• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1406-1420
• /
• 2017

Artificial neural networks (ANNs) play an important role in the fields of function approximation, prediction, and classification. ANN performance is critically dependent on the input parameters, including the number of neurons in each layer, and the optimal values of weights and biases assigned to each neuron. In this study, we apply the particle swarm optimization method, a popular optimization algorithm for determining the optimal values of weights and biases for every neuron in different layers of the ANN. Several regression models, including general linear regression, Fourier regression, smoothing spline, and polynomial regression, are conducted to evaluate the proposed method's prediction power compared to multiple linear regression (MLR) methods. In addition, residual analysis is conducted to evaluate the optimized ANN accuracy for both training and test datasets. The experimental results demonstrate that the proposed method can effectively determine optimal values for neuron weights and biases, and high accuracy results are obtained for prediction applications. Evaluations of the proposed method reveal that it can be used for prediction and estimation purposes, with a high accuracy ratio, and the designed model provides a reliable technique for optimization. The simulation results show that the optimized ANN exhibits superior performance to MLR for prediction purposes.

• Coupled systems mechanics
• /
• v.6 no.1
• /
• pp.55-74
• /
• 2017

The evaluation of torsional effects on multistory buildings remains an open issue, despite considerable research efforts and numerous publications. In this study, a large number of multiple test structures are considered with normally distributed topological attributes, in order to quantify the statistically derived relationships between the torsional criteria and response parameters. The linear regression analysis results, depict that the center of twist and the ratio of torsion (ROT) index proved numerically to be the most reliable criteria for the prediction of the modal rotation and displacements, however the residuals distribution and R-squared derived for the ductility demands prediction, was not constant and low respectively. Thus, the assessment of the torsional parameters' contribution to the nonlinear structural response was investigated using artificial neural networks. Utilizing the connection weights approach, the Center of Strength, Torsional Stiffness and the Base Shear Torque curves were found to exhibit the highest impact numerically, while all the other torsional indices' contribution was investigated and quantified.

• Journal of Industrial Convergence
• /
• v.16 no.4
• /
• pp.33-46
• /
• 2018

Personal credit scoring is an effective tool for banks to properly guide decision profitably on granting loans. Recently, many classification algorithms and models are used in personal credit scoring. Personal credit scoring technology is usually divided into statistical method and non-statistical method. Statistical method includes linear regression, discriminate analysis, logistic regression, and decision tree, etc. Non-statistical method includes linear programming, neural network, genetic algorithm and support vector machine, etc. But for the development of the credit scoring model, there is no consistent conclusion to be drawn regarding which method is the best. In this paper, we will compare the performance of the most common scoring techniques such as logistic regression, neural network, and support vector machines using personal credit data of the financial institution in China. Specifically, we build three models respectively, classify the customers and compare analysis results. According to the results, support vector machine has better performance than logistic regression and neural networks.

• Journal of the Korean Statistical Society
• /
• v.31 no.1
• /
• pp.63-75
• /
• 2002

Most attempts at Bayesian analysis of neural networks involve hierarchical modeling. We believe that similar results can be obtained with simpler models that require less computational effort, as long as appropriate restrictions are placed on parameters in order to ensure propriety of posterior distributions. In particular, we adopt a model first introduced by Lee (1999) that utilizes an improper prior for all parameters. Straightforward Gibbs sampling is possible, with the exception of the bias parameters, which are embedded in nonlinear sigmoidal functions. In addition to the problems posed by nonlinearity, direct sampling from the posterior distributions of the bias parameters is compounded due to the duplication of hidden nodes, which is a source of multimodality. In this regard, we focus on sampling from the marginal posterior distribution of the bias parameters with Markov chain Monte Carlo methods that combine traditional Metropolis sampling with a slice sampler described by Neal (1997, 2001). The methods are illustrated with data examples that are largely confined to the analysis of nonparametric regression models.

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.155-166
• /
• 2002

Neural networks have been studied as a popular tool for classification and they are very flexible. Also, they are used for many applications of pattern classification and pattern recognition. This paper focuses on Bayesian approach to feed-forward neural networks with single hidden layer of units with logistic activation. In this model, we are interested in deciding the number of nodes of neural network model with p input units, one hidden layer with m hidden nodes and one output unit in Bayesian setup for fixed m. Here, we use the latent variable into the prior of the coefficient regression, and we introduce the 'sequential step' which is based on the idea of the data augmentation by Tanner and Wong(1787). The MCMC method(Gibbs sampler and Metropolish algorithm) can be used to overcome the complicated Bayesian computation. Finally, a proposed method is applied to a simulated data.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.7
• /
• pp.403-411
• /
• 2021

This study discusses the influence of economic factors on the clothing exports from China and 15 South and Southeast Asian countries to the United States. A basic gravity trade model with three predictors, including the GDP value produced by exporting and importing countries and their geographical distance was established to explain the bilateral trade patterns. The conventional approach of multiple regression and the novel approach of Artificial Neural Networks (ANNs) were developed based on the value of clothing exports from 2012 to 2018 and applied to the trade pattern prediction of 2019. The results showed that ANNs can achieve a more accurate prediction in bilateral trade patterns than the commonly-used econometric analysis of the basic gravity trade model. Future studies can examine the predictive power of ANNs on an extended gravity model of trade that includes explanatory variables in social and environmental areas, such as policy, initiative, agreement, and infrastructure for trade facilitation, which are crucial for policymaking and managerial consideration. More research should be conducted for the examination of the balance between developing countries' economic growth and their social and environmental sustainability and for the application of more advanced machine-learning algorithms of global trade flow examination.

• Journal of Navigation and Port Research
• /
• v.42 no.5
• /
• pp.341-346
• /
• 2018

Supramax bulk carriers cover a wide range of ocean transportation requirements, from major to minor bulk cargoes. Market forecasting for this segment has posed a challenge to researchers, due to complexity involved, on the demand side of the forecasting model. This paper addresses this issue by using technical indicators as input features, instead of complicated supply-demand variables. Artificial neural networks (ANN), one of the most popular machine-learning tools, were used to replace classical time-series models. Results revealed that ANN outperformed the benchmark binomial logistic regression model, and predicted direction of the spot market with more than 70% accuracy. Results obtained in this paper, can enable chartering desks to make better short-term chartering decisions.

• Computers and Concrete
• /
• v.19 no.5
• /
• pp.457-465
• /
• 2017

The Taiwanese liquid crystal display (LCD) industry has traditionally produced a huge amount of waste glass that is placed in landfills. Waste glass recycling can reduce the material costs of concrete and promote sustainable environmental protection activities. Concrete is always utilized as structural material; thus, the concrete compressive strength with a variety of mixtures must be studied using predictive models to achieve more precise results. To create an efficient waste LCD glass concrete (WLGC) design proportion, the related studies utilized a multivariable regression analysis to develop a compressive strength waste LCD glass concrete equation. The mix design proportion for waste LCD glass and the compressive strength relationship is complex and nonlinear. This results in a prediction weakness for the multivariable regression model during the initial growing phase of the compressive strength of waste LCD glass concrete. Thus, the R ratio for the predictive multivariable regression model is 0.96. Neural networks (NN) have a superior ability to handle nonlinear relationships between multiple variables by incorporating supervised learning. This study developed a multivariable prediction model for the determination of waste LCD glass concrete compressive strength by analyzing a series of laboratory test results and utilizing a neural network algorithm that was obtained in a related prior study. The current study also trained the prediction model for the compressive strength of waste LCD glass by calculating the effects of several types of factor combinations, such as the different number of input variables and the relevant filter for input variables. These types of factor combinations have been adjusted to enhance the predictive ability based on the training mechanism of the NN and the characteristics of waste LCD glass concrete. The selection priority of the input variable strategy is that evaluating relevance is better than adding dimensions for the NN prediction of the compressive strength of WLGC. The prediction ability of the model is examined using test results from the same data pool. The R ratio was determined to be approximately 0.996. Using the appropriate input variables from neural networks, the model validation results indicated that the model prediction attains greater accuracy than the multivariable regression model during the initial growing phase of compressive strength. Therefore, the neural-based predictive model for compressive strength promotes the application of waste LCD glass concrete.

• Computers and Concrete
• /
• v.5 no.6
• /
• pp.559-572
• /
• 2008

The effects of fly ash and superplasticizer (SP) on workability of concrete are quite difficult to predict because they are dependent on other concrete ingredients. Because of high complexity of the relations between workability and concrete compositions, conventional regression analysis could be not sufficient to build an accurate model. In this study, a workability model has been built using artificial neural networks (ANN). In this model, the workability is a function of the content of all concrete ingredients, including cement, fly ash, blast furnace slag, water, superplasticizer, coarse aggregate, and fine aggregate. The effects of water/binder ratio (w/b), fly ash-binder ratio (fa/b), superplasticizer-binder ratio (SP/b), and water content on slump were explored by the trained ANN. This study led to the following conclusions: (1) ANN can build a more accurate workability model than polynomial regression. (2) Although the water content and SP/b were kept constant, a change in w/b and fa/b had a distinct effect on the workability properties. (3) An increasing content of fly ash decreased the workability, while raised the slump upper limit that can be obtained.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.22 no.9
• /
• pp.741-746
• /
• 2009

Compare to conventional Indium Tin Oxide (ITO) film deposition methods, cesium assisted sputtering method has been shown superior electrical, mechanical, and optical film properties. However, it is not easy to use cesium assisted sputtering method since ITO film properties are very sensitive to Cesium assisted equipment condition but their mechanism is not yet clearly defined physically or mathematically. Therefore, to optimize deposited ITO film characteristics, development of accurate and reliable process model is essential. For this, in this work, we developed ITO film deposition process model using neural networks and design of experiment (DOE). Developed model prediction results are compared with conventional statistical regression model and developed neural process model has been shown superior prediction results on modeling of ITO film thickness, sheet resistance, and transmittance characteristics.