基于人工神经网络的中药药性判别研究

山东大学学报(医学版) ›› 2011, Vol. 49 ›› Issue (1): 57-61.

基于人工神经网络的中药药性判别研究

李雨，李骁，薛付忠，刘言训

山东大学公共卫生学院卫生统计学研究所，济南 250012

收稿日期:2010-09-21 出版日期:2011-01-10 发布日期:2011-01-10
通讯作者: 刘言训(1962- ），男，硕士，硕士生导师，主要从事卫生统计学研究。 E-mail：liuyx@sdu.edu.cn
作者简介:李雨(1982- )，女，硕士研究生，主要从事中药药性识别的统计模型研究。
基金资助:
国家重点基础研究发展计划(973计划)课题：中药药性理论相关基础问题研究（2007CB512601）。

Discrimination of properties of Chinese traditional medicines based on an artificial neural network

LI Yu， LI Xiao， XUE Fu-zhong， LIU Yan-xun

Institute of Health Statistics, School of Public Health, Shandong University, Jinan 250012, China

Received:2010-09-21 Online:2011-01-10 Published:2011-01-10

摘要/Abstract

摘要：

目的探讨中药的属性特征与其药性的相关性，及基于误差反向传播算法(BP)的人工神经网络在中药药性判别中的可行性。方法收集《中华本草》中收录的药性明确、属性特征详尽且具有代表性的植物药1728种，先后以单因素和多因素非条件Logistic回归筛选与药性相关性有统计学意义的药材属性特征，再构建基于中药材属性特征的药性判别的BP神经网络模型，并以此模型对药材的药性进行判别分类。结果按照分层随机抽样的原则，从寒、热性两类药材中分别随机抽取60%的药材作为训练集，其余40%（共691种）药材组成测试集，构建三层BP模型对药材做出判别。测试药材中，热性药的正确率为70.72%，寒性药的正确率为71.96%，整体正确率为71.49%。结论基于中药的属性特征，BP神经网络模型能够进行药性的快速识别，且该模型具有自适应性、容错性、非线性等特点，能够有效解决中药属性特征与药性的非线性相关关系问题，为中药药性的有效判别提供了新思路和新方法。

关键词: 人工神经网络；中药药性；判别分析

Abstract:

Objective To explore the correlation between properties of Chinese traditional medicines（TCM）and their original characters, and to identify the feasibility of an error back-propagation artificial neural network (BP-ANN) to discriminate properties of TCM based on original characters. Methods Information on original characters and properties of 1728 kinds of TCM was first collected from “Chinese Herbal Medicine”. 24 kinds of statistically significant characters were screened by single-factor and multi-factor logistic regression analysis. BP-ANN was applied to construct a model and to discriminate properties of TCM based on statistically significant characters. Results According to the principle of stratified random sampling, 60% of TCM in the cold group and the hot group were respectively selected as the training set and the remaining 40%(691 kinds in all) made up the testing set. A three-layer BP-ANN model was built to describe the correlation between properties of TCM and statistically significant characters; according to this model，the discriminative accuracy was 70.72% and 71.96% in the hot group and the cold group, respectively, and the overall accuracy was 71.49%. Conclusion Based on original characters, BP-ANN is capable of rapidly discriminating properties of TCM; BP-ANN, characteristic of adaptability, fault-tolerance and nonlinearity, and can effectively solve the problem of nonlinear correlation between properties of TCM and their original characters, providing a new idea and method for TCM property discrimination.

Key words: Artificial neural Network； Property of Chinese traditional medicines； Discriminatory analysis

中图分类号:

R282.5

李雨，李骁，薛付忠，刘言训. 基于人工神经网络的中药药性判别研究[J]. 山东大学学报(医学版), 2011, 49(1): 57-61.

LI Yu， LI Xiao， XUE Fu-zhong， LIU Yan-xun. Discrimination of properties of Chinese traditional medicines based on an artificial neural network[J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2011, 49(1): 57-61.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	钟女娟1，宋咏梅2，刘更生2，薛付忠1，刘言训1. 中药经验要素贝叶斯网络模型构建及应用[J]. 山东大学学报(医学版), 2012, 50(2): 157-.
[2]	张新新1，李雨1，纪玉佳2，王鹏2，张永清2，薛付忠1. 主成分-线性判别分析在中药药性识别中的应用[J]. 山东大学学报(医学版), 2012, 50(1): 143-146.
[3]	齐方1，容蓉2，薛付忠1. 贝叶斯网络模型在中药整体药性特征分析中的应用[J]. 山东大学学报(医学版), 2011, 49(5): 147-152.