A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem

We propose a threshold-varying artificial neural network (TV-ANN) approach for solving the binary classification problem. Using a set of simulated and real-world data set for bankruptcy prediction, we illustrate that the proposed TV-ANN fares well, both for training and holdout samples, when compared to the traditional backpropagation artificial neural network (ANN) and the statistical linear discriminant analysis. The performance comparisons of TV-ANN with a genetic algorithm-based ANN and a classification tree approach C4.5 resulted in mixed results.     

人工神经网络在劳动力供求预测中的应用

劳动动力市场是一个非线性系统,常规方法对其建模进行预测的准确率不高。通过引入机器学习领域的研究成果,结合劳动力市场自身的特点,建立BP人工神经网络模型,对劳动力市场的模拟和供求量的预测都得到较好的结果,提出了将人工神经网络应用于劳动力市场建模的一般方法,可以用来定量研究劳动力市场的各种问题,具有可操作性和实用性,比现有方法的拟合效果好,预测准确率高。     

Prediction of rock fragmentation due to blasting using artificial neural network

Prediction of rock fragmentation is essential for optimizing blasting operation. Fragmentation depends on many parameters such as rock mass properties, blast geometry and explosive properties. In this paper, artificial neural network (ANN) method is implemented to develop a model to predict rock fragmentation due to blasting in an iron ore mine. In the developing of the proposed model eight parameters such as hole diameter, burden, powder factor, blastability index, etc., were incorporated. Training of the model was performed by back-propagation algorithm using 220 datasets. A four-layer ANN was found to be optimum with architecture 10-9-7-1. Sensitivity analysis revealed that the most effective parameters on rock fragmentation are blastability index (G), charge per delay (J), burden (C), SMR (F) and powder factor (E).     

Prediction and analysis of flow behavior of a polymer melt through nanochannels using artificial neural network and statistical methods

A new methodology, namely, artificial neural network (ANN) approach was proposed for modeling and predicting flow behavior of the polyethylene melt through nanochannels of nanoporous alumina templates. Wetting length of the nanochannels was determined to be a function of time, temperature, diameter of nanochannels, and surface properties of the inner wall of the nanochannels. An ANN was designed to forecast the relationship between the length of wetting as output parameter and other aforementioned parameters as input variables. It was demonstrated that the ANN method is capable of modeling this phenomenon with high accuracy. The designed ANN was then employed to obtain the wetting length of the nanochannels for those cases, which were not reported by the wetting experiments. The results were then analyzed statistically to identify the effect of each independent variable, namely, time, temperature, diameter of nanochannels, and surface properties of the inner wall of nanochannels as well as their combinations on the wetting length of the nanochannels. Interesting results were attained and discussed.     

Cluster analysis in industrial market segmentation through artificial neural network

Market segmentation has commonly applied cluster analysis. This study intends to make the comparison of conventional two-stage method with proposed two-stage method through the simulated data. The proposed two-stage method is the combination of self-organizing feature maps and K-means method. The simulation results show that the proposed scheme is better than the conventional two-stage method based on the rate of misclassification.     

Plane-Gaussian artificial neural network

Multilayer perceptrons (MLPs) and radial basis functions networks (RBFNs) have been widely concerned in recent years. In this paper, based on k-plane clustering (kPC) algorithm, we propose a novel artificial network model termed as Plane-Gaussian network to enlarge the arsenal of the neural networks. This network adopts a so-called Plane-Gaussian activation function (PGF) in hidden neurons. Replacing traditional central point of Gaussian radial basis function (RBF) with central hyperplane, PGF forms a band-shaped rather than spheral-shaped receptive field in RBF, which makes PGF able to express its peculiar geometrical characteristics: locality and globality. Importantly, it is also proved that PGF network (PGFN) having one hidden layer is capable of universal approximation. As a universal approximator, PGFN gives an informal way of bridging the gap between MLP and RBFN. The experiments report comparison between training time and classification accuracies on some artificial and UCI datasets and conclude that (1) PGFN runs significantly faster than MLP and (2) PGFN has comparable or better classification performance than MLP and RBFN, especially in subspace-distributed datasets.     

Using neural network ensembles for bankruptcy prediction and credit scoring

Bankruptcy prediction and credit scoring have long been regarded as critical topics and have been studied extensively in the accounting and finance literature. Artificial intelligence and machine learning techniques have been used to solve these financial decision-making problems. The multilayer perceptron (MLP) network trained by the back-propagation learning algorithm is the mostly used technique for financial decision-making problems. In addition, it is usually superior to other traditional statistical models. Recent studies suggest combining multiple classifiers (or classifier ensembles) should be better than single classifiers. However, the performance of multiple classifiers in bankruptcy prediction and credit scoring is not fully understood. In this paper, we investigate the performance of a single classifier as the baseline classifier to compare with multiple classifiers and diversified multiple classifiers by using neural networks based on three datasets. By comparing with the single classifier as the benchmark in terms of average prediction accuracy, the multiple classifiers only perform better in one of the three datasets. The diversified multiple classifiers trained by not only different classifier parameters but also different sets of training data perform worse in all datasets. However, for the Type I and Type II errors, there is no exact winner. We suggest that it is better to consider these three classifier architectures to make the optimal financial decision.     

Prediction of sand ripple geometry under waves using an artificial neural network

The length and height of a sand ripple in the seabed are the two basic parameters used to estimate the bottom shear stress and predict the transport of sand by wave action. These values are currently obtained with the help of many empirical equations. A different estimation method, in the form of an artificial neural network, is presented in this paper. The network is trained by measurements collected in the laboratory and in-situ under different forcing conditions. Validation of the present neural network results with different measurements shows that the new method can predict the ripple length and height much more accurately than the conventional empirical equations.     

Prediction of creep curve of HP40Nb steel using artificial neural network

Neural Computing and Applications - Simulation of creep curves using data obtained from a limited number of short-time creep tests is helpful for predicting the long-time creep life of materials by...     

灰色人工神经网络人口总量预测模型及应用

针对单一指标进行人口总量预测精度不高的问题,基于灰色系统理论和人工神经网络理论,用1990年至2004年中国人口总量序列建立并训练一个多指标的灰色人工神经网络人口总量预测模型。对2005年至2007年的人口总量进行检验性预测,结果表明灰色人工神经网络模型大大提高了预测精度。     

Prediction of power output of a coal-fired power plant by artificial neural network

Accurate modeling of thermal power plant is very useful as well as difficult. Conventional simulation programs based on heat and mass balances represent plant processes with mathematical equations. These are good for understanding the processes but usually complicated and at times limited with large number of parameters needed. On the other hand, artificial neural network (ANN) models could be developed using real plant data, which are already measured and stored. These models are fast in response and easy to be updated with new plant data. Usually, in ANN modeling, energy systems can also be simulated with fewer numbers of parameters compared to mathematical ones. Step-by-step method of the ANN model development of a coal-fired power plant for its base line operation is discussed in this paper. The ultimate objective of the work was to predict power output from a coal-fired plant by using the least number of controllable parameters as inputs. The paper describes two ANN models, one for boiler and one for turbine, which are eventually integrated into a single ANN model representing the real power plant. The two models are connected through main steam properties, which are the predicted parameters from boiler ANN model. Detailed procedure of ANN model development has been discussed along with the expected prediction accuracies and validation of models with real plant data. The interpolation and extrapolation capability of ANN models for the plant has also been studied, and observed results are reported.     

Evolving artificial neural network ensembles

Using a coordinated group of simple solvers to tackle a complex problem is not an entirely new idea. Its root could be traced back hundreds of years ago when ancient Chinese suggested a team approach to problem solving. For a long time, engineers have used the divide-and-conquer strategy to decompose a complex problem into simpler sub-problems and then solve them by a group of solvers. However, knowing the best way to divide a complex problem into simpler ones relies heavily on the available domain knowledge. It is often a manual process by an experienced engineer. There have been few automatic divide-and-conquer methods reported in the literature. Fortunately, evolutionary computation provides some of the interesting avenues to automatic divide-and-conquer methods. An in-depth study of such methods reveals that there is a deep underlying connection between evolutionary computation and ANN ensembles. Ideas in one area can be usefully transferred into another in producing effective algorithms. For example, using speciation to create and maintain diversity had inspired the development of negative correlation learning for ANN ensembles, and an in-depth study of diversity in ensembles. This paper will review some of the recent work in evolutionary approaches to designing ANN ensembles.     

一种改进的人工神经网络模型

提出一种新型人工神经网络模型,称为“基于模式神经元的人工神经网络（Pattern Neuron Based Artificial Neural Network,PNBANN）”。与现有的神经计算网络不同,PNBANN是一种完全基于神经元连接的网络模型。网络中的每一个神经元都唯一代表一种模式,每当接收新模式时,自动建立一个新的连接,把信息存储在网络中;而接收已有的模式时,已有的神经元连接得到加强。当模式神经元的输出达到所设定的感觉阈值时,对应模式的信息被记忆。因此,PNBANN就是不断地接收、存储各种信息,并把感觉足够强的模式记忆下来,这一过程更接近于人脑的学习、记忆过程。实验结果证明,PNBANN学习效率高,在学习新知识时不会影响已有的知识,同时具有很强的识别能力。     

Prediction of ultimate bearing capacity through various novel evolutionary and neural network models

Engineering with Computers - In the current study, various evolutionary artificial intelligence and machine learning models namely, optimized artificial neural network (ANN), genetic algorithm...     

Prediction of highway asphalt pavement performance based on Markov chain and artificial neural network approach

The Journal of Supercomputing - In order to study the problems of inadequate maintenance measures, inappropriate maintenance time, and unreasonable use of funds in asphalt pavement maintenance of...     

Prediction of unconfined compressive strength of rock surrounding a roadway using artificial neural network

The unconfined compressive strength (UCS) of rocks is an important design parameter in rock engineering and geotechnics, which is required and determined for rock mechanical studies in mining and civil projects. This parameter is usually determined through a laboratory UCS test. Since the preparation of high-quality samples is difficult, expensive and time consuming for laboratory tests, development of predictive models for determining the mechanical properties of rocks seems to be essential in rock engineering. In this study, an attempt was made to develop an artificial neural network (ANN) and multivariable regression analysis (MVRA) models in order to predict UCS of rock surrounding a roadway. For this, a database of laboratory tests was prepared, which includes rock type, Schmidt hardness, density and porosity as input parameters and UCS as output parameter. To make a database (including 93 datasets), different rock samples, ranging from weak to very strong types, are used. To compare the performance of developed models, determination coefficient (R ²), variance account for (VAF), mean absolute error (E _a) and mean relative error (E _r) indices between predicted and measured values were calculated. Based on this comparison, it was concluded that performance of the ANN model is considerably better than the MVRA model. Further, a sensitivity analysis shows that rock density and Schmidt hardness were recognized as the most effective parameters, whereas porosity was considered as the least effective input parameter on the ANN model output (UCS) in this study.     

Fractional snow cover mapping through artificial neural network analysis of MODIS surface reflectance

Accurate areal measurements of snow cover extent are important for hydrological and climate modeling. The traditional method of mapping snow cover is binary where a pixel is considered either snow-covered or snow-free. Fractional snow cover (FSC) mapping can achieve a more precise estimate of areal snow cover extent by estimating the fraction of a pixel that is snow-covered. The most common snow fraction methods applied to Moderate Resolution Imaging Spectroradiometer (MODIS) images have been spectral unmixing and an empirical Normalized Difference Snow Index (NDSI). Machine learning is an alternative for estimating FSC as artificial neural networks (ANNs) have been successfully used for estimating the subpixel abundances of other surfaces. The advantages of ANNs are that they can easily incorporate auxiliary information such as land cover type and are capable of learning nonlinear relationships between surface reflectance and snow fraction. ANNs are especially applicable to mapping snow cover extent in forested areas where spatial mixing of surface components is nonlinear. This study developed a multilayer feed-forward ANN trained through backpropagation to estimate FSC using MODIS surface reflectance, NDSI, Normalized Difference Vegetation Index (NDVI) and land cover as inputs. The ANN was trained and validated with higher spatial-resolution FSC maps derived from Landsat Enhanced Thematic Mapper Plus (ETM+) binary snow cover maps. Testing of the network was accomplished over training and independent test areas. The developed network performed adequately with RMSE of 12% over training areas and slightly less accurately over the independent test scenes with RMSE of 14%. The developed ANN also compared favorably to the standard MODIS FSC product. The study also presents a comprehensive validation of the standard MODIS snow fraction product whose performance was found to be similar to that of the ANN.     

Prediction of seismic slope stability through combination of particle swarm optimization and neural network

One of the main concerns in geotechnical engineering is slope stability prediction during the earthquake. In this study, two intelligent systems namely artificial neural network (ANN) and particle swarm optimization (PSO)–ANN models were developed to predict factor of safety (FOS) of homogeneous slopes. Geostudio program based on limit equilibrium method was utilized to obtain 699 FOS values with different conditions. The most influential factors on FOS such as slope height, gradient, cohesion, friction angle and peak ground acceleration were considered as model inputs in the present study. A series of sensitivity analyses were performed in modeling procedures of both intelligent systems. All 699 datasets were randomly selected to 5 different datasets based on training and testing. Considering some model performance indices, i.e., root mean square error, coefficient of determination (R ²) and value account for (VAF) and using simple ranking method, the best ANN and PSO–ANN models were selected. It was found that the PSO–ANN technique can predict FOS with higher performance capacities compared to ANN. R ² values of testing datasets equal to 0.915 and 0.986 for ANN and PSO–ANN techniques, respectively, suggest the superiority of the PSO–ANN technique.     

An artificial neural network satisfiability tester

An artificial neural network tester for the satisfiability problem of propositional calculus is presented. Satisfiability is treated as a constraint satisfaction optimization problem and, contrary to most of the existing satisfiability testers, the expressions are converted into disjunctive normal form before testing. The artificial neural network is based on the principles of harmony theory. Its basic characteristics are the simulated annealing procedure and the harmony function; the latter constitutes a measure of the satisfiability of the expression under the current truth assignment to its variables. The tester is such that: (a) the satisfiability of any expression is determined; (b) a truth assignment to the variables of the expression is output which renders true the greatest possible number of clauses; (c) all the truth assignments which render true the maximum number of clauses can be produced. © 2001 John Wiley & Sons, Inc.