Tablets Classification Method Based on Bayesian Decision and Near Infrared Spectroscopy

被引:0
|
作者
Zhou Yang [1 ,2 ]
Lu Jin [1 ]
Dai Shu-Guang [2 ]
Liu Tie-Bing [1 ]
Shi Yang [1 ]
Ge Ding-Fei [1 ]
Li Bo-Bin [3 ]
机构
[1] Zhejiang Univ Sci & Technol, Lab NIR Applicat, Hangzhou 310023, Zhejiang, Peoples R China
[2] Shanghai Univ Sci & Technol, Coll Opt & Elect Engn, Shanghai 200093, Peoples R China
[3] Natl Qual Supervis & Testing Ctr Rice Wine, Shaoxing 310027, Peoples R China
关键词
Tablets classification; Near infrared spectroscopy; Bayesian decision; Parameter estimation; DISCRIMINATION;
D O I
10.3724/SP.J.1096.2013.20317
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Lack of samples and uneven distribution in different sample sets is the problem at tablets classification using near infrared spectroscopy that cause the classification error. A classification method based on Bayesian decision making is proposed. The method estimate the priori probability density of calibration set and class conditional probability density of unknown tablets spectral using different kinds of calibration set. The posterior probability is calculated by Bayesian full probability formula. The unknown tablet is classified according to its posterior probability. The experiment selects four categories of citalopram tablets with different amount in each category. The Bayesian decision model based on calibration set of 70 spectra is used to classify 20 tablets in the validation set. Comparing to PLSDA method, the sensitivity and specificity of the Bayesian model is 100%, validating the Bayesian decision taxonomy can improve the classification accuracy and adaptability in the distribution based on NIR spectral.
引用
收藏
页码:293 / 296
页数:4
相关论文
共 17 条
  • [1] Support vector machine regression (SVR/LS-SVM)-an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data
    Balabin, Roman M.
    Lomakina, Ekaterina I.
    [J]. ANALYST, 2011, 136 (08) : 1703 - 1712
  • [2] Analysis of pharmaceuticals by NIR spectroscopy without a reference method
    Blanco, Marcelo
    Peguero, Anna
    [J]. TRAC-TRENDS IN ANALYTICAL CHEMISTRY, 2010, 29 (10) : 1127 - 1136
  • [3] Tablet potency of Tianeptine in coated tablets by near infrared spectroscopy: Model optimisation, calibration transfer and confidence intervals
    Boiret, Mathieu
    Meunier, Loic
    Ginot, Yves-Michel
    [J]. JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS, 2011, 54 (03) : 510 - 516
  • [4] Comparative study of non-destructive methods to quantify thickness of tablet coatings
    Cahyadi, C.
    Karande, A. D.
    Chan, L. W.
    Heng, P. W. S.
    [J]. INTERNATIONAL JOURNAL OF PHARMACEUTICS, 2010, 398 (1-2) : 39 - 49
  • [5] Application of linear/non-linear classification algorithms in discrimination of pork storage time using Fourier transform near infrared (FT-NIR) spectroscopy
    Chen, Quansheng
    Cai, Jianrong
    Wan, Xinmin
    Zhao, Jiewen
    [J]. LWT-FOOD SCIENCE AND TECHNOLOGY, 2011, 44 (10) : 2053 - 2058
  • [6] CHU Xiao-Li, 2011, MOL SPECTROSCOPY ANA, P99
  • [7] Chemometric quantitation of the active substance (containing CN) in a pharmaceutical tablet using near-infrared (NIR) transmittance and NIR FT-Raman spectra
    Dyrby, M
    Engelsen, SB
    Norgaard, L
    Bruhn, M
    Lundsberg-Nielsen, L
    [J]. APPLIED SPECTROSCOPY, 2002, 56 (05) : 579 - 585
  • [8] NONPARAMETRIC ESTIMATION OF COMPOSITE FUNCTIONS
    Juditsky, Anatoli B.
    Lepski, Oleg V.
    Tsybakov, Alexandre B.
    [J]. ANNALS OF STATISTICS, 2009, 37 (03): : 1360 - 1404
  • [9] Using combinations of principal component scores from different spectral ranges in near-infrared region to improve discrimination for samples of complex composition
    Lee, Sanguk
    Chung, Hoeil
    Choi, Hangseok
    Cha, Kyungjoon
    [J]. MICROCHEMICAL JOURNAL, 2010, 95 (01) : 96 - 101
  • [10] Combining Infrared, Near Infrared with Soft Independent Modeling of Class Analogy for Identification of Vegetable Blend Oil
    Li Juan
    Fan Lu
    Bi Yan-Lan
    Qu Ling-Bo
    Deng De-Wen
    Zhou Zhan-Ming
    Wu Cun-Rong
    [J]. CHINESE JOURNAL OF ANALYTICAL CHEMISTRY, 2010, 38 (04) : 475 - 482