On the use of counterpropagation artificial neural networks to characterize Italian rice varieties

A counterpropagation artificial neural network (CP-ANN) approach was used to classify 1779 Italian rice samples according to their variety, using physical measurements which are routinely determined for the commercial classification of the product. If compared to the classical Principal Component Analysis, the mapping based on the Kohonen network showed a significantly better representational ability, being able to separate classes which appeared quite undistinguished in the PC space. From the classification and prediction viewpoint, the optimal CP-ANN was able to correctly predict more than 90% of the test set samples.     

Predicting chain dimensions from an artificial neural network model

Artificial neural network models are used to investigate polymer chain dimensions. In our model, the input nodes are glass transition temperature (T_g), entanglement molecular weight (M_e), and melt density (ρ). The number of nodes in the hidden layer is eight. We found that the relative error for prediction of the characteristic ratio ranges from 0.77 to 7.5% and that the overall average error is 3.57%. Artificial neural network models may provide a new method for studying statistics properties of polymer chains. © 2000 John Wiley & Sons, Inc. J Polym Sci B: Polym Phys 38: 3163–3167, 2000     

Assessment of applicability domain for multivariate counter-propagation artificial neural network predictive models by minimum Euclidean distance space analysis: A case study

Alongside the validation, the concept of applicability domain (AD) is probably one of the most important aspects which determine the quality as well as reliability of the established quantitative structure–activity relationship (QSAR) models. To date, a variety of approaches for AD estimation have been devised which can be applied to particular type of QSAR models and their practical utilization is extensively elaborated in the literature. The present study introduces a novel, simple, and effective distance-based method for estimation of the AD in case of developed and validated predictive counter-propagation artificial neural network (CP ANN) models through a proficient exploitation of the Euclidean distance (ED) metric in the structure-representation vector space. The performance of the method was evaluated and explained in a case study by using a pre-built and validated CP ANN model for prediction of the transport activity of the transmembrane protein bilitranslocase for a diverse set of compounds. The method was tested on two more datasets in order to confirm its performance for evaluation of the applicability domain in CP ANN models. The chemical compounds determined as potential outliers, i.e., outside of the CP ANN model AD, were confirmed in a comparative AD assessment by using the leverage approach. Moreover, the method offers a graphical depiction of the AD for fast and simple determination of the extreme points.     

人工神经网络研究硝基苯化合物结构与毒性的关系

基于简单的化学基团描述符,应用人工神经网络研究了硝基苯类化合物对黑呆头鱼的毒性构效关系,并与多元线性回归相比较,结果显示了人工神经网络处理非线性问题的优越性.     

人工神经网络用于光度法测定工业废水中的铬和铁

为了快速测定工业废水中的铬和铁,利用BP人工神经网络模型,并与分光光度法相结合,不经分离同时测定工业废水中的铬和铁。在铬-铁-二苯碳酰二肼显色体系中,控制pH在1.0-2.0之间,用分光光度法测定显色体系的吸收光谱,应用三层人工神经网络解析吸收光谱,同时测得铬和铁的浓度。详细研究了分光光度法同时测定铬和铁的测定条件和网络训练的最佳训练参数,BP人工神经网络的动量参数为0.8,拓扑结构为20-15-2,转换函数的形状参数为0.9。该测定方法不仅可用于环境监测,而且能用于食品、材料、药物、生物样品、矿物等物质中铬和铁的测定。     

Application of different training methodologies for the development of a back propagation artificial neural network retention model in ion chromatography

The reliability of predicted separations in ion chromatography depends mainly on the accuracy of retention predictions. Any model able to improve this accuracy will yield predicted optimal separations closer to the reality. In this work artificial neural networks were used for retention modeling of void peak, fluoride, chlorite, chloride, chlorate, nitrate and sulfate. In order to increase performance characteristics of the developed model, different training methodologies were applied and discussed. Furthermore, the number of neurons in hidden layer, activation function and number of experimental data used for building the model were optimized in terms of decreasing the experimental effort without disruption of performance characteristics. This resulted in the superior predictive ability of developed retention model (average of relative error is 0.4533%). Copyright © 2008 John Wiley & Sons, Ltd.     

应用人工神经网络预测多氯代二苯骈呋喃的色谱保留指数

以量子化学方法在密度泛函B3LYP/6-31G(d)水平上计算得到了多氯代二苯骈呋喃系列化合物(PCDF)分子的结构参数:最高占据轨道能(EHOMO)、最低空轨道能(ELUMO)、最正原子净电荷(q+)、最负原子净电荷(q-)、分子偶极矩(μ)、极化率(α)、分子平均体积(Vm)、恒容热容(C■V).采用误差反向传播(BP)算法的人工神经网络,建立了EHOMO、ELUMO、q+、q-、μ、α、Vm、C■V与PCDF色谱保留指数之间关系的模型,检测样本的预报值与实验值相对误差范围为-1.66%².39%,平均相对误差为0.31%,达到了很好的预测效果.     

The solubility modelling of non-polar gases in polar and non-polar solvent based on scaled particle theory by artificial neural network

In this work, the effective parameters of the scaled particle theory (SPT) are used as the input to the artificial neural network (ANN) to calculate as the output, the solubility (mole fraction of gas in liquid phase) of non-polar gases in polar and non-polar solvents at 298.15?K and 101.325?kPa. It has been found that ANN used in this work should has five neurons in the hidden layer to achieve the least error. The results of ANN have been compared with the experimental values. The results of this comparison are quite satisfactory. The average relative deviations of the simulations in training and testing stages have been calculated 0.92% and 0.89%, respectively. Finally, the results of ANN were compared with the results of SPT. According to this comparison, it is clear that SPT as a thermodynamic model predicts the solubility of the studied gases in the solvents with the same accuracy of ANN which is a purely mathematical model.     

Hydroxyl and acid number prediction in polyester resins by near infrared spectroscopy and artificial neural networks

Back-propagation artificial neural networks (BP-ANN) are applied for modeling hydroxyl number and acid value of a set of 62 samples of polyester resins from their near infrared (NIR) spectra. The results are compared to the classical calibration approaches, i.e. principal component regression (PCR) and partial least squares (PLS). The set of available samples is split into: (i) a training set, for models calculation; (ii) a test set, for setting the correct number of latent variables in PCR and PLS and for selecting the end point of the training phase of BP-ANN; (iii) a “production set” of samples, which are predicted to evaluate the models predictive ability. This approach guarantees that the predictive ability of the models is evaluated by genuine predictions. BP-ANN resulted always better than the classical PCR and PLS, from the point of view of the predictive ability. The study of the breakdown number of experiments to include in the training set showed instead that this factor does influence PCR and PLS at a lesser degree than what happens for BP-ANN. The latter approach requires a larger number of experiments for obtaining good results. The choice of optimal training sets is efficiently performed by Kohonen self-organizing maps (SOMs). It can be concluded that FT-NIR spectroscopy and BP-ANN models can be properly employed for monitoring the polyesterification of dicarboxylic acids with diols by predicting the acid and hydroxyl numbers directly along the process line.     

一种改进BP网络结构用于化学中的非线性校正

针对化学领域中的非线性关系特点,在常规BP网络基础上,提出了一种“杂交”型BP网络,包含两个隐层,并有输入层到输出层的直连接。它可很好地解释数据中同时存在的线性及非线性关系,效果优于多元回归法及普通BP算法。     

Evaluation of a mathematical model using experimental data and artificial neural network for prediction of gas separation

In recent times, membranes have found wide applications in gas separation processes. As most of the industrial membrane separation units use hollow fiber modules, having a proper model for simulating this type of membrane module is very useful in achieving guidelines for design and characterization of membrane separation units. In this study, a model based on Coker, Freeman, and Fleming＇s study was used for estimating the required membrane area. This model could simulate a multicomponent gas mixture separation by solving the governing differential mass balance equations with numerical methods. Results of the model were validated using some binary and multicomponent experimental data from the literature. Also, the artificial neural network （ANN） technique was applied to predict membrane gas separation behavior and the results of the ANN simulation were compared with the simulation results of the model and the experimental data. Good consistency between these results shows that ANN method can be successfully used for prediction of the separation behavior after suitable training of the network     

Application of artificial neural network to evaluation of dimensional accuracy of 3D-printed polylactic acid parts

Additive manufacturing (AM) has begun to replace traditional fabrication because of its advantages, such as easy manufacturing of parts with complex geometry, and mass production. The most important limitation of AM is that dimensional accuracy cannot be achieved in all parts. Dimensional accuracy is essential for high reliability, high performance, and useful final products. This study investigates the impact of printing parameters on the dimensional accuracy of samples fabricated through fused deposition modeling (FDM), an additive manufacturing (AM) method utilizing polylactic acid (PLA) material. The experimental design process was performed using Taguchi methodology. ANOVA was used to determine the most important parameter affecting accuracy. Based on experimental studies, the optimal printing parameters for parts are determined as follows: concentric infill pattern, 3 mm wall thickness, 70% infill density, and a layer thickness of 200 μm. Artificial neural network (ANN) was used in the evaluation and prediction of the results. The R-square (R²) performance evaluation criterion was above 95% from the ANN results. This value shows that the results are significant. The data acquired from this study may assist in identifying optimal parameters that contribute to the fabrication of samples with high dimensional accuracy using the FDM method.     

Dynamic modelling of milk ultrafiltration by artificial neural network

Artificial neural networks (ANNs) have been used to dynamically model crossflow ultrafiltration of milk. It aims to predict permeate flux, total hydraulic resistance and the milk components rejection (protein, fat, lactose, ash and total solids) as a function of transmembrane pressure and processing time. Dynamic modelling of ultrafiltration performance of colloidal systems (such as milk) is very important for designing of a new process and better understanding of the present process. Such processes show complex non-linear behaviour due to unknown interactions between compounds of a colloidal system, thus the theoretical approaches were not being able to successfully model the process. In this work, emphasis has been focused on intelligent selection of training data, using few training data points and small network. Also it has been tried to test the ANN ability to predict new data that may not be originally available. Two neural network models were constructed to predict the flux/total resistance and rejection during ultrafiltration of milk. The results showed that there is an excellent agreement between the validation data (not used in training) and modelled data, with average errors less than 1%. Also the trained networks are able to accurately capture the non-linear dynamics of milk ultrafiltration even for a new condition that has not been used in the training process.