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

基于偏最小二乘回归的类模型方法用于中药牛黄的真伪鉴别
引用本文:徐路,付海燕,姜宁,俞晓平.基于偏最小二乘回归的类模型方法用于中药牛黄的真伪鉴别[J].分析化学,2010,38(2).
作者姓名:徐路  付海燕  姜宁  俞晓平
作者单位:1. 中国计量学院生命科学学院,杭州,310018;大理学院,大理,671000
2. 湖南大学化学化工学院,长沙,410082
3. 中国计量学院生命科学学院,杭州,310018
基金项目:农业部科技重大专项基金(No.2009ZX08012-013B)资助项目
摘    要:针对独立软模式类簇法(SIMCA)在确定主成分数和决策区间时遇到的困难,提出了一种基于PLSR的类模型方法——PLS类模型方法(PLSCM)。通过把类描述问题转化为常见的PLSR问题,采用成熟的蒙特卡罗交互验证法确定模型的隐变量数和决策区间。采用本方法对不同牛黄样品的近红外光谱数据(波长范围4000~9000 cm-1)进行分析,可成功鉴别牛黄的真伪。本方法的可操作性和鉴别准确率均优于经典的SIMCA方法。对于原始光谱数据,PLSCM的训练和预测准确率均为100%,对于经SNV处理的数据,训练和预测准确率分别为99%和100%。

关 键 词:化学模式识别  类模型  独立软模式类簇法  偏最小二乘回归类模型  

A New Class Model Based on Partial Least Square Regression and Its Applications for Identifying Authenticity of Bezoar Samples
XU Lu,FU Hai-Yan,JIANG Ning,YU Xiao-Ping.A New Class Model Based on Partial Least Square Regression and Its Applications for Identifying Authenticity of Bezoar Samples[J].Chinese Journal of Analytical Chemistry,2010,38(2).
Authors:XU Lu  FU Hai-Yan  JIANG Ning  YU Xiao-Ping
Institution:College of Life Sciences;China Jiliang University;Hangzhou 310018;College of Pharmary;Dali University;Dali 671000;College of Chemistry and chemical Engineering;Hunan University;Changsha 410082
Abstract:SIMCA(self independent modeling of class analogy) is a classical class modeling method for chemical pattern recognition.Although widely used,SIMCA suffers difficulties in selecting a proper number of principal components and determining the decision region.A new class modeling technique based on partial least squares regression,partial least squares class model(PLSCM) is proposed,where the number of latent variables and decision region can be readily estimated by the routine methods in multivariate calibrat...
Keywords:Chemical pattern recognition  Class model  Soft independent modeling of class analogy  Partial least squared class model  
本文献已被 CNKI 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