Artificial neural network for on-site quantitative analysis of soils using laser induced breakdown spectroscopy

Nowadays, due to environmental concerns, fast on-site quantitative analyses of soils are required. Laser induced breakdown spectroscopy is a serious candidate to address this challenge and is especially well suited for multi-elemental analysis of heavy metals. However, saturation and matrix effects prevent from a simple treatment of the LIBS data, namely through a regular calibration curve. This paper details the limits of this approach and consequently emphasizes the advantage of using artificial neural networks well suited for non-linear and multi-variate calibration. This advanced method of data analysis is evaluated in the case of real soil samples and on-site LIBS measurements. The selection of the LIBS data as input data of the network is particularly detailed and finally, resulting errors of prediction lower than 20% for aluminum, calcium, copper and iron demonstrate the good efficiency of the artificial neural networks for on-site quantitative LIBS of soils.     

Estimation of Average Comonomer Content of Ethylene/1-Olefin Copolymers Using Crystallization Analysis Fractionation (Crystaf) and Artificial Neural Network (ANN)

Summary: An artificial neural network (ANN) with a 4-3-3-1 architecture was developed to estimate average comonomer content of ethylene/1-olefin copolymers from crystallization analysis fractionation (Crystaf) results. The ANN was trained with a back propagation algorithm. It was found that average comonomer contents predicted from ANN agree well with experimental results for both training and testing data sets. The developed ANN was also used to systematically investigate the effects of chain microstructures and Crystaf operating conditions on Crystaf calibration curves.     

Artificial neural network for Cu quantitative determination in soil using a portable Laser Induced Breakdown Spectroscopy system

Laser Induced Breakdown Spectroscopy (LIBS) is an advanced analytical technique for elemental determination based on direct measurement of optical emission of excited species on a laser induced plasma. In the realm of elemental analysis, LIBS has great potential to accomplish direct analysis independently of physical sample state (solid, liquid or gas). Presently, LIBS has been easily employed for qualitative analysis, nevertheless, in order to perform quantitative analysis, some effort is still required since calibration represents a difficult issue. Artificial neural network (ANN) is a machine learning paradigm inspired on biological nervous systems. Recently, ANNs have been used in many applications and its classification and prediction capabilities are especially useful for spectral analysis. In this paper an ANN was used as calibration strategy for LIBS, aiming Cu determination in soil samples. Spectra of 59 samples from a heterogenic set of reference soil samples and their respective Cu concentration were used for calibration and validation. Simple linear regression (SLR) and wrapper approach were the two strategies employed to select a set of wavelengths for ANN learning. Cross validation was applied, following ANN training, for verification of prediction accuracy. The ANN showed good efficiency for Cu predictions although the features of portable instrumentation employed. The proposed method presented a limit of detection (LOD) of 2.3 mg dm^− 3 of Cu and a mean squared error (MSE) of 0.5 for the predictions.     

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.     

Comparison of Artificial Neural Networks with Partial Least Squares Regression for Simultaneous Determinations by ICP-AES

Simultaneous determination of several elements （U, Ta, Mn, Zr and W） with inductively coupled plasma atomic emission spectrometry （ICP-AES） in the presence of spectral interference was performed using chemometrics methods. True comparison between artificial neural network （ANN） and partial least squares regression （PLS） for simultaneous determination in different degrees of overlap was investigated. The emission spectra were recorded at uranium analytical line （263.553 nm） with a 0.06 nm spectral window by ICP-AES. Principal component analysis was applied to data and scores on 5 dominant principal components were subjected to ANN. A 5-5-5 （input, hidden and output neurons） network was used with linear transfer function after both hidden and output layers. The PI,S model was trained with five latent variables and 20 samples in calibration set. The relative errors of predictions （REP） in test set were 3.75% and 3.56% for ANN and PLS respectively.     

The prediction of total anthocyanin concentration in red-grape homogenates using visible-near-infrared spectroscopy and artificial neural networks

This study compares the performance of partial least squares (PLS) regression analysis and artificial neural networks (ANN) for the prediction of total anthocyanin concentration in red-grape homogenates from their visible-near-infrared (Vis-NIR) spectra. The PLS prediction of anthocyanin concentrations for new-season samples from Vis-NIR spectra was characterised by regression non-linearity and prediction bias. In practice, this usually requires the inclusion of some samples from the new vintage to improve the prediction. The use of WinISI LOCAL partly alleviated these problems but still resulted in increased error at high and low extremes of the anthocyanin concentration range. Artificial neural networks regression was investigated as an alternative method to PLS, due to the inherent advantages of ANN for modelling non-linear systems. The method proposed here combines the advantages of the data reduction capabilities of PLS regression with the non-linear modelling capabilities of ANN. With the use of PLS scores as inputs for ANN regression, the model was shown to be quicker and easier to train than using raw full-spectrum data. The ANN calibration for prediction of new vintage grape data, using PLS scores as inputs, was more linear and accurate than global and LOCAL PLS models and appears to reduce the need for refreshing the calibration with new-season samples. ANN with PLS scores required fewer inputs and was less prone to overfitting than using PCA scores. A variation of the ANN method, using carefully selected spectral frequencies as inputs, resulted in prediction accuracy comparable to those using PLS scores but, as for PCA inputs, was also prone to overfitting with redundant wavelengths.     

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.     

An expeditious method for determining particle size distribution by near infrared spectroscopy: Comparison of PLS2 and ANN models

The particle size distribution of a solid product can be crucial parameter considering its application to different kinds of processes. The influence of particle size on near infrared (NIR) spectra has been used to develop effective alternative methods to traditional ones in order to determine this parameter. In this work, we used the chemometrical techniques partial least squares 2 (PLS2) and artificial neural networks (ANNs) to simultaneously predict several variables to the rapid construction of particle size distribution curves. The PLS2 algorithm relies on linear relations between variables, while the ANN technique can model non-linear systems.Samples were passed through sieves of different sieve opening in order to separate several size fractions that were used to construct two types of particle size distribution curves. The samples were recorded by NIR and their spectra were used with PLS2 and ANN to develop two calibration models for each. The correlation coefficients and relative standard errors of prediction (RSEP) have been used to assess the goodness of fit and accuracy of the results.The four calibration models studied provided statistically identical results based on RSEP values. Therefore, the combined use of NIR spectroscopy and PLS2 or ANN calibration models allows determining the particle size distributions accurately. The results obtained by ANN or PLS2 are statistically similar.     

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.     

Multicomponent acid-base titration by principal component-artificial neural network calibration

In this study, a three-layered feed-forward artificial neural network (ANN) trained by back-propagation learning was used to model the complex non-linear relationship between the concentration of anthranilic acid (HA), nicotinic acid (HN), picolinic acid (HP) and sulfanilic acid (HS) in their quaternary mixtures and the pH of solutions at different volumes of the added titrant. The principal components of the pH matrix were used as the input of the network. The network architecture and parameters were optimized to give low prediction error. The optimized networks predicted the concentrations of acids in synthetic mixtures. The results showed that the ANN used can proceed the titration data with low percent relative error of prediction (i.e.<4%). A comparison between the ANN and PLS methods revealed the superiority of the results obtained by the former method.     

Evaluation of laser induced breakdown spectroscopy for multielemental determination in soils under sewage sludge application

Laser induced breakdown spectroscopy (LIBS) is an atomic emission spectroscopy technique for simple, direct and clean analysis, with great application potential in environmental sustainability studies. In a single LIBS spectrum it is possible to obtain qualitative information on the sample composition. However, quantitative analysis requires a reliable model for analytical calibration. Multilayer perceptron (MLP), an artificial neural network, is a multivariate technique that is capable of learning to recognize features from examples. Therefore MLP can be used as a calibration model for analytical determinations. Accordingly, the present study proposes to evaluate the traditional linear fit and MLP models for LIBS calibration, in order to attain a quantitative multielemental method for contaminant determination in soil under sewage sludge application. Two sets of samples, both composed of two kinds of soils were used for calibration and validation, respectively. The analyte concentrations in these samples, used as reference, were determined by a reference analytical method using inductively coupled plasma optical emission spectrometry (ICP OES). The LIBS-MLP was compared to a LIBS-linear fit method. The values determined by LIBS-MLP showed lower prediction errors, correlation above 98% with values determined by ICP OES, higher accuracy and precision, lower limits of detection and great application potential in the analysis of different kinds of soils.     

Differential Kinetic Spectrophotometric Determination of Methamidophos and Fenitrothion in Water and Food Samples by Use of Chemometrics

A spectrophotometric method for simultaneous analysis of methamidophos and fenitrothion was proposed by application of chemometrics to the spectral kinetic data, which was based upon the difference in the inhibitory effect of the two pesticides on acetylcholinesterase (AChE) and the use of 5,5′‐dithiobis(2‐nitrobenzoic acid) (DTNB) as a chromogenic reagent for the thiocholine iodide (TChI) released from the acetylthiocholine iodide (ATChI) substrate. The absorbance of the chromogenic product was measured at 412 nm. The different experimental conditions affecting the development and stability of the chromogenic product were carefully studied and optimized. Linear calibration graphs were obtained in the concentration range of 0.5–7.5 ng·mL^?1 and 5–75 ng·mL^?1 for methamidophos and fenitrothion, respectively. Synthetic mixtures of the two pesticides were analysed, and the data obtained processed by chemometrics, such as partial least square (PLS), principal component regression (PCR), back propagation‐artificial neural network (BP‐ANN), radial basis function‐artificial neural network (RBF‐ANN) and principal component‐radial basis function‐artificial neural network (PC‐RBF‐ANN). The results show that the RBF‐ANN gives the lowest prediction errors of the five chemometric methods. Following the validation of the proposed method, it was applied to the determination of the pesticides in several commercial fruit and vegetable samples; and the standard addition method yielded satisfactory recoveries.     

Resolution of overlapping capillary electrophoresis peaks by using chemometric analysis: quantification of the components in compound reserpine tablets

The application of multivariate curve resolution with alternating least squares (MCR-ALS) methods to second-order data from capillary electrophoresis with diode array detector (CE-DAD) is reported. Initial qualitative solutions obtained by evolving factor analysis (EFA) and pure-variable detection method can be further optimized by a simultaneous analysis of multiple electrophoresis run data with ALS regression. While unknown samples are analyzed simultaneously against the corresponding standards in different composition ratios, the exact amounts of common components in different CE runs can be determined by the traditional calibration curve method, and quantification can thus be achieved. The above methods are applied to the determination of the components in compound reserpine tablets in overlapping peaks from CE. The quantification results are compared with those of the first derivative of the electropherogram method and artificial neural network (ANN) method.     

Simultaneous spectrophotometric determination of Fe and Ni with xylenol orange using principal component analysis and artificial neural networks in some industrial samples

Artificial neural networks (ANNs) are among the most popular techniques for nonlinear multivariate calibration in complicated mixtures using spectrophotometric data. In this study, Fe and Ni were simultaneously determined in aqueous medium with xylenol orange (XO) at pH 4.0. In this way, after reducing the number of spectral data using principal component analysis (PCA), 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. Adjustable experimental and network parameters were optimized, 30 calibration and 20 prediction samples were prepared over the concentration ranges of 0-400 mug l(-1) Fe and 0-300 mug l(-1) Ni. The resulting R.S.E. of prediction (S.E.P.) of 3.8 and 4.7% for Fe and Ni were obtained, respectively. The method has been applied to the spectrophotometric determination of Fe and Ni in synthetic samples, some Ni alloys, and some industrial waste waters.     

神经网络方法在血管紧张素转换酶抑制剂定量构效关系建模中的应用

对20个ACEI化合物用量子化学方法进行结构优化并计算出10个参数,用9种不同隐含层节点数的BP神经网络研究了ACEI的定量构效关系,建立了节点为10/6/1的三层BP神经网络模型。结果表明:以量化理论计算所得参数可以构建合理的ACEI定量构效关系模型,神经网络模型M6的r2=0.995,S=0.050,6个验证集化合物的残差平方和为0.002,预测能力明显强于多元线形回归模型,亦优于同类文献报道,可作为ACEI研发领域中预测先导化合物活性的理论工具。     

Artificial neural network for simultaneous determination of two components of compound paracetamol and diphenhydramine hydrochloride powder on NIR spectroscopy

Diffuse reflectance near-infrared (NIR) spectroscopy is a technique widely used for rapid and non-destructive analysis of solid samples. A method for simultaneous analysis of the two components of compound paracetamol and diphenhydramine hydrochloride powdered drug has been developed by using artificial neural network (ANN) on near-infrared (NIR) spectroscopy. An ANN containing three layers of nodes was trained. Various ANN models based on pretreated spectra (first-derivative, second-derivative and standard normal variate; SNV) were tested and compared, respectively. In the models the concentration of paracetamol and caffeine as active principles of compound paracetamol and diphenhydramine hydrochloride powder was determined simultaneously. Partial least squares regression (PLS) multivariate calibrations were also used, which were compared with ANN. The best model was obtained at first-derivative spectra. We have also discussed the parameters that affected the networks and predicted the test set (unknown) specimens. The degree of approximation, a new evaluation criteria of the network were employed, which proved the accuracy of the predicted results.     

Usage of Artificial Neural Network (Back Propagation) in Optimising Salicylic Acid Determination with Ferric(III) Nitrate

Abstract

The use of artificial neural networks (ANN) in optimizing salicylic acid (SA) determination is presented in this paper. A simple and rapid spectrophotometric method for salicylic acid (SA) determination was carried out based on the complexation of salicylic acid–ferric(III) nitrate, SAFe(III). The SA forms a stable purple complex with ferric(III) nitrate at pH 2.45. The useful dynamic linear range is 0.01–0.35 g/L. It has a maximum absorption at 524 nm and the stability is more than 50 hours. The results were used for artificial neural networks (ANNs) training to optimize data. For training and validation purposes, a back‐propagation (BP) artificial neural network (ANN) was used. The results showed that ANN technique was very effective and useful in broadening the limited dynamic linear response range mentioned to an extensive calibration response (0.01–0.70 g/L). It was found that a network with 22 hidden neurons was highly accurate in predicting the determination of SA. This network scores a summation of squared error (SSE) skill and low average predicted error of 0.0078 and 0.00427 g/L, respectively.     

Extending the working calibration ranges of four hexachlorocyclohexane isomers in gas chromatography-electron capture detector by radial basis function neural network

A radial basis function neural network (RBFNN) method was developed for the first time to model the nonlinear calibration curves of four hexachlorocyclohexane (HCH) isomers, aiming to extend their working calibration ranges in gas chromatography-electron capture detector (GC-ECD). Other 14 methods, including seven parametric curve fitting methods, two nonparametric curve fitting methods, and five other artificial neural network (ANN) methods, were also developed and compared. Only the RBFNN method, with logarithm-transform and normalization operation on the calibration data, was able to model the nonlinear calibration curves of the four HCH isomers adequately. The RBFNN method accurately predicted the concentrations of HCH isomers within and out of the linear ranges in certified test samples. Furthermore, no significant difference (p > 0.05) was found between the results of HCH isomers concentrations in water samples calculated with RBFNN method and ordinary least squares (OLS) method (R² > 0.9990). Conclusively, the working calibration ranges of the four HCH isomers were extended from 0.08-60 ng/ml to 0.08-1000 ng/ml without sacrificing accuracy and precision by means of RBFNN. The outstanding nonlinear modeling capability of RBFNN, along with its universal applicability to various problems as a “soft” modeling method, should make the method an appealing alternative to traditional modeling methods in the calibration analyses of various systems besides the GC-ECD.     

Nondestructive Quantitative Analysis of Analgini Powder Pharmaceutical by Near-Infrared Spectroscopy and Artifical Neural Network Technique

ABSTRACT

This paper demonstrates the usefulness of near-infrared (NIR) spectra and artificial neural network (ANN) in nondestructive quantitative analysis of pharmaceuticals. Real data sets from near-infrared reflectance spectra of analgini powder pharmaceutical were used to build up an artificial neural network to predict unknown samples. The parameters affecting the network were discussed. A new network evaluation criterion, the degree of approximation, was employed. The overfitting was discussed. Owing to the good nonlinear multivariate calibration nature of ANN, the predicted result was reliable and precise. The relative error of unknown samples was less than 2.5%     

Application of artificial neural networks to the determination of pesticides by linear sweep stripping voltammetry

In this work, artificial neural network (ANN), a powerful chemometrics approach for linear and nonlinear calibration models, was applied to detect three pesticides in mixtures by linear sweep stripping voltammetry (LSSV) despite their overlapped voltammograms. Electrochemical parameters for the voltammetry, such as scan rate, deposit time and deposit potential, were evaluated and optimized from the signal response data using ANN model by minimizing the relative prediction error (RPE). The proposed method was successfully applied to the detection of pesticides in synthetic samples and several commercial fruit samples.