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

Previous Articles     Next Articles

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. 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.

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

CLC Number: 

  • O641