基于自组织神经网络的麻黄模式识别研究  

Pattern Recognition of Ephedra Based on Self-Organization Neural Network

作　　者：申明金 曹洪斌 Shen Mingjin;Cao Hongbin(Department of Chemistry,College of Pharmacy,North Sichuan Medical College,Nanchong 637000,China)

机构地区：[1]川北医学院药学院化学教研室,四川南充637000

出　　处：《山东化工》2023年第5期61-62,74,共3页Shandong Chemical Industry

基　　金：南充科技局市校合作项目(19SXHZ0238)。

摘　　要：介绍了自组织竞争网络和自组织特征映射网络的原理。中药药用价值与其所含微量元素有直接的关系,药材分类是中药质量控制的重要方法。采用麻黄中微量元素数据建立网络模型,对网络结构参数进行了优化并对麻黄样本进行了聚类分析。数据分析结果表明,自组织竞争网络和自组织特征映射网络都有较好的分类结果,符合生产实际,是中药麻黄化学模式识别的一种有效方法。The theory of self-organization competitive neural network and self-organization mapping neural network had been introduced in this paper.Traditional Chinese medicinal value is directly related to trace elements and classification is an important method for quality control.The trace element contents of ephedra were as the inputs to build network model.The parameter of net structure were optimized and the cluster analysis of input sample was made.The results showed that the effect of classification of the two kinds of network is good and accord with practical production,these two kinds of network were proved to be effective pattern recognition method of ephedra.

关 键 词：自组织竞争神经网络 自组织特征映射神经网络 麻黄 微量元素 模式识别 

分 类 号：O652[理学—分析化学]