高等学校化学学报

高等学校化学学报 ›› 2004, Vol. 25 ›› Issue (7): 1251.

• 研究简报 • 上一篇    下一篇

温度限制串联相关网络-近红外光谱法用于药物甲硝唑的质量控制

崔秀君1, 张卓勇2, Peterde B Harrington3, 任玉林4   

  1. 1. 东北师范大学化学学院, 长春 130024;
    2. 首都师范大学化学系, 三维信息获取与应用教育部重点实验室, 北京 100037;
    3. 俄亥俄大学化学系, Athens 45701-2979;
    4. 吉林大学化学学院, 长春 130023
  • 收稿日期:2003-08-26 出版日期:2004-07-24 发布日期:2004-07-24
  • 通讯作者: 张卓勇(1956年出生),男,博士,教授,博士生导师,从事光谱分析及化学计量学研究E-mail:zhuoyong-zhang@hotmail.com E-mail:zhuoyong-zhang@hotmail.com
  • 基金资助:

    北京市教育委员会科学技术发展项目(批准号:KM200310028105)资助

Quality Control of the Powder Pharmaceutical Samples of Metronidazole Based on Near Infrared Reflectance Spectra with Temperature-constrained Cascade Correlation Neural Networks

CUI Xiu-Jun1, ZHANG Zhuo-Yong2, Peter de B Harrington3, REN Yu-Lin4   

  1. 1. Faculty of Chemistry, Northeast Normal University, Changchun 130024, China;
    2. Department of Chemistry, MOE Key Lab for 3-D Information Acquisition and Applications, Capital Normal University, Beijing 100037, China;
    3. Department of Chemistry and Biochemistry, Ohio University, Athens 45701-2979, USA;
    4. College of Chemistry, Jilin University, Changchun 130023, China
  • Received:2003-08-26 Online:2004-07-24 Published:2004-07-24

PDF (PC)

被引次数

7

摘要： 近红外漫反射光谱是一种简便、快速的有机物分析方法,样品不需处理即可直接测量,易于实现固态样非破坏测定.近红外漫反射光谱分析技术广泛应用于农业、食品、化妆品、烟草和石油等方面的组分分用近红外漫反射光谱法进行药品的非破坏性分析正成为国际热门课题.但近红外漫反射光谱的光谱范宽,吸收强度很弱,且组分间光谱严重重叠,给非破坏性分析带来了困难.而近红外漫反射光谱法与化量学相结合,能有效地解决光谱重叠带来的问题[1～3].

关键词: 温度串联相关网络, 近红外漫反射光谱, 分类, 甲硝唑

Abstract: Temperature-constrained cascade correlation networks(TCCCNs) were applied to the identification of the powder pharmaceutical samples of metronidazole based on near infrared(NIR) diffuse reflectance spectra. This work focused on the comparison of performances of the uni-output TCCCN(Uni-TCCCN) to multi-output TCCCN(Multi-TCCCN) by using near infrared diffuse reflectance spectra of metronidazole. The TCCCN models were verified with independent prediction samples by using the "cross-validation" method. The networks were used to discriminate qualified, un-qualified and counterfeit metronidazole pharmaceutical powders. The results showed that multiple outputs network generally worked better than the single output networks. With proper network parameters the pharmaceutical powders can be classified at a rate of 100% in this work. Also, the effects of neural network parameters including number of candidate nodes, type of transfer functions(linear, sigmoid functions and temperature-constrained sigmoid function, respectively) on classification were discussed.

Key words: Temperature-constrained cascade correlation networks, Near infrared reflectance spectrum, Classification, Metronidazole

中图分类号: 

TrendMD: