• Journal of computational fluids engineering
• /
• v.21 no.2
• /
• pp.12-24
• /
• 2016

The standard ${\kappa}-{\varepsilon}$ and realizable ${\kappa}-{\varepsilon}$ models are adopted to improve the prediction performance on the recirculating flow. In this paper, the backward facing step flows are used to assess the prediction performance of the recirculation zone. The model constants of turbulence model are obtained by the experimental results and they have a different value according to the flow. In the case of an isotropic flow situation, decaying of turbulent kinetic energy should follow a power law behavior. In accordance with the power law, the coefficients for the dissipation rate of turbulent kinetic energy are not universal. Also, the other coefficients as well as the dissipation coefficient are not constant. As a result, a suitable coefficients can be varied according to each of the flow. The changes of flow over the backward facing step in accordance with model constants of the ${\kappa}-{\varepsilon}$ models show that the reattachment length is dependent on the growth rate(${\lambda}$) and the ${\kappa}-{\varepsilon}$ models can be improved the prediction performance by changing the model constants about the recirculating flow. In addition, it was investigated for the curvature correction effect of the ${\kappa}-{\varepsilon}$ models in the recirculating flow. Overall, the curvature corrected ${\kappa}-{\varepsilon}$ models showed an excellent prediction performance.

• International Journal of Highway Engineering
• /
• v.14 no.5
• /
• pp.101-111
• /
• 2012

PURPOSES: Because expressway ramps are very complex segments where diverse roadway design elements dynamically change within relatively short length, drivers on ramps are required to drive their cars carefully for safety. Especially, ramps on expressways are designed to guarantee driving at high speed so that the risk and severity of traffic accidents on expressway ramps may be higher and more deadly than other facilities on expressways. Safe deceleration maneuvers are required on off-ramps, whereas safe acceleration maneuvers are necessary on onramps. This difference in required maneuvers may contribute to dissimilar patterns and severity of traffic accidents by ramp types. Therefore, this study was aimed at developing prediction models of the severity of traffic accidents on expressway on- and off-ramps separately in order to consider dissimilar patterns and severity of traffic accidents according to types of ramps. METHODS: Four-year-long traffic accident data between 2007 and 2010 were utilized to distinguish contributing design elements in conjunction with AADT and ramp length. The prediction models were built using the negative binomial regression model consisting of the severity of traffic accident as a dependent variable and contributing design elements as in independent variables. RESULTS: The developed regression models were evaluated using the traffic accident data of the ramps which was not used in building the models by comparing actual and estimated severity of traffic accidents. Conclusively, the average prediction error rates of on-ramps and offramps were 30.5% and 30.8% respectively. CONCLUSIONS: The prediction models for the severity of traffic accidents on expressway on- and off-ramps will be useful in enhancing the safety on expressway ramps as well as developing design guidelines for expressway ramps.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.40 no.3
• /
• pp.259-265
• /
• 2016

Recently, life prediction models for Pb-based and Pb-free solders used in chip resistor assemblies under thermal cycling have been introduced. The models suggest that the field lifetimes of Pb-free solders would be better than those of Pb-based solders when used for chip resistors under thermal cycling conditions, while the lifetime of the chip assemblies under accelerated test conditions show a reverse relationship. In this study, the prediction models were verified by applying the model to another research case. Finite element models were built, thermal cycling conditions were applied, and the energy densities were calculated. Finally, life prediction analysis was conducted for the cases where Pb-based and Pb-free solders were used. The prediction results were then compared with the test data of the case. It was verified that the predictions of the developed life cycle models are on the practical scale.

• Computers and Concrete
• /
• v.26 no.6
• /
• pp.533-546
• /
• 2020

The prediction of spall response of reinforced concrete members like columns and slabs have been attempted by earlier researchers with analytical solutions, as well as with empirical models developed from data generated from physical or numerical experiments, with different degrees of success. In this article, compared to the empirical models, more versatile and accurate models are developed based on model-free approach of artificial neural network (ANN). Synthetic data extracted from the results of numerical experiments from literature have been utilized for the purpose of training and testing of the ANN models. For two concrete members, namely, slabs and columns, different sets of ANN models were developed, each of which proved to have definite advantages over the corresponding empirical model reported in literature. In case of slabs, for all three categories of spall, the ANN model results were superior to the empirical models as evaluated by the various performance metrics, such as correlation, root mean square error, mean absolute error, maximum overestimation and maximum underestimation. The ANN models for each category of column spall could handle three variables together: namely, depth, spacing of longitudinal and transverse reinforcement, as contrasted to the empirical models that handled one variable at a time, and at the same time yielded comparable performance. The application of the ANN models for spall prediction of concrete slabs and columns developed in this study has been discussed along with their limitations.

• International Journal of Advanced Culture Technology
• /
• v.11 no.3
• /
• pp.310-314
• /
• 2023

The purpose of this study is to predict the remaining capacity of lithium-ion batteries and evaluate their performance using five artificial intelligence models, including linear regression analysis, decision tree, random forest, neural network, and ensemble model. We is in the study, measured Excel data from the CS2 lithium-ion battery was used, and the prediction accuracy of the model was measured using evaluation indicators such as mean square error, mean absolute error, coefficient of determination, and root mean square error. As a result of this study, the Root Mean Square Error(RMSE) of the linear regression model was 0.045, the decision tree model was 0.038, the random forest model was 0.034, the neural network model was 0.032, and the ensemble model was 0.030. The ensemble model had the best prediction performance, with the neural network model taking second place. The decision tree model and random forest model also performed quite well, and the linear regression model showed poor prediction performance compared to other models. Therefore, through this study, ensemble models and neural network models are most suitable for predicting the remaining capacity of lithium-ion batteries, and decision tree and random forest models also showed good performance. Linear regression models showed relatively poor predictive performance. Therefore, it was concluded that it is appropriate to prioritize ensemble models and neural network models in order to improve the efficiency of battery management and energy systems.

• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.235-245
• /
• 2011

Early criticality prediction models that determine whether a design entity is fault-prone or not are becoming more and more important as software development projects are getting larger. Effective predictions can reduce the system development cost and improve software quality by identifying trouble-spots at early phases and proper allocation of effort and resources. Many prediction models have been proposed using statistical and machine learning methods. This paper builds a prediction model using Support Vector Machine(SVM) which is one of the most popular modern classification methods and compares its prediction performance with a well-known prediction model, BackPropagation neural network Model(BPM). SVM is known to generalize well even in high dimensional spaces under small training data conditions. In prediction performance evaluation experiments, dimensionality reduction techniques for data set are not used because the dimension of input data is too small. Experimental results show that the prediction performance of SVM model is slightly better than that of BPM and polynomial kernel function achieves better performance than other SVM kernel functions.

• Journal of Information Technology Services
• /
• v.13 no.3
• /
• pp.221-233
• /
• 2014

Because people's interest of the stock market has been increased with the development of economy, a lot of studies have been going to predict fluctuation of stock prices. Latterly many studies have been made using scientific and technological method among the various forecasting method, and also data using for study are becoming diverse. So, in this paper we propose stock prices prediction models using sentiment analysis and machine learning based on news articles and SNS data to improve the accuracy of prediction of stock prices. Stock prices prediction models that we propose are generated through the four-step process that contain data collection, sentiment dictionary construction, sentiment analysis, and machine learning. The data have been collected to target newspapers related to economy in the case of news article and to target twitter in the case of SNS data. Sentiment dictionary was built using news articles among the collected data, and we utilize it to process sentiment analysis. In machine learning phase, we generate prediction models using various techniques of classification and the data that was made through sentiment analysis. After generating prediction models, we conducted 10-fold cross-validation to measure the performance of they. The experimental result showed that accuracy is over 80% in a number of ways and F1 score is closer to 0.8. The result can be seen as significantly enhanced result compared with conventional researches utilizing opinion mining or data mining techniques.

• Communications for Statistical Applications and Methods
• /
• v.17 no.1
• /
• pp.99-106
• /
• 2010

In this paper, we present two methods for obtaining prediction intervals for the times to failure of units censored in multiple stages in a progressively censored sample from proportional hazard rate models. A numerical example and a Monte Carlo simulation study are presented to illustrate the prediction methods.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.27 no.2
• /
• pp.1-13
• /
• 2002

In this paper, we compares the business failure prediction accuracy among Linear Programming Discriminant Analysis(LPDA) model, Multivariate Discriminant Analysis (MDA) model and logit analysis model. The Data for 417 companies analyzed were gathered from KIS-FAS Published by Korea Information Service in 1999. The result of comparison for four time horizons shows that LPDA Is advantageous in prediction accuracy over the other two models when over all tilt ratio and business failure accuracy are considered simultaneously.

• International Journal of Precision Engineering and Manufacturing
• /
• v.3 no.4
• /
• pp.72-77
• /
• 2002

The load interaction effect can be best illustrated by the phenomenon of overload retardation. Some prediction methods for retardation are reviewed and the problems discussed in the present paper. The so-called under-load effect much of the retardation disappears if a very low level minimum stress follows the overload, is also of importance for a prediction model to work properly under random load spectrum. The concept of Interactive Zone (IZ) fully considering reversed plasticity during unloading was discussed. This IZ concept can be combined with existing models to derive some improved models that can naturally take account of the under-load effect. Some simulations by IZ improved models for test under complex load sequences including multiple overloads and both over/under loads are compared with test results. It is seen that the improvement by IZ concept greatly enhanced the ability of existing models to accommodate complex load interaction effects.