Artificial neural networks for determination of enantiomeric composition of alpha-phenylglycine using UV spectra of cyclodextrin host-guest complexes: comparison of feed-forward and radial basis function networks

In this work feed-forward neural networks and radial basis function networks were used for the determination of enantiomeric composition of alpha-phenylglycine using UV spectra of cyclodextrin host-guest complexes and the data provided by two techniques were compared. Wavelet transformation (WT) and principal component analysis (PCA) were used for data compression prior to neural network construction and their efficiencies were compared. The structures of the wavelet transformation-radial basis function networks (WT-RBFNs) and wavelet transformation-feed-forward neural networks (WT-FFNNs), were simplified by using the corresponding wavelet coefficients of three mother wavelets (Mexican hat, daubechies and symlets). Dilation parameters, number of inputs, hidden nodes, learning rate, transfer functions, number of epochs and SPREAD values were optimized. Performances of the proposed methods were tested with regard to root mean square errors of prediction (RMSE%), using synthetic solutions containing a fixed concentration of beta-cyclodextrin (beta-CD) and fixed concentration of alpha-phenylglycine (alpha-Gly) with different enantiomeric compositions. Although satisfactory results with regard to some statistical parameters were obtained for all the investigated methods but the best results were achieved by WT-RBFNs.     

Nondestructive determination of compound amoxicillin powder by NIR spectroscopy with the aid of chemometrics

Near-infrared (NIR) spectroscopy, in combination with chemometrics, enables nondestructive analysis of solid samples without time-consuming sample preparation methods. A new method for the nondestructive determination of compound amoxicillin powder drug via NIR spectroscopy combined with an improved neural network model based on principal component analysis (PCA) and radial basis function (RBF) neural networks is investigated. The PCA technique is applied to extraction relevant features from lots of spectra data in order to reduce the input variables of the RBF neural networks. Various optimum principal component analysis-radial basis function (PCA-RBF) network models based on conventional spectra and preprocessing spectra (standard normal variate (SNV) and multiplicative scatter correction (MSC)) have been established and compared. Principal component regression (PCR) and partial least squares (PLS) multivariate calibrations are also used, which are compared with PCA-RBF neural networks. Experiment results show that the proposed PCA-RBF method is more efficient than PCR and PLS multivariate calibrations. And the PCA-RBF approach with SNV preprocessing spectra is found to provide the best performance.     

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.     

Artificial neural network combined with principal component analysis for resolution of complex pharmaceutical formulations

A chemometric approach based on the combined use of the principal component analysis (PCA) and artificial neural network (ANN) was developed for the multicomponent determination of caffeine (CAF), mepyramine (MEP), phenylpropanolamine (PPA) and pheniramine (PNA) in their pharmaceutical preparations without any chemical separation. The predictive ability of the ANN method was compared with the classical linear regression method Partial Least Squares 2 (PLS2). The UV spectral data between 220 and 300 nm of a training set of sixteen quaternary mixtures were processed by PCA to reduce the dimensions of input data and eliminate the noise coming from instrumentation. Several spectral ranges and different numbers of principal components (PCs) were tested to find the PCA-ANN and PLS2 models reaching the best determination results. A two layer ANN, using the first four PCs, was used with log-sigmoid transfer function in first hidden layer and linear transfer function in output layer. Standard error of prediction (SEP) was adopted to assess the predictive accuracy of the models when subjected to external validation. PCA-ANN showed better prediction ability in the determination of PPA and PNA in synthetic samples with added excipients and pharmaceutical formulations. Since both components are characterized by low absorptivity, the better performance of PCA-ANN was ascribed to the ability in considering all non-linear information from noise or interfering excipients.     

Simultaneous determination of composition of human urinary calculi by use of artificial neural networks

A new chemometric method, which uses artificial neural networks (ANN), is presented for determination of the composition of urinary calculi. The selected constituents were whewellite, weddellite, and uric acid from which approximately 40% of the urinary calculi obtained from Macedonia patients are composed. The results for the synthetic mixtures were better then those obtained by partial least squares (PLS) regression or by the principal component regression (PCR), because neural networks have better prediction capacity. The generalization abilities of the optimized neural networks were checked using the standard addition method on carefully selected real natural samples.     

Simultaneous determination of Co, Ni, Cu and Zn ions in foodstuffs and vegetables with a new Schiff base using artificial neural networks

New complexes of Co²⁺, Ni²⁺, Cu²⁺ and Zn²⁺ with a recently synthesized Schiff base derived from 3,6-bis((aminoethyl)thio)pyridazine were applied for their simultaneous determination with artificial neural networks. The analytical data show the ratio of metal to ligand in all metal complexes is 1:1. The absorption spectra were evaluated with respect to Schiff base concentration, pH and time of the color formation reactions. It was found that at pH 10.0 and 60 min after mixing, the complexation reactions are completed and the colored complexes exhibited absorption bands in the wavelength range 300-500 nm. Spectral data was reduced using principal component analysis and subjected to artificial neural networks. The data obtained from synthetic mixtures of four metal ions were processed by principal component-feed forward neural networks (PCFFNNs) and principal component-radial basis function networks (PCRBFNs). Performances of the proposed methods were tested with regard to root mean square errors of prediction (RMSEP%), using synthetic solutions. Under the working conditions, the proposed methods were successfully applied to simultaneous determination of Co²⁺, Ni²⁺, Cu²⁺ and Zn²⁺ in different vegetable, foodstuff and pharmaceutical product samples.     

Automatic identification of terpenoid skeletons by feed-forward neural networks

Feed-forward neural networks (FFNNs) were used to predict the skeletal type of molecules belonging to six classes of terpenoids. A database that contains the ¹³C NMR spectra of about 5000 compounds was used to train the FFNNs. An efficient representation of the spectra was designed and the constitution of the best FFNN input vector format resorted from an heuristic approach. The latter was derived from general considerations on terpenoid structures.     

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.     

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.     

Calibration in non-linear NIR spectroscopy using principal component artificial neural networks

Near-infrared (NIR) spectroscopy was used in simultaneous, non-destructive analysis of antipyriine and caffeine citrate tablets. Principal component artificial neural networks (PC-ANNs) were used to construct models for the analytes, using the testing set for external validation. Four pretreated spectra, namely, first-derivative, second-derivative, standard normal variate (SNV) and multiplicative scatter correction (MSC) spectra led to simplified and more robust models than conventional spectra. In PC-ANNs models, the spectra data were analyzed by principal component analysis (PCA) firstly. Then the scores of the principal compounds (PCs) were chosen as input nodes for input layer instead of the spectra data. The artificial neural networks (ANNs) models using the spectra data as input nodes were also established, which were compared with the PC-ANNs models. The result shows the SNV model of PC-ANNs multivariate calibration has the lowest training error and predicting error. The concept of the degree of approximation was introduced and performed as the selective criterion of the optimum network parameters.     

Qualitative and quantitative investigation of chromium-polluted soils by laser-induced breakdown spectroscopy combined with neural networks analysis

Laser-induced breakdown spectroscopy (LIBS) has been applied to the analysis of three chromium-doped soils. Two chemometric techniques, principal components analysis (PCA) and neural networks analysis (NNA), were used to discriminate the soils on the basis of their LIBS spectra. An excellent rate of correct classification was achieved and a better ability of neural networks to cope with real-world, noisy spectra was demonstrated. Neural networks were then used for measuring chromium concentration in one of the soils. We performed a detailed optimization of the inputs of the network so as to improve its predictive performances and we studied the effect of the presence of matrix-specific information in the inputs examined. Finally the inputs of the network—the spectral intensities—were replaced by the line areas. This provided the best results with a prediction accuracy and precision of about 5% in the determination of chromium concentration and a significant reduction of the data, too. Awarded a poster prize on the occasion of the Euro-Mediterranean Symposium on Laser-induced Breakdown Spectroscopy (EMSLIBS 2005), Aachen, Germany, 6–9 September 2005.     

人工神经网络在纸浆卡伯值光学定量分析中的应用

卡伯值 (硬度 )是纸浆的重要质量指标 ,是制浆过程控制的关键参数 .目前的测量方法包括化学分析法和光学分析法两大类型 ,国内大多数的制浆造纸厂采用离线的传统化学分析法来测定纸浆的卡伯值 ,需要比较长的时间 .而光学分析法因具有实时性好、精度和可靠性高等优点 ,已逐步用于卡伯值的在线测量和控制 .研究 [1] 发现 ,在 460～ 580 nm的可见光谱范围内 ,蒸煮液吸光度的变化可以表征纸浆中木素含量的变化 .本文将可见分光光谱技术应用于蒸煮液中木素含量的在线测量 ,根据蒸煮液在所选波段的吸光度来预测纸浆的卡伯值 ,建立纸浆卡伯值与蒸煮…     

Quantification of butanol and ethanol in aqueous phases by reflectometric interference spectroscopy--different approaches to multivariate calibration

This paper presents several methods for analysis of data from reflectometric interference spectroscopic measurements (RIfS) of water samples. The set-up consists of three sensors with different polymer layers. Mixtures of butanol and ethanol in water were measured from 0 to 12,000 ppm each. The data space was characterized by principal component analysis (PCA). Calibration and prediction were achieved by multivariate methods, e.g. multiple linear regression (MLR), partial least squares (PLS) with additional predictors, and quadratic partial least squares (Q-PLS), and by use of artificial neural networks. Artificial neural networks gave the best results of all the calibration methods used. Calibration and prediction of the concentration of the two analytes by artificial neural nets were robust and the set-up could be reduced to only two sensors without deterioration of the prediction.     

Classification of rapeseed and soybean oils by use of unsupervised pattern-recognition methods and neural networks

Unsupervised pattern-recognition methods and Kohonen neural networks have been applied to the classification of rapeseed and soybean oil samples according to their type and quality by use of chemical and physical properties (density, refractive index, saponification value, and iodine and acid numbers) and thermal properties (thermal decomposition temperatures) as variables. A multilayer feed-forward (MLF) neural network (NN) has been used to select the most important variables for accurate classification of edible oils. To accomplish this task different neural networks architectures trained by back propagation of error method, using chemical, physical, and thermal properties as inputs, were employed. The network with the best performance and the smallest root mean squared (RMS) error was chosen. The results of MLF network sensitivity analysis enabled the identification of key properties, which were again used as variables in principal components analysis (PCA), cluster analysis (CA), and in Kohonen self-organizing feature maps (SOFM) to prove their reliability.     

水体透射光谱结合主成分分析(PCA )改进化学需氧量(COD)含量估算研究

化学需氧量（Chemical Oxygen Demand,COD）是水体有机污染的一项重要指标,化学需氧量越高,表示水污染程度越严重。 为了解决传统的COD测量方法耗时较长,不利于快速、实时地获取水体中COD的信息等问题。本文提出了基于透射光谱测量结合主成分分析(Principal Component Analysis, PCA)改进水体COD含量估算模型。具体的,采集100组COD水体光谱信息,分别使用3种不同的高光谱数据预处理方法对光谱数据进行预处理,分析不同预处理方法对模型精度的影响,并基于不同的预处理方法分别建立高斯过程回归模型(Gaussian Process Regression, GPR)和BP神经网络模型,分析不同预处理方法对模型精度的影响;并对各模型结合PCA数据降维方法进行模型的改进,通过比较模型的精度选择最优模型进行水体COD含量的检测。结果显示,相比于原始光谱数据建立的GPR模型和BP神经网络模型,数据预处理后的模型精度明显提升;且结合PCA对预处理后的数据进一步降维处理后,模型精度得到了进一步的提升。其中,基于标准正态变量变换特征结合PCA改进BP神经网络模型基于PCA改进的BP神经网络模型R^2高达0.9940,均方根误差RMSE为0.022540。证明了基于PCA改进的BP神经网络数据降维方法对预处理后的光谱数据进行降维处理,有利于去除光谱中的冗余信息,提取特征信息,可以实现高光谱检测方法可以实现COD含量估算模型的优化,从而为传统COD测量方法存在的问题提出了一种新的解决思路。     

A pilot study on colonic mucosal tissues by fluorescence spectroscopy technique: Discrimination by principal component analysis (PCA) and artificial neural network (ANN) analysis

Pulsed laser‐induced autofluorescence spectra of pathologically certified normal and malignant colonic mucosal tissues were recorded at 325 nm excitation. The spectra were analysed using three different methods for discrimination purposes. First, all the spectra were subjected to the principal component analysis (PCA) and the discrimination between normal and malignant cases were achieved using parameters like, spectral residuals, Mahalanobis distance and scores of factors. Second, to understand the changes in tissue composition between the two classes (normal, and malignant), difference spectrum was constructed by subtracting mean spectrum of calibration set samples from simulated mean of all spectra of any one class (normal/malignant) and in third, artificial neural network (ANN) analysis was carried out on the same set of spectral data by training the network with spectral features like, mean, median, spectral residual, energy, standard deviation, number of peaks for different thresholds (100, 250 and 500) after carrying out 1st‐order differentiation of the training set samples and discrimination between normal and malignant conditions were achieved. The specificity and sensitivity were determined in PCA and ANN analyses and they were found to be 100 and 91.3% in PCA, and 100 and 93.47% in ANN, respectively. Copyright © 2008 John Wiley & Sons, Ltd.     

Simultaneous determination of aniline and cyclohexylamine by principal component artificial neural networks.

A specterophotometric method for simultaneous determination of aniline and cyclohexylamine using principal component artificial neural networks is proposed. This method is based on the reactions involving aniline and/or cyclohexylamine, with bis(acetylacetoneethylendiamine)tributylphosphine cobalt(III) perchlorate as a complexing reagent. A nonionic surfactant, Triton X-100, was used for dissolving the complexes and intensifying the signals. The absorption data were based on the spectra registered in the range of 350 - 550 nm. 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. The predictive ability of artificial neural networks was examined for the determination of aniline and cyclohexylamine in synthetic mixtures.     

Real-Time Distinguishing of the Xylene Isomers Using Photoionization and Dissociation Mass Spectra Obtained by Femtosecond Laser Mass Spectrometry (FLMS)

Abstract

Distinguishing chemicals and improvement on analytical methods has a direct impact on modern chemical analysis. In this work, the dissociative ionization of xylene isomers was investigated using a femtosecond laser mass spectrometry (FLMS) method with a custom-built linear time-of-flight (TOF) instrument. Laser beams at 800?nm and 400?nm were used and intensity-dependent analysis of the obtained mass spectra was performed using principal component analysis (PCA) to distinguish the xylene isomers, which give identical mass spectra in appearance that cannot be distinguished using normal mass spectrometry methods. The results show that there is a statistically highly significant difference between the xylene isomers for two principal components (1 ? α?>?99.99%) and minimal information loss (<5%) took place during the PCA procedure. Also, the use of the k-medoid clustering method showed that the isomers may be distinguished in real-time for a wide range of ionization laser pulse powers with approximately 99% accuracy. The results suggest that real-time isomer analysis by the FLMS method is suitable for mass spectral identification applications. The FLMS method has been shown to be an important alternative to other mass spectrometric methods that use different ionization mechanisms.     

Qualitative and quantitative analysis of oxytetracycline by near-infrared spectroscopy

Near-infrared (NIR) spectroscopy, in combination with chemometrics, enable the analysis of raw materials without time-consuming sample preparation methods. The aim of our work was to estimate critical parameters in the analytical specification of oxytetracycline, and consequently the development of a method for quantification and qualification of these parameters by NIR spectroscopy. A Karl Fischer (K.F.) titration to determine the water content, a colorimetric assay method, and Fourier transform-infrared (FT-IR) spectroscopy to identify the oxytetracycline base, were used as reference methods, respectively. Multivariate calibration was performed on NIR spectral data using principal component analysis (PCA), partial least-squares (PLS 1) and principal component regression (PCR) chemometric methods. Multivariate calibration models for NIR spectroscopy have been developed. Using PCA and the Soft Independent Modelling of Class Analogy (SIMCA) approach, we established the cluster model for the determination of sample identity. PLS 1 and PCR regression methods were applied to develop the calibration models for the determination of water content and the assay of the oxytetracycline base. Comparing the PLS and PCR regression methods we found out that the PLS is better established by NIR, especially as the spectroscopic data (NIR spectra) are highly collinear and there are many wavelengths due to non-selective wavelengths. The calibration models for NIR spectroscopy are convenient alternatives to the colorimetric method and to the K.F. method, as well as to FT-IR spectroscopy, in the routine control of incoming material.     

Spectrophotometric multicomponent determination of sunset yellow, tartrazine and allura red in soft drink powder by double divisor-ratio spectra derivative, inverse least-squares and principal component regression methods

Double divisor-ratio spectra derivative (graphical method), classical least-squares and principal component regression (two numerical methods) methods were developed for the spectrophotometric multicomponent analysis of soft drink powders and synthetic mixtures containing three colorants without any chemical separation. The graphical method is based on the use of derivative signals of the ratio spectra using double divisor. In this method, the linear determination ranges were 2-8 mug ml(-1) sunset yellow, 4-18 mug ml(-1) tartrazine and 2-8 mug ml(-1) allura red in 0.1 M HCl. In the numerical methods, a training set was randomly prepared by using 18 samples containing between 0 and 8 mug ml(-1) of sunset yellow, 0-18 mug ml(-1) of tartrazine and 0-8 mug ml(-1) of allura red. The chemometric calibrations were calculated by using the prepared training set and its absorbances at seven points (from 375.0 to 550.0 nm) in the spectral region 325-584 nm. The proposed methods were validated by using synthetic ternary mixtures and applied to the simultaneous determination of three colorants in soft drink powders. The obtained results were statistically compared with each other.