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

支持向量机与紫外光谱法用于鉴别清开灵注射液六混中间体
引用本文:朱向荣,李娜,史新元,乔延江,张卓勇.支持向量机与紫外光谱法用于鉴别清开灵注射液六混中间体[J].光谱学与光谱分析,2008,28(7):1626-1629.
作者姓名:朱向荣  李娜  史新元  乔延江  张卓勇
作者单位:1. 首都师范大学化学系,北京,100037
2. 北京中医药大学中药学院,北京,100102
摘    要:采用一阶导数对紫外可见光谱数据进行预处理,消除光谱中的斜坡背景,用支持向量机(SVM)进行建模,分别对4个批次的中药清开灵注射液六混中间体以及其混和批次共147个样本进行了鉴别。对建模参数的影响作了系统的研究,在优化参数条件下,正确率分别可达100%,95.4%,97.3%,100%和97.3%。结果表明SVM鉴别准确率高,模型的泛化能力强。此方法也为中药注射液生产过程的质量控制提供了一条有效的途径。

关 键 词:支持向量机  紫外光谱  清开灵注射液  中间体

Study on the Chinese Medicinal Qingkailing Inj ections Intermediate by Support Vector Machines and Ultraviolet Spectrometry
ZHU Xiang-rong,LI Na,SHI Xin-yuan,QIAO Yan-jian,ZHANG Zhuo-yong.Study on the Chinese Medicinal Qingkailing Inj ections Intermediate by Support Vector Machines and Ultraviolet Spectrometry[J].Spectroscopy and Spectral Analysis,2008,28(7):1626-1629.
Authors:ZHU Xiang-rong  LI Na  SHI Xin-yuan  QIAO Yan-jian  ZHANG Zhuo-yong
Institution:Department of Chemistry, Capital Normal University, Beijing 100037, China.
Abstract:The first derivative and wavelet compression methods were used to eliminate the slope-background and reduce variables for the measured ultraviolet (UV) spectra of Chinese medicinal Qingkailing injections intermediate. Then, support vector machine (SVM) was used for building the classification model to discriminate qualified and unqualified samples. The effects of spectral preprocessing and model parameters were investigated. Under optimized conditions, correct classifications of 100%, 95.4%, 97.3%, and 100% were obtained for the four batches of the intermediate of Qingkailing injection samples, respectively. A percentage of 97.3% of the intermediate samples were correctly classified for all the four batches of mixture samples. Results showed that SVM technique can be a useful means for quality control of Chinese medicinal injections owing to its good accuracy and better generalization.
Keywords:Support vector machine  Ultraviolet spectrometry  Qingkailing injections  Intermediate
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