迭代目标转换因子分析与人工神经网络法用于邻、间、对硝基甲苯的分光光度同时测定的比较研究

本文将迭代目标转换因子分析与人工神经网络法用于分光光度法同时测定邻、间、对硝基甲苯,并与目标转换因子分析的结果进行了比较.结果表明,迭代目标转换因子分析法与线性网络法的效果都很好.其相对误差分别为1.3％和1.2％,而目标转换因子分析法的预测误差较大,其相对误差为10.4％.     

Homogeneous liquid-liquid microextraction via flotation assistance coupled with gas chromatography-mass spectrometry for determination of myclobutanil in cucumber,tomato, grape,and strawberry using genetic algorithm

Facile and potent homogeneous liquid–liquid microextraction via flotation assistance method (HLLME-FA) combined with gas chromatography-mass spectrometry was proposed for determination of trace amounts of myclobutanil in fruit and vegetable samples. The paramount parameters, such as extraction and homogeneous solvent types and volumes, ionic strength and extraction time were studied. Under optimum conditions, the detection limit of 0.005 ng g^?1, the linear range of 0.05–100 ng g^?1, and the precision of 3.8% were acquired. A three-layer arti?cial neural network (ANN) model was used with 10 neurons and tan-sigmoid function at hidden layer and a linear transfer function at output layer were developed to predict the process. The results indicated that the proposed ANN model could perfectly predict the process with the mean square error of 0.89%. Then genetic algorithm was utilised to optimise the parameters. The proposed procedure showed satisfactory results for analysis of cucumber, tomato, grape, and strawberry.     

EIS multianalyte sensing with an automated SIA system—An electronic tongue employing the impedimetric signal

In this work, the simultaneous quantification of three alkaline ions (potassium, sodium and ammonium) from a single impedance spectrum is presented. For this purpose, a generic ionophore - dibenzo-18-crown-6 - was used as a recognition element, entrapped into a polymeric matrix of polypyrrole generated by electropolymerization. Electrochemical impedance spectroscopy (EIS) and artificial neural networks (ANNs) were employed to obtain and process the data, respectively. In fact, EIS detected the ions exchanged between the medium and the sensing layer whereas ANNs, after an appropriated training process, could turn the impedance spectrum into concentrations values. A sequential injection analysis (SIA) system was employed for operation and to automatically generate the information required for the training of the ANN. Best results were obtained by using a backpropagation neural network made up by two hidden layers: the first one contained three neurons with the radbas transfer function and the second one ten neurons with the tansig transfer function. Three commercial fertilizers were tested employing the proposed methodology on account of the high complexity of their matrix. The experimental results were compared with reference methods.     

径向基函数神经网络荧光光度法同时测定痕量铝、镓、铟、铊

以径向基网络(RBF)对荧光光谱严重重叠的Al3 、Ga3 I、n3 、Tl3 四组分混合体系同时进行测定。通过正交设计安排样本,在激发波长390 nm下,测定446~615nm的发射光谱。以34个特征波长处的荧光强度值作为网络特征参数,经网络训练和计算得出Al3 、Ga3 、In3 、Tl3 四者的平均回收率分别为99.07%、103.49%、98.72%、95.04%,在时间和精度上都比LMBP网络优越。     

盐湖水化学类型的人工神经网络判别方法

研究了作为典型径向基函数网络之一的概率神经网络在盐湖水化学类型分类预测中的应用，验证了该方法的可靠性，得到了满意的分类预测结果。实验结果和网络结构分析表明，概率神经网络方法比熟知的反向传播算法(BP)网络要好。概率神经网络的研究应用为化学模式识别提供了一个新工具。     

Distinct Role of Mono-2-ethylhexyl Phthalate in Neuronal Transmission in Rat CA3 Hippocampal Neurons: Involvement of Ion Channels

Mono-(2-ethylhexyl) phthalate (MEHP) is one of the main active metabolites of di-(2-ethylhexyl) phthalate (DEHP). In our previous works, by using rat and Drosophila models, we showed a disruption of neural function due to DEHP. However, the exact neural effects of MEHP are still unclear. To explore the effects of MEHP on the central nervous system, the electrophysiological properties of spontaneous action potential (sAP), mini-excitatory postsynaptic currents (mEPSCs), ion channels, including Na⁺, Ca²⁺, and K⁺ channels from rat CA3 hippocampal neurons area were assessed. Our data showed that MEHP (at the concentrations of 100 or 300 μM) decreased the amplitude of sAP and the frequency of mEPSCs. Additionally, MEHP (100 or 300 μM) significantly reduced the peak current density of Ca²⁺ channels, whereas only the concentration of 300 μM decreased the peak current density of Na⁺ and K⁺ channels. Therefore, our results indicate that exposure to MEHP could affect the neuronal excitability and synaptic plasticity of rat CA3 hippocampal neurons by inhibiting ion channels’ activity, implying the distinct role of MEHP in neural transmission.     

Modeling the first stages of Cu precipitation in α-Fe using a hybrid atomistic kinetic Monte Carlo approach

We simulate the coherent stage of Cu precipitation in α-Fe with an atomistic kinetic Monte Carlo (AKMC) model. The vacancy migration energy as a function of the local chemical environment is provided on-the-fly by a neural network, trained with high precision on values calculated with the nudged elastic band method, using a suitable interatomic potential. To speed up the simulation, however, we modify the standard AKMC algorithm by treating large Cu clusters as objects, similarly to object kinetic Monte Carlo approaches. Seamless matching between the fully atomistic and the coarse-grained approach is achieved again by using a neural network, that provides all stability and mobility parameters for large Cu clusters, after training on atomistically informed results. The resulting hybrid algorithm allows long thermal annealing experiments to be simulated, within a reasonable CPU time. The results obtained are in very good agreement with several series of experimental data available from the literature, spanning over different conditions of temperature and alloy composition. We deduce from these results and relevant parametric studies that the mobility of Cu clusters containing one vacancy plays a central role in the precipitation mechanism.     

Neural network modelling of adsorption isotherms

This paper examines the possibility to use a single neural network to model and predict a wide array of standard adsorption isotherm behaviour. Series of isotherm data were generated from the four most common isotherm equations (Langmuir, Freundlich, Sips and Toth) and the data were fitted with a unique neural network structure. Results showed that a single neural network with a hidden layer having three neurons, including the bias neuron, was able to represent very accurately the adsorption isotherm data in all cases. Similarly, a neural network with four hidden neurons, including the bias, was able to predict very accurately the temperature dependency of adsorption data.     

Neural networks for Nyquist plots prediction during corrosion inhibition of a pipeline steel

This paper presents a predictive model for electrochemical impedance Nyquist plots using artificial neural network. The proposed model obtains predictions of imaginary impedance based on the real part of the impedance as a function of time. The model takes into account the variations of the real impedance and immersion time of steel in a corrosive environment, considering constant carboxyamido-imidazoline corrosion inhibitor concentrations (5 and 25 ppm). For the network, the Levenberg–Marquardt learning algorithm, the hyperbolic tangent sigmoid transfer function, and the linear transfer function were used. The best-fitting training data set was obtained with five neurons in the hidden layer for 5 ppm of inhibitor and two neurons in the hidden layer for 25 ppm of inhibitor, which made it possible to predict the efficiency with accuracy at least as good as that of the theoretical error, over the whole theoretical range. On the validation data set, simulations and theoretical data test were in good agreement with an R value of 0.984 for 5 ppm and 0.994 for 25 ppm of inhibitor. The developed model can be used for the prediction of the real and imaginary parts of the impedance as a function of time for short simulation times.     

Photocatalytic Degradation of Oxytetracycline in Aqueous Solutions with TiO2 in Suspension and Prediction by Artificial Neural Networks

In this study, the photocatalytic degradation of oxytetracycline (OTC) in aqueous solutions has been studied under different conditions such as initial pollutant concentrations, amount of catalyst, and pH of the solution. Experimental results showed that photocatalysis was clearly the predominant process in the pollutant degradation, since OTC adsorption on the catalyst and photolysis are negligible. The optimal TiO₂ concentration for OTC degradation was found to be 1.0 g/L. The apparent rate constant decreased, and the initial degradation rate increased with increasing initial OTC concentration with the other parameters kept unchanged. Subsequently, data obtained from photocatalytic degradation were used for training the artificial neural networks (ANN). The Levenberg–Marquardt algorithm, log sigmoid function in the hidden layer, and the linear activation function in the output layer were used. The optimized ANN structure was four neurons at the input layer, eighteen neurons at the hidden layer, and one neuron at the output layer. The application of 18 hidden neurons allowed to obtain the best values for R² and the mean squared error, 0.99751 and 7.504e–04, respectively, showing the relevance of the training, and hence the network can be used for final prediction of photocatalytic degradation of OTC with suspended TiO₂.     

Simultaneous kinetic-spectrophotometric determination of carbidopa, levodopa and methyldopa in the presence of citrate with the aid of multivariate calibration and artificial neural networks

The kinetic methodology based on the difference of reaction rates, is based on the reaction between a common oxidizing agents such as tris(1,10-phenanthroline) and iron(III) complex (ferriin, [Fe (phen)₃]³⁺) in the presence of citrate and spectrophotometrically, monitoring the changes of absorbance at the maximum wavelength of 511 nm. Experimental conditions such as pH, reagents and citrate concentrations were optimized, and the data obtained from the experiments were processed by several chemometric approaches, such as artificial neural network (ANN) and partial least squares (PLS). A set of synthetic mixtures of carbidopa (CD), levodopa (LD) and methyldopa (MD) was evaluated and the results obtained by the applications of these chemometric approaches were discussed and compared. It was found that the back propagation artificial neural network (BP-ANN) method afforded better precision relatively than those of radial basis function artificial neural networks (RBF-ANN) and PLS. The proposed method was also applied satisfactorily to the determination of carbidopa, levodopa and methyldopa in real samples.     

An electronic tongue using potentiometric all-solid-state PVC-membrane sensors for the simultaneous quantification of ammonium and potassium ions in water

The simultaneous determination of NH₄⁺ and K⁺ in solution has been attempted using a potentiometric sensor array and multivariate calibration. The sensors used are rather non-specific and of all-solid-state type, employing polymeric (PVC) membranes. The subsequent data processing is based on the use of a multilayer artificial neural network (ANN). This approach is given the name "electronic tongue" because it mimics the sense of taste in animals. The sensors incorporate, as recognition elements, neutral carriers belonging to the family of the ionophoric antibiotics. In this work the ANN type is optimized by studying its topology, the training algorithm, and the transfer functions. Also, different pretreatments of the starting data are evaluated. The chosen ANN is formed by 8 input neurons, 20 neurons in the hidden layer and 2 neurons in the output layer. The transfer function selected for the hidden layer was sigmoidal and linear for the output layer. It is also recommended to scale the starting data before training. A correct fit for the test data set is obtained when it is trained with the Bayesian regularization algorithm. The viability for the determination of ammonium and potassium ions in synthetic samples was evaluated; cumulative prediction errors of approximately 1% (relative values) were obtained. These results were comparable with those obtained with a generalized regression ANN as a reference algorithm. In a final application, results close to the expected values were obtained for the two considered ions, with concentrations between 0 and 40 mmol L^–1.     

Application of high-order neural networks in chemistry

Summary The effectiveness and usefulness of the so-called high-order neural networks for classification of chemical objects is demonstrated. The high-order neural networks usually do not need hidden neurons for correct interpretation of patterns. A simple formula for partial derivatives of the minimized objective (error) function is derived, which is used for production of weight coefficients during the adaptation process. An illustrative example dealing with inductive and resonance effects of functional groups by the second-order neural network is presented.     

Modeling of Osmotic Pressure of Aqueous Poly(Ethylene Glycol) Solutions Using the Artificial Neural Network and Free Volume Flory Huggins Model

In this work, the modified Flory-Huggins coupled with the free-volume concept and the artificial neural network models were used to obtain the osmotic pressure of aqueous poly(ethylene glycol) solutions. In the artificial neural network, the osmotic pressure of aqueous poly(ethylene glycol) solutions depends on temperature, molecular weight and the mole fractions of poly(ethylene glycol) in aqueous solution. The network topology is optimized and the (3-1-1) architecture is found using optimization of an objective function with batch back propagation (BBP) method for 134 experimental data points. The results obtained from the neural network in obtaining of the osmotic pressure of aqueous poly(ethylene glycol) were compared with those obtained from the free volume Flory-Huggins model (FV-FH). The results showed that the modified Flory-Huggins model and also the artificial neural network can accurately predict the osmotic pressure of aqueous poly(ethylene glycol) solutions but the accuracy of ANN is much better than the modified Flory-Huggins model.     

Transport properties of quantum-classical systems

Correlation function expressions for calculating transport coefficients for quantum-classical systems are derived. The results are obtained by starting with quantum transport coefficient expressions and replacing the quantum time evolution with quantum-classical Liouville evolution, while retaining the full quantum equilibrium structure through the spectral density function. The method provides a variety of routes for simulating transport coefficients of mixed quantum-classical systems, composed of a quantum subsystem and a classical bath, by selecting different but equivalent time evolution schemes of any operator or the spectral density. The structure of the spectral density is examined for a single harmonic oscillator where exact analytical results can be obtained. The utility of the formulation is illustrated by considering the rate constant of an activated quantum transfer process that can be described by a many-body bath reaction coordinate.