Globally flexible functional forms: The neural distance function

The output distance function is a key concept in economics. However, its empirical estimation often violates properties dictated by neoclassical production theory. In this paper, we introduce the neural distance function (NDF) which constitutes a global approximation to any arbitrary production technology with multiple outputs given by a neural network (NN) specification. The NDF imposes all theoretical properties such as monotonicity, curvature and homogeneity, for all economically admissible values of outputs and inputs. Fitted to a large data set for all US commercial banks (1989–2000), the NDF explains a very high proportion of the variance of output while keeping the number of parameters to a minimum and satisfying the relevant theoretical properties. All measures such as total factor productivity (TFP) and technical efficiency (TE) are computed routinely. Next, the NDF is compared with the Translog popular specification and is found to provide very satisfactory results as it possesses the properties thought as desirable in neoclassical production theory in a way not matched by its competing specification.     

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%     

Ultrasound-assisted extraction of phenolics from wine lees: Modeling,optimization and stability of extracts during storage

The ultrasound-assisted extraction process of phenolics including anthocyanins from wine lees was modeled and optimized in this research. An ultrasound bath system with the frequency of 40 kHz was used and the acoustic energy density during extraction was identified to 48 W/L. The effects of extraction time, extraction temperature, solvent-to-solid ratio and the solvent composition on the extraction yields of total phenolics and total anthocyanins were taken into account. The extraction process was simulated and optimized by means of artificial neural network (ANN) and genetic algorithm (GA). The constructed ANN models were accurate to predict the extraction yields of both total phenolics and total anthocyanins according to the statistical analysis. Meanwhile, the input space of the ANN models was optimized by GA, so as to maximize the extraction yields. Under the optimal conditions, the experimental yields of total phenolics and total anthocyanins were 58.76 and 6.69 mg/g, respectively, which agreed with the predicted values. Furthermore, more amounts of total phenolics and total anthocyanins were extracted by ultrasound at the optimal conditions than by conventional maceration.On the other hand, the stability of phenolics in the liquid extracts obtained from ultrasound-assisted extraction during storage was evaluated. After 30-day storage, the total phenolic contents in extracts stored at 4 °C and 20 °C decreased by 12.5% and 12.1%, respectively. Moreover, anthocyanins were more stable at 4 °C while tartaric esters and flavonols exhibited a better stability at 20 °C. Overall, the loss of phenolics during storage found in this study could be acceptable.     

Multi-step prediction of time series with random missing data

Multi-step prediction is still an open challenge in time series prediction. Moreover, practical observations are often incomplete because of sensor failure or outliers causing missing data. Therefore, it is very important to carry out research on multi-step prediction of time series with random missing data. Based on nonlinear filters and multilayer perceptron artificial neural networks (ANNs), one novel approach for multi-step prediction of time series with random missing data is proposed in the study. With the basis of original nonlinear filters which do not consider the missing data, first we obtain the generalized nonlinear filters by using a sequence of independent Bernoulli random variables to model random interruptions. Then the multi-step prediction model of time series with random missing data, which can be fit for the online training of generalized nonlinear filters, is established by using the ANN’s weights to present the state vector and the ANN’s outputs to present the observation equation. The performance between the original nonlinear filters based ANN model for multi-step prediction of time series with missing data and the generalized nonlinear filters based ANN model for multi-step prediction of time series with missing data is compared. Numerical results have demonstrated that the generalized nonlinear filters based ANN are proportionally superior to the original nonlinear filters based ANN for multi-step prediction of time series with missing data.     

Nondestructive method for the calculation of bulk material composition by X‐ray fluorescence,using surface analysis on corroded bronze objects

The formation of patina on the surface of archeological bronze objects is a complex phenomenon, being influenced by various parameters induced by the environment and the alloy composition. Over several years, many attempts have been made to analyze the bulk composition of the alloys by nondestructive surface measurements. In this paper, we propose an analytical approach to evaluate the composition of bronze alloys using neural network analysis and X‐ray fluorescence spectrometry. Copyright © 2012 John Wiley & Sons, Ltd.     

Cytotoxicity and 2D-QSAR study of some heterocyclic compounds

Herein we have studied the cytotoxicity and quantitative structure–activity relationship (QSAR) of heterocyclic compounds containing cyclic urea and thiourea nuclei. A set of 22 hydantoin and thiohydantoin related heterocyclic compounds were investigated with respect to their LC₅₀ values (Log of LC₅₀) against brine shrimp lethality bioassay in order to derive the 2D-QSAR models using MLR, PLS and ANN methods. The best predictive models by MLR, PLS and ANN methods gave highly significant square correlation coefficient (R²) values of 0.83, 0.81 and 0.91 respectively. The model also exhibited good predictive power confirmed by the high value of cross validated correlation coefficient Q² (0.74).     

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.     

Environmental noise classifier using a new set of feature parameters based on pitch range

Automatic Noise Recognition was performed in two stages: (1) feature extraction based on the pitch range, found by analyzing the autocorrelation function and (2) classification using a classifier trained on the extracted features. Since most environmental noise types change their acoustical characteristics over time, we focused on the “pitch range” of the sounds in order to extract features. Two different classifiers, Support Vector Machines (SVM) and k-means clustering, were performed and compared using the proposed features. The SVM and k-means clustering classifiers achieve recognition rates up to 95.4% and 92.8%, respectively. Although both classifiers provided high accuracy, the SVM-based classifier outperformed the k-means clustering classifier by approximately 7.4%.