程度相似度结合聚类分析在金银花药材质量评价中的应用  

In combination of the extent similarity and the clustering analysis to evaluate the quality of Flos lonicerae japonicae

作　　者：段和祥[1] 刘永锁[1] 罗国安[1] 王义明[1] 

机构地区：[1]清华大学化学系

出　　处：《中成药》2007年第3期318-321,共4页Chinese Traditional Patent Medicine

基　　金：国家科技攻关项目(2004BA721A13)资助

摘　　要：目的:采用程度相似度算法,并结合聚类分析对金银花药材的质量进行评价。方法:建立金银花指纹图谱。对35批金银花样本,计算其相关系数、夹角余弦和程度相似度,并进行聚类分析。结果:程度相似度和聚类分析相结合评价金银花药材,判断结果符合实际情况。结论:该方法准确、可行,可作中药质量评价的一种直观、合理、有效的技术手段。AIM： The extent similarity algorithm was introduced, integrated clustering analysis to evaluate me quality of different sources of Flos lonicerae japonicae. METHODS： The fingerprint spectum of Flos lonicerae japonicae was established to calculate correlation coefficient, cosine of the included angle and extent similarity of thirty-five samples, and then clustering analysis was adopted. RESULTS： In combination of the extent similarity and the clustering analysis to evaluate the quality of Flos lonicerae japonicae, and the results showed that it accorded with reality. CONCLUSION： This method is accurate and reliable, and it is an apparent, credible and efficient method for quality evaluation of Chinese medicines.

关 键 词：指纹图谱 程度相似度 聚类分析 金银花 

分 类 号：R284.1[医药卫生—中药学]