Genetic algorithm optimisation combined with partial least squares regression and mutual information variable selection procedures in near-infrared quantitative analysis of cotton-viscose textiles

被引:114
作者
Durand, A. [1 ]
Devos, O. [1 ]
Ruckebusch, C. [1 ]
Huvenne, J. P. [1 ]
机构
[1] Univ Sci & Tech Lille Flandres Artois, LASIR, CNRS, UMR 8516, F-59655 Villeneuve Dascq, France
关键词
near-infrared spectroscopy; textile; multivariate calibration; genetic algorithm; mutual information; artificial neural network;
D O I
10.1016/j.aca.2007.03.024
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
In this work, different approaches for variable selection are studied in the context of near-infrared (NIR) multivariate calibration of textile. First, a model-based regression method is proposed. It consists in genetic algorithm optimisation combined with partial least squares regression (GA-PLS). The second approach is a relevance measure of spectral variables based on mutual information (MI), which can be performed independently of any given regression model. As MI makes no assumption on the relationship between X and Y, non-linear methods such as feed-forward artificial neural network (ANN) are thus encouraged for modelling in a prediction context (MI-ANN). GA-PLS and MI-ANN models are developed for NIR quantitative prediction of cotton content in cotton-viscose textile samples. The results are compared to full-spectrum (480 variables) PLS model (FS-PLS). The model requires 11 latent variables and yielded a 3.74% RMS prediction error in the range 0-100%. GA-PLS provides more robust model based on 120 variables and slightly enhanced prediction performance (3.44% RMS error). Considering MI variable selection procedure, great improvement can be obtained as 12 variables only are retained. On the basis of these variables, a 12 inputs ANN model is trained and the corresponding prediction error is 3.43% RMS error. (c) 2007 Elsevier B.V. All rights reserved.
引用
收藏
页码:72 / 79
页数:8
相关论文
共 37 条
[1]  
ASTAKHOV SA, MILCA ALGORITHM
[2]   STANDARD NORMAL VARIATE TRANSFORMATION AND DE-TRENDING OF NEAR-INFRARED DIFFUSE REFLECTANCE SPECTRA [J].
BARNES, RJ ;
DHANOA, MS ;
LISTER, SJ .
APPLIED SPECTROSCOPY, 1989, 43 (05) :772-777
[3]  
BARTON FE, 1996, APPL SPECTROSC, V20, P41
[4]   Spectrophotometric variable selection by mutual information [J].
Benoudjit, N ;
François, D ;
Meurens, M ;
Verleysen, M .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2004, 74 (02) :243-251
[5]   Use of near-infrared spectrometry in control analyses of acrylic fibre manufacturing processes [J].
Blanco, M ;
Coello, J ;
Iturriaga, H ;
Maspoch, S ;
Pagès, J .
ANALYTICA CHIMICA ACTA, 1999, 383 (03) :291-298
[6]   Structural FTIR analysis and thermal characterisation of lyocell and viscose-type fibres [J].
Carrillo, A ;
Colom, X ;
Sunol, JJ ;
Saurina, J .
EUROPEAN POLYMER JOURNAL, 2004, 40 (09) :2229-2234
[7]   Using chemometric methods and NIR spectrophotometry in the textile industry [J].
Cleve, E ;
Bach, E ;
Schollmeyer, E .
ANALYTICA CHIMICA ACTA, 2000, 420 (02) :163-167
[8]  
CZEKALSKI J, 2004, J NAT FIBERS, V1, P25
[9]  
Eckschlager K., 1994, Information Theory in Analytical Chemistry
[10]  
FISHER G, 2005, INT FIBER J, V20, P14