近红外漫反射光谱法和模式识别技术鉴别中药材产地  

Determination of Geographical Origins of Chinese Medical Herbs by NIR and Pattern Recognition

作　　者：刘沭华[1] 张学工[1] 周群[2] 孙素琴[2] 

机构地区：[1]清华大学自动化系,北京100084 [2]清华大学化学系,北京100084

出　　处：《光谱学与光谱分析》2006年第4期629-632,共4页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(60275014);国家中医药管理局科技重大项目(国中医药科2001ZDZX01)资助

摘　　要：采用近红外漫反射光谱法获得了来自不同产地的中药材的红外光谱,结合近邻法和多类支持向量机等模式识别技术,对来自四个不同产地的269个白芷样本和六个不同产地的350个野生和栽培丹参样本进行了产域鉴别,得到的交叉验证准确率分别达到99%和95%,为中药材产地的快速无损鉴别探索了一条有效的途径。Geographical origin of medical herbs is an important factor of the quality of many traditional Chinese herbal medicines. The objective of the present study is to investigate whether NIR spectroscopy coupled with pattern recognition techniques could effectively discriminate geographical origins of medical herbs. Nearest neighbor method （NNM） and a SVM-based multiclass classifier were employed to discriminate 269 Angelicae Dahuricae Radix （ADR） samples from 4 provinces and 380 Salviae Miltiorrhizae Radix （SMR） samples from 6 provinces in China. The multiclass classifier achieves leave-one-out cross-validation accuracy of 99% for （ADR） and 95% （SMR）. This classification scheme can be a highly accurate approach to the rapid and nondestructive discrimination of medical herbs of different origins.

关 键 词：近红外光谱 模式识别 中药材鉴别 

分 类 号：O657.3[理学—分析化学]