基于两种模式识别技术的盐酸左氧氟沙星注射液近红外光谱定量分析

J4 ›› 2009, Vol. 47 ›› Issue (6): 1318-1322.

基于两种模式识别技术的盐酸左氧氟沙星注射液近红外光谱定量分析

张勇^1,2, 宋岩^3,4, 丛茜¹, 赵冰³

1. 吉林大学工程仿生教育部重点实验室, 长春 130022|2. 吉林工程技术师范学院信息工程学院, 长春 130052;3. 吉林大学超分子结构与材料国家重点实验室, 长春 130012|4. 长春中医药大学新药研发中心, 长春 130117

收稿日期:2009-02-27 出版日期:2009-11-26 发布日期:2010-01-07
通讯作者: 赵冰 E-mail:zhaob@mail.jlu.edu.cn.

Application of Two Pattern Recognition Techniques to Near-infrared Spectroscopy Quantitative Analysis ofLevofloxacin Hydrochloride for Injection

ZHANG Yong^1,2, SONG Yan^3,4, CONG Qian¹, ZHAO Bing³

1. Key Laboratory of Bionic Engineering of Ministry of Education, Jilin University, Changchun 130022, China|2. College of Information Engineering, Jilin Teachers&rsquo|Institute of Engineering and Technology, Changchun 130052, China;3. State Key Laboratory for Supramolecular Structure and Materials, Jilin University, Changchun 130012, China;4. Center for New Drugs Research, Changchun University of Traditional Chinese Medicine, Changchun 130117, China

Received:2009-02-27 Online:2009-11-26 Published:2010-01-07
Contact: ZHAO Bing E-mail:zhaob@mail.jlu.edu.cn.

摘要/Abstract

摘要：

测定同一厂家生产的53个不同批次盐酸左氧氟沙星注射液的近红外光谱. 先利用小波变换技术对光谱变量进行去噪, 并对其有效的压缩, 以提高建模效率, 再分别利用神经网络及支持向量机技术建立盐酸左氧氟沙星注射液样品的定量分析模型, 并讨论了建模过程中相关参数的优化选择. 仿真实验表明, 建立的SVM定量分析模型的相关性要优于BP网, 同时SVM定量分析模型的RMSECV及RME两个指标值也显示其预测效果良好, 泛化能力强.

关键词: 近红外光谱；支持向量机；人工神经网络；小波变换；盐酸左氧氟沙星注射液

Abstract:

The 53 samples of Levofloxacin Hydrochloride for injection from different batches of a factory were surveyed by nearinfrared (NIR) spectroscopy. The spectrum variables of all the samples had been efficiently compressed and denoised through the wavelet transformation (WT) technology before the models were established by pattern recognition techniques. The two quantitative analysis models of Levofloxacin Hydrochloride for injection established via support vector machine (SVM) and artificial neural network (ANN) were studied separately in this experiment using radial basis function (RBF) SVM and back propag
ation (BP) network, and the related parameters were also discussed in detail. The simulation results show that the correlation of predicted values and chemical determination values of SVM model is better than that of ANN model, and SVM model owns excellent generalization for quantitative analysis results and high prediction accuracy.

Key words: nearinfrared spectroscopy, support vector machine, artificial neural network, wavelet transformation, Levofloxacin Hydrochloride injection

中图分类号:

O641

张勇, 宋岩, 丛茜, 赵冰. 基于两种模式识别技术的盐酸左氧氟沙星注射液近红外光谱定量分析[J]. J4, 2009, 47(6): 1318-1322.

ZHANG Yong, SONG Yan, CONG Qian, ZHAO Bing. Application of Two Pattern Recognition Techniques to Near-infrared Spectroscopy Quantitative Analysis ofLevofloxacin Hydrochloride for Injection[J]. J4, 2009, 47(6): 1318-1322.

[1]	崔宝秋, 赵东霞, 杨忠志. 蚯蚓血红蛋白载氧功能的Fukui函数[J]. J4, 2012, 50(01): 129-133.
[2]	赵岷, 李作盛, 张元, 王璐. 含不同二硫醇盐的Pt(Ⅱ)吡啶三嗪配合物的二阶NLO性质[J]. J4, 2011, 49(02): 331-335.