Single-step calibration, prediction and real samples data acquisition for artificial neural network using a CCD camera

An artificial neural network (ANN) model is developed for simultaneous determination of Al(III) and Fe(III) in alloys by using chrome azurol S (CAS) as the chromogenic reagent and CCD camera as the detection system. All calibration, prediction and real samples data were obtained by taking a single image. Experimental conditions were established to reduce interferences and increase sensitivity and selectivity in the analysis of Al(III) and Fe(III). In this way, an artificial neural network consisting of three layers of nodes was trained by applying a back-propagation learning rule. Sigmoid transfer functions were used in the hidden and output layers to facilitate nonlinear calibration. Both Al(III) and Fe(III) can be determined in the concentration range of 0.25-4 μg ml⁻¹ with satisfactory accuracy and precision. The proposed method was also applied satisfactorily to the determination of considered metal ions in two synthetic alloys.     

Application of artificial neural networks as a technique for interference removal: kinetic-spectrophotometric determination of trace amounts of Se(IV) in the presence of Te(IV)

Artificial neural networks (ANNs) are among the most popular techniques for nonlinear multivariate calibration in complicated mixtures using spectrophotometric data. In this study we propose a computer-based method for removing Te(IV) interference in the determination of Se(IV) using artificial neural networks. In this way, an artificial neural network consisting of three layers of nodes was trained by applying a back-propagation learning rule. The resulting RMSE of prediction for selenium was obtained as 0.108.     

Artificial neural networks for simultaneous spectrophotometric differential kinetic determination of Co(II) and V(IV)

A method for simultaneous analysis of V(IV) and Co(II) has been developed by using artificial neural network (ANN). This method is based on the difference of the chemical reaction rate of V(IV) and Co(II) with Fe(III) in the presence of chromogenic reagent, 1,10-phenanthroline. The reduced product of the reaction, Fe(II), can form a colored complex with 1,10-phenanthroline and make a visible spectrophotometric signal for indirect monitoring of the V(IV) and Co(II) concentrations. Feed forward neural networks have been trained to quantify considered metal ions in mixtures under optimum conditions. The networks were shown to be capable of correlating reduced spectral kinetic data using principal component analysis (PCA) of mixtures with individual metal ion. In this way an ANN containing three layers of nodes was trained. Sigmoidal and linear transfer functions were used in the hidden and output layers, respectively, to facilitate nonlinear calibration. Both V(IV) and Co(II) were analyzed in the concentration range of 0.1-4.0 μg ml⁻¹. The proposed method was also applied satisfactorily to the determination of considered metal ions in several synthetic and water samples.     

Separation of antimony(III) with iodide and dithizone by sorption on polyurethane foam from sulphuric acid medium for its spectrophotometric determination in glasses

A method for quantitative separation of antimony(III) by sorption on polyether based polyurethane foam and its spectrophotometric determination has been described. The method involves formation of a pink-red complex of antimony(III) with iodide (0.045M) and dithizone (2.3 x 10(-5)M) in 0.25-0.75M H(2)SO(4) medium, sorption of the complex on polyurethane foam (within 45 min) at room temperature followed by its elution with acidified acetone (acetone containing 0.008% H(2)SO(4)) and spectrophotometric measurement at 507.2 nm ( = 2.56 x 10(4) l mol cm). The method obeys Beer's law from 0.1 to 6.0 mug antimony(III). Tolerance limits of other ions are Co (100 mug), Ni (100 mug), Fe (10 mug), Cu (0.5 mug), Sn (20 mug), Zn (100 mug), As (100 mug), Mn (200 mug), Pb (50 mug), Ti (100 mug), V (50 mug), etc. Interference by iron and copper have been eliminated by treating with KOH prior to the extraction of antimony. The method has been standardized with glass samples spiked with known amounts of antimony and applied to the determination of antimony in various glasses.     

Water-soluble polymers for spectrophotometric and flow injection determination of cobalt with nitroso-R-salt

The water-soluble polymers poly(ethylenimine), quaternized poly(ethylenimine), and poly-4-vinyl-(N-benzyltrimethyl) ammonium chloride were found to be able to change the kinetics of the reaction of cobalt with nitroso-R-salt and the optical density of the cobalt complex formed. The optimum pH range for the complex formation was a wide range from 1 to 10 and at pH 2 the reaction developed instantly. The calibration graph was linear in the range 0.005-2 mug ml(-1). The effective molar absorptivity coefficient of the complex was equal to (2.8+/-0.08)10(3). A spectrophotometric determination method for cobalt with nitroso-R-salt in the presence of water-soluble polymers (before and after membrane preconcentration) and a colorimetric flow injection method were developed. For the flow injection-based spectrophotometric determination, the calibration graph was linear in the concentration range of 0-4.0 mug ml(-1) cobalt with a regression coefficient of 0.9992. The relative standard deviation (R.S.D.) for the determination of 1.0 mug ml(-1) cobalt was 0.9% (ten replicate injections), and at all concentration measured, the R.S.D. of the data was below 5.0%. The proposed FI procedure was applied to river water samples after membrane preconcentration of cobalt. The limit of detection was 4 ng ml(-1).     

Simultaneous determination of iron and aluminium by differential kinetic spectrophotometric method and chemometrics

A differential kinetic spectrophotometric method was researched and developed for the simultaneous determination of iron and aluminium in food samples. It was based on the direct reaction kinetics and spectrophotometry of these two metal ions with Chrome Azurol S (CAS) in ethylenediamine-hydrochloric acid buffer (pH 6.3). The results were interpreted with the use of chemometrics. The kinetic runs and the visible spectra of the complex formation reaction were studied between 540 and 750 nm every 30 s over a total period of 285 s. A set of synthetic metal mixture samples was used to build calibrations models. These were based on the spectral and kinetic two-way data matrices, which were processed separately by the radial basis function-artificial neural network (global RBF-ANN) method. The prediction performance of these models was poorer than that from the combined kinetic-spectral three-way array, which was similarly processed by the same method (% relative prediction error (RPE_T) = 5.6). These results demonstrate that improved predictions can be obtained from the data array, which has more information, and that appropriate chemometrics methods can enhance analytical performance of simple techniques such as spectrophotometry.Other chemometrics models were then applied: N-way partial least squares (NPLS), parallel factor analysis (PARAFAC), back propagation-artificial neural network (BP-ANN), single radial basis function-artificial neural network (RBF-ANN), and principal component neural network (PC-RBF-ANN). There was no substantial difference between the methods with the overall %RPE_T range being 5.0-5.8. These two values corresponded to the NPLS and BP-ANN models, respectively. The proposed method was applied for the determination of iron and aluminium in some commercial food samples with satisfactory results.     

A kinetic spectrophotometric method for the determination of ternary mixtures of reducing sugars with the aid of artificial neural networks and multivariate calibration

A differential spectrophotometric method has been developed for the simultaneous quantitative determination of glucose (GLU), fructose (FRU) and lactose (LAC) in food samples. It relies on the different kinetic rates of the analytes in their oxidative reaction with potassium ferricyanide (K₃Fe(CN)₆) as the oxidant. The reaction data were recorded at the analytical wavelength (420 nm) of the K₃Fe(CN)₆ spectrum. Since the kinetic runs of glucose, fructose and lactose overlap seriously, the condition number was calculated for the data matrix to assist with the optimisation of the experimental conditions. Values of 80 °C and 1.5 mol l⁻¹ were selected for the temperature and concentration of sodium hydroxide (NaOH), respectively. Linear calibration graphs were obtained in the concentration range of 2.96-66.7, 3.21-67.1 and 4.66-101 mg l⁻¹ for glucose, fructose and lactose, respectively. Synthetic mixtures of the three reducing sugar were analysed, and the data obtained were processed by chemometrics methods, such as partial least square (PLS), principal component regression (PCR), classical least square (CLS), back propagation-artificial neural network (BP-ANN) and radial basis function-artificial neural network (RBF-ANN), using the normal and the first-derivative kinetic data. The results show that calibrations based on first-derivative data have advantages for the prediction of the analytes and the RBF-ANN gives the lowest prediction errors of the five chemometrics methods. Following the validation of the proposed method, it was applied for the determination of the three reducing sugars in several commercial food samples; and the standard addition method yielded satisfactory recoveries in all instances.     

Determination of trace metals in waters and compost by on-line precipitation coupled to flame atomic absorption spectrophotometry or ion chromatography

A general rapid on-line preconcentration method for the determination of trace metals coupled to flame atomic absorption spectrophotometry (FAAS) or ion chromatography (IC) with spectrophotometric detection is described. The method is based on the on-line precipitation of metal hydroxides with sodium hydroxide and their dissolution in a small volume of nitric acid solution. All the chemical and physical variables that affect the efficiency of metal precipitation and elution in the flow injection system have been studied. The detection limits obtained by FAAS are 0.1, 0.3, 0.5 and 0.5 mug l(-1) for Zn, Cu, Ni and Pb, respectively. When the on-line precipitation is coupled to IC with post-column derivatization with the spectrophotometric reagent 4-(2-pyridylazo) resorcinol (PAR), the detection limits are 3, 1, 5, 3, and 3 mug l(-1) for Cu, Zn, Ni, Co and Mn, respectively. The proposed general method was successfully applied to determine independently the above mentioned metals in compost and tap and river water samples.     

Principal Component‐Wavelet Neural Network as a Multivariate Calibration Method for Simultaneous Determination of Iron,Nickel, and Cobalt

Abstract

Principal component‐artificial neural network (PC‐ANN) and principal component‐wavelet neural network (PC‐WNN) are applied for simultaneous determination of iron(II), nickel(II), and cobalt(II). A simple and selective spectrophotometric method for simultaneous determination of iron(II), nickel(II), and cobalt(II) based on formation of their complexes with 1‐(2‐pyridylazo)‐2‐naphtol (PAN) in micellar media is described. Although the complexes of Fe(II), Ni(II), and Co(II) with reagent show a spectral overlap, they have been simultaneously determined by PC‐ANN and PC‐WNN. The results obtained by the two methods were compared and it was shown that in PC‐WNN, the convergence speed was faster and the root mean square error of prediction set was also smaller than PC‐ANN. Interference effects of common anions and cations were studied and the proposed method was also applied satisfactorily to the determination of Fe(II), Ni(II) and Co(II) in synthetic samples.     

Spectrophotometric determination of metal ions in electroplating solutions in the presence of EDTA with the aid of multivariate calibration and artificial neural networks

Metal ions such as Co(II), Ni(II), Cu(II), Fe(III) and Cr(III), which are commonly present in electroplating baths at high concentrations, were analysed simultaneously by a spectrophotometric method modified by the inclusion of the ethylenediaminetetraacetate (EDTA) solution as a chromogenic reagent. The prediction of the metal ion concentrations was facilitated by the use of an orthogonal array design to build a calibration data set consisting of absorption spectra collected in the 370-760 nm range from solution mixtures containing the five metal ions earlier. With the aid of this data set, calibration models were built based on 10 different chemometrics methods such as classical least squares (CLS), principal component regression (PCR), partial least squares (PLS), artificial neural networks (ANN) and others. These were tested with the use of a validation data set constructed from synthetic solutions of the five metal ions. The analytical performance of these chemometrics methods were characterized by relative prediction errors and recoveries (%). On the basis of these results, the computational methods were ranked according to their performances using the multi-criteria decision making procedures preference ranking organization method for enrichment evaluation (PROMETHEE) and geometrical analysis for interactive aid (GAIA). PLS and PCR models applied to the spectral data matrix that used the first derivative pre-treatment were the preferred methods. They together with ANN-radial basis function (RBF) and PLS were applied for analysis of results from some typical industrial samples analysed by the EDTA-spectrophotometric method described. DPLS, DPCR and the ANN-RBF chemometrics methods performed particularly well especially when compared with some target values provided by industry.     

Simultaneous determination of cobalt, nickel and palladium in micellar media using partial least square regression and direct orthogonal signal correction

A simple, novel and sensitive spectrophotometric method was described for the simultaneous determination of cobalt, nickel and palladium. The method is based on the complex formation of Co, Ni and Pd with 1-(2-pyridylazo)-2-naphtol (PAN) in Tween-80 micellar media. All factors affecting on the sensitivity were optimized and the linear dynamic range for determination of Co, Ni and Pd was found. The experimental calibration matrix was designed by measuring the absorbance over the range of 520-700 nm for 21 samples of 0.10-1.0, 0.050-0.50 and 0.050-4.0 microg ml(-1) of Co, Ni and Pd, respectively. The partial least square (PLS) modeling based on singular value decomposition (SVD) was used for the multivariate calibration of the spectrophotometric data. The direct orthogonal signal correction was used for pre-processing of data matrices and the prediction results of model, with and without using direct orthogonal signal correction, were statistically compared. The effects of various anions and cations on selectivity of the method were investigated. The proposed method was successfully applied to the determination of Co, Ni and Pd in water and alloy samples.     

Simultaneous determination of thiocyanate and salicylate by a combined UV-spectrophotometric detection principal component artificial neural network

A modified principle component artificial neural network (PC-ANN) model is developed for simultaneous determination of thiocyanate and salycilate concentration after passing through the bulk of a liquid membrane by tri-phenyl benzyl phosphonium chloride. All calibration, and test samples data were obtained using UV-Vis spectrophotometer. In this way, a modified PC-ANN consisting of three layers of nodes was trained by combination of Bayesian-Levenberg-Marquardt as training rule. Sigmoid and liner transfer functions were used in the hidden and output layers respectively to facilitate nonlinear calibration. The model could accurately estimate the concentration of components with acceptable precision and accuracy, for mixtures. The PC-ANN model exhibits a good ability for the simultaneous determination of the thiocyanate and salycilate in concentration range 0.5 x 10(-4) mol.l(-1) up to 5.0 x 10(-4) mol.l(-1) with Root Mean square error (2.22% and 2.20%, for thiocyanate and salycilate, respectively) and high correlation coefficients (R2= 0.998 or greater). Results obtained with modified trained PC-ANN were compared with stepwise linear regression (SMLR) model. Validation of the two models shows a better ability in estimation of the modified PC-ANN as compared with the SMLR model (MSRE given are 3.12%, 6.31%.).     

Separation and determination of metallocyanide complexes of Fe(II), Ni(II) and Co(III) by ion-interaction chromatography with membrane suppressed conductivity detection applied to analysis of oil refinery streams (sour water)

A separation and determination method for the analysis of cyanometallic complexes of Fe(II), Ni(II) and Co(III) was developed to be applied to the analysis of petroleum refinery streams (sour water). Ion-interaction chromatography was used employing an analytical column IonPac NS1 10 microm and a chromatographic system ICS 2500 equipped with a membrane conductivity suppression ASRS ultra 4mm, both supplied by Dionex Corporation. The mobile phase was composed of 2 mmol l(-1) TBAOH, 1 mmol l(-1) Na(2)CO(3), 0.1 mol l(-1) NaCN and ACN (77:23, v/v), flowing at 0.7 ml min(-1). At the optimized conditions, detection limits estimated by the calibration curve parameters and relative standard deviation were: 0.002 mg CNl(-1) and 3.1% for Fe(CN)(6)(4-); 0.003 mg CNl(-1) and 2.5% for Ni(CN)(4)(2-) and 0.003 mg CNl(-1) and 2.8% for Co(CN)(6)(3-). Sour water samples without any pretreatment (except membrane filtration) from a petroleum refinery in Brazil were analyzed successfully by external calibration method.     

人工神经网络光度法同时测定土壤中铅-镉-镍

研究了以4－（2－吡啶偶氮）－间苯二酚（PAR）为显色剂、十二烷基硫酸钠（SDS）为增敏剂、乙酸－乙酸钠为缓冲液，在水相中对铅、镉、镍进行同时测定。利用二次回归正交组合设计，对体系因子进行了优化。以苏州吴县水稻田土壤为研究对象，利用反向人工神经网络对其中铅、镉、镍的全量、有效态、活化态分别进行了同时测定，预测结果与AAS法所测结果基本一致。     

Simultaneous determination of manganese and zinc in mixtures using first- and second-derivative spectrophotometry

A new direct spectrophotometric determination of manganese with 5,8-dihydroxy-1,4-naphthoquinone (naphthazarin,NAZA) is reported. Absorption maximum, molar absorptivity and Sandell's sensitivity of 1:2 (M:L) complex are 695 nm, 1.88x10(4) l mol(-1) cm(-1) and 2.92 ng cm(-2), respectively. A linear calibration graph is obtained up to a concentration of 7.2 mug ml(-1) of manganese. The optimum range for determination (Ringbom) is between 0.20 and 6.8 mug ml(-1). A rapid method for simultaneous determination of manganese and zinc in their mixture using derivative spectra is described. The range 0.28-5.6 mug ml(-1) manganese could be determined in the presence of 0.33-6.8 mug ml(-1) zinc and vice versa. The developed method was applied to the simultaneous spectrophotometric determination of manganese and zinc in some synthetic mixtures and was found to give satisfactory results.     

Determination of Cd in sonicate slurries and leachates of biological and environmental materials by FI-CV-AAS

An analytical method for Cd analysis in solid samples which combines the ultrasonic slurry formation with cold vapour generation and atomic absorption spectrometry is described. The samples are suspended in HCl and sonicated until homogeneous and reduced particle size slurry formation. Several aspects were studied: acidity of the medium, sonication time, and slurry formation in different matrices. The procedure described permits the use of direct calibration, with KCN addition as masking agent of interfering ions (Cu, Pb, Ni and Zn) present in the environmental matrices. Supernatant analysis of these last samples experimentally shown that preparation of the suspension with 6 mol l(-1) HCl concentration led to quantitative extraction of Cd. Biological materials analysis needed the use of the standard addition calibration method due to the high matrix effect observed. Supernatant analysis in biological samples does not give a total Cd recovery for all of them. The detection limits observed for Cd were 0.05 and 0.2 mug l(-1) for supernatant and slurry analysis respectively in environmental samples, while in biological samples were 0.2 and 0.6 mug l(-1) for supernatant and slurry analysis, respectively. In all case the better precision was obtained for supernatant analysis (3-6%) than slurry analysis (6-12%). The results obtained by analysing different reference materials (sewage sludge, city waste incineration, Antarctic krill and human hair) showed good agreement with the certified value confirming the validity of such a method for Cd determination instead to wet digestion procedures.     

Determination of nickel by anodic adsorptive stripping voltammetry with a cation exchanger-modified carbon paste electrode

The behavior of a modified carbon paste electrode (CPE) for nickel determination by anodic adsorptive stripping voltammetry (AAdsSV) was studied. The electrode was built incorporating the Dowex 50W x 12 (H(+) form) ion exchanger to a Nujol-graphite base paste. Ni(2+) was preconcentrated on the electrode surface in open circuit conditions, with the reduction (-1300 mV)/reoxidation step carried out in HCl solution (pH 3). During deposition time (5 min), the hydrogen evolution did not present obstacle in the quantification of nickel. For 12 min of accumulation and 5 min of deposition, nickel can be quantified up to 600 mug l(-1). The detection limit was 0.005 mug l(-1) at a linear potential scan rate of 200 mV s(-1). Interferences from Hg(2+) and Ag(2+) up to a concentration of 1 and 0.6 mg l(-1), respectively, were eliminated with the aid of the anion exchanger Dowex-2 (mesh 200-400) which was added to the sample in the preconcentration step. The tolerance for some metal ions such as Cu(2+), Cd(2+), Fe(3+), Zn(2+), Co(2+) and Pb(2+) was improved in the same way. The method was applied for the determination of nickel in samples of tap and mineral water. At the concentration level of 50 mug l(-1) of Ni (2+), the results were in good agreement with those obtained using Inductively Coupled Plasma Atomic Emission Spectrometry (ICP-AES). For a Ni(2+) concentration of 5 mug l(-1), the results obtained showed better accuracy than those obtained by ICP-AES.     

Separation and preconcentration of iron(II) and iron(III) from natural water on a melamine-formaldehyde resin

A combined method for the preconcentration and selective spectrophotometric determination of both valencies of iron, i.e., Fe(II) and Fe(III), down to 0.4 mug l(-1) has been developed. Iron(III) from synthetic and natural water samples has been concentrated on a melamine-formaldehyde resin at pH 5; iron(II) was not retained under identical conditions. The oxidized iron was concentrated on a second resin column. The iron in both columns was eluted with 1 M HCl solution and separately analyzed by the 1,10-phenanthroline-citrate spectrophotometric method. The effect of pH, adsorption and elution rates, and interferences on the developed procedure were investigated. Metal ions that can be retained by the resin at moderate concentrations, e.g., Al(3+), do not cause interference in more dilute solutions encountered in natural water samples. At least 160-fold volume enrichment can be easily obtained using an adsorption flowrate of 50 ml min(-1). A hydrothermal water sample was analyzed by the recommended procedure and by a literature method, and the results were statistically compared by t- and F-tests.     

Cloud point extraction, preconcentration and simultaneous spectrophotometric determination of nickel and cobalt in water samples

Cloud point extraction has been used for the preconcentration and simultaneous spectrophotometric determination of nickel and cobalt after the formation of a complex with 2-amino-cyclopentene-1-dithiocarboxylic acid (ACDA), and latter analysis by spectrophotometer using Triton X-114 as surfactant. The parameters affecting the separation phase and detection process were optimized. Under the optimum experimental conditions (i.e. pH=5, 0.07 mM ACDA, Triton X-114=0.25% (w/v)), calibration graphs were linear in the range of 20-500 and 20-200 microg l(-1) with detection limits of 10 and 7.5 microg l(-1) for Ni and Co, respectively. The method was applied to the determination of Ni and Co in natural and waste water samples with satisfactory results.