanced Search)

一类基于组效关系神经网络模型的中药药效预测方法
A method for predicting activity of traditional Chinese medi cine based on quantitative composition-activity relationship of neural network model

赵筱萍,范骁辉,余杰,程翼宇
ZHAO Xiao-ping 1,2 , FAN Xiao-hui1, YU Jie1, CHENG Yi- yu 1*(1. Department of Chinese Medicine Science and Engineering, Zhejian g University, Hangzhou 310027, China; 2. Zhejiang Medical College, Hangzhou 310053, China) [

摘要(Abstract):

目的 :研究与药效相关的中药质量分析方法。方法 :分别选取非线性函数逼近能力较强的BP神经网络和径向基函数神经网络 ,并与偏最小二乘法相结合 ,建立中药组效关系模型 ,进而用组效关系模型计算预测药效 ,据此评价中药质量。结果与结论 :将其应用于川芎质量评价 ,无论在训练误差、预测误差以及相关系数等方面 ,均明显优于PCR和PLSR方法 ,具有较理想的训练及预测精度和可信度 ,能够较准确地反映川芎各化学组分与药效检测指标间复杂的非线性映射关系 ,可发展成为能反映药效的中药质量评价方法。
Objective: To study a method for evaluating the q uality of traditional Chinese medicine (TCM) according as their activity. Method: Combined with partial least squares (PLS), BP and RBF neura l networks were selected to establish the model of quantitative composition-act ivity relationship (QCAR) due to their strong approximation capabilities for non linear function respectively. The activity of TCM was predicted with the QCAR m odel , and the quality of TCM was evaluated according to the predicted activity. Result & Conclusion: The proposed method was applied to evaluate the quality of Chuanxiong. The results indicated that, in the indexes includ ing training error, prediction error and correlation coefficient, the establis hed model is better than the model established by principal component regression or PLS regression. The new model can accurately represent the complicated nonli near relationship between the components and the bioactivity of Chuanxiong. C onsequently, this method has potential to evaluate the quality of TCM according to bioactivity. [

关键词(KeyWords): 中药组效关系;中药质量评价;神经网络;偏最小二乘法
quantitative composition-activity relationship ; quality evaluation of traditional Chinese medicine; neutral network; partia l least squares

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金重大研究计划重点项目(90 2 0 90 0 5 ) ;; 国家重点基础研究发展规划项目 (G19990 5 44 0 5 )

作者(Author): 赵筱萍,范骁辉,余杰,程翼宇
ZHAO Xiao-ping 1,2 , FAN Xiao-hui1, YU Jie1, CHENG Yi- yu 1*(1. Department of Chinese Medicine Science and Engineering, Zhejian g University, Hangzhou 310027, China; 2. Zhejiang Medical College, Hangzhou 310053, China) [

Email:

DOI:

扩展功能
本文信息
服务与反馈
本文关键词相关文章
本文作者相关文章
中国知网
分享