首页 | 本学科首页   官方微博 | 高级检索  
     检索      

模式识别和红外光谱法相结合鉴别中药材产地
引用本文:刘沭华,张学工,周群,孙素琴.模式识别和红外光谱法相结合鉴别中药材产地[J].光谱学与光谱分析,2005,25(6):878-881.
作者姓名:刘沭华  张学工  周群  孙素琴
作者单位:1. 清华大学自动化系,北京,100084
2. 清华大学化学系,北京,100084
基金项目:国家中医药管理局科技重大项目(国中医药科2001ZDZX01),国家自然科学基金项目(60275007)资助
摘    要:用红外光谱法取得来自不同产地的中药材的中红外光谱,结合模式识别的方法实现中药产地的快速鉴别。采用了近邻法和多类支持向量机方法对采集自4个不同产地的269个白芷样本和6个不同产地的380个丹参样本进行了产地鉴别,得到的交叉验证准确率达99%,为中药材产地的自动鉴别探索了一条有效的途径。

关 键 词:傅里叶红外光谱  模式识别  中药材鉴别  支持向量机
文章编号:1000-0593(2005)06-0878-04
修稿时间:2003年12月16

Use of FTIR and Pattern Recognition to Determine Geographical Origins of Chinese Medical Herbs
LIU Shu-hua,ZHANG Xue-gong,ZHOU Qun,SUN Su-Qin.Use of FTIR and Pattern Recognition to Determine Geographical Origins of Chinese Medical Herbs[J].Spectroscopy and Spectral Analysis,2005,25(6):878-881.
Authors:LIU Shu-hua  ZHANG Xue-gong  ZHOU Qun  SUN Su-Qin
Institution:Department of Automation, Tsinghua University, Beijing 100084, China.
Abstract:Geographical origin of medical herbs is an important factor of the quality of ma ny traditional Chinese herbal medicines. The objective of this study is to inves tigate whether FTIR spectroscopy coupled with pattern recognition techniques cou ld effectively discriminate geographical origins of medical herbs. Nearest neig hbor method (NNM) and a SVM-based multiclass classifier were employed to discri minate 269 angelicae dahuricae radix (ADR) samples from 4 provinces in China and 380 salviae miltiorrhizae radix (SMR) samples from 6 provinces. A leave-one- out cross-validation accuracy of 99% was achieved by the multiclass classifier. The study shows this classification scheme can be a highly accurate approach f or the discrimination of medical herbs of different origins.
Keywords:FTIR spectrum  Pattern recognition  Chinese medical herb  Support vector mechanism
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号