Comparing radial basis function and feed-forward neural networks assisted by linear discriminant or principal component analysis for simultaneous spectrophotometric quantification of mercury and copper

被引:27
作者
Akhlaghi, Y [1 ]
Kompany-Zareh, M [1 ]
机构
[1] Inst Adv Studies Basic Sci, Zanjan 45195159, Iran
关键词
artificial neural networks; PCA; linear discriminant analysis; metal ions; spectrophotometry;
D O I
10.1016/j.aca.2004.12.079
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Copper(II) and mercury(II) were analyzed simultaneously employing a spectrophotometric method based on application of murexide solution as a chromogenic reagent. A full factorial six level design was used for the construction of calibration and prediction data sets consisting of absorption spectra recorded in 350-700 nm range from solution mixtures. A control data set, from a random design, was applied for validation of the calibration models. The presence of non-linearities was confirmed by a recently discussed methodology based on augmented partial residual plots (APaRPs). Combinations of principal component analysis (PCA) or linear discriminant analysis (LDA) with radial basis function networks (RBFNs) or feed-forward neural networks (FFNNs) were built and investigated, as four calibration models. Number of inputs and hidden nodes for each of the networks were optimized. Performances of methods were tested with relative standard error of prediction (RSEP%), using synthetic solutions of two metal ions as prediction set. Linear discriminant analysis assisted networks (LDRBNN) resulted in preferred models, using only one latent variable for each of the analytes. All of the methods were applied for the analysis of a number of synthetic samples and a dental alloy sample and satisfactory results were obtained. (c) 2005 Elsevier B.V. All rights reserved.
引用
收藏
页码:331 / 338
页数:8
相关论文
共 35 条
[1]   PRINCIPAL COMPONENT REGRESSION FOR MIXTURE RESOLUTION IN CONTROL ANALYSIS BY UV-VISIBLE SPECTROPHOTOMETRY [J].
BLANCO, M ;
COELLO, J ;
ITURRIAGA, H ;
MASPOCH, S ;
REDON, M .
APPLIED SPECTROSCOPY, 1994, 48 (01) :37-43
[2]   DATA-PROCESSING USING NEURAL NETWORKS [J].
BLANK, TB ;
BROWN, SD .
ANALYTICA CHIMICA ACTA, 1993, 277 (02) :273-287
[3]   NONLINEAR MULTIVARIATE MAPPING OF CHEMICAL-DATA USING FEEDFORWARD NEURAL NETWORKS [J].
BLANK, TB ;
BROWN, SD .
ANALYTICAL CHEMISTRY, 1993, 65 (21) :3081-3089
[4]  
BOBROV N, 1978, JU LURIE HDB ANAL CH
[5]   OPTIMAL MINIMAL NEURAL INTERPRETATION OF SPECTRA [J].
BORGGAARD, C ;
THODBERG, HH .
ANALYTICAL CHEMISTRY, 1992, 64 (05) :545-551
[6]   Detection of nonlinearity in multivariate calibration [J].
Centner, V ;
de Noord, OE ;
Massart, DL .
ANALYTICA CHIMICA ACTA, 1998, 376 (02) :153-168
[7]  
Coulomb B, 2001, QUIM ANAL, V20, P99
[8]   ROBUSTNESS ANALYSIS OF RADIAL BASE FUNCTION AND MULTILAYERED FEEDFORWARD NEURAL-NETWORK MODELS [J].
DERKS, EPPA ;
PASTOR, MSS ;
BUYDENS, LMC .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1995, 28 (01) :49-60
[9]   Variable selection for neural networks in multivariate calibration [J].
Despagne, F ;
Massart, DL .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1998, 40 (02) :145-163
[10]  
Despagne F, 1998, ANALYST, V123, p157R