• Special Issue of the Society of Naval Architects of Korea
• /
• 2005.06a
• /
• pp.177-184
• /
• 2005

This paper is concerns with the development of the formulae to predict deformation of curved plate due to line heating. For this purpose thermal elasto-plastic analysis has been carried out for both flat and curved plate models with varying parameters which affect the result of line heating. based on the results of numerical analysis, the formulae for predicting angular deformation has been derived through the regression analysis, which. It has been seen that the present model well agrees with the numerical analysis results and can reflect the curvature effect of plate to be heated. This paper ends with some comments on this formulae.

• 한국IT서비스학회:학술대회논문집
• /
• 2007.11a
• /
• pp.145-156
• /
• 2007

In the previous e-government studies, there was no study in which the ambitious problem of assessing the expected performance of an e-government software when it is adopted in other country. This study was motivated to propose a new method to resolve this research question. With using the KIPONet (Korean Intellectual Property Office Net) as a target e-government software, which has been successfully implemented and operated by the Republic of Korea government since Jan 1999 for the purpose of managing the intellectual property rights (IPRs), we propose a Hybrid Qualitative Reasoning (HQR) approach to predicting the expected performance of the KIPONet. The main recipes of the HQR are that the HQR considers causal relationships existing among both qualitative and quantitative variables of the KIPONet, and that uncertainties embedded in some variables are handled by using Monte Carlo mechanism. The application of the proposed HQR to predicting the expected performance of the KIPONet results in statistically significant outcomes with 95% confidence level.

• Journal of Environmental Science International
• /
• v.6 no.3
• /
• pp.239-247
• /
• 1997

The numerical experiments using a particle tracking model have been performed for predicting the change of water Quality and shoreline. In present study, comparison of the numerical model results with the analytic solution shows that the point of the mainmum concentration and the distribution pattern is very similar. The reflection effect from the boundary was newly Introduced for making clear the effect of the closed boundary which set limits to application of a particle tracking model. The present model seems to reappear physical phenomenon well. This model shows well qualitative appearance of pollutant diffusion in Kwangan beach. Therefore, this model is regarded as a useful means for predicting diffusion movement of suspended sand, and change of water quality.

• Journal of the Ergonomics Society of Korea
• /
• v.28 no.3
• /
• pp.55-62
• /
• 2009

This study is concerned with predicting human search performance using a visual lobe. The most previous studies on human performance in visual search have been limited to a single-target search. This study extended the visual search research to multiple-target search including targets of different types as well as targets of same types. A model for predicting visual search performance was proposed and the model was validated by human search data. Additionally, this study found that human subjects always did not use a constant ratio of the whole visual lobe size for each type of targets in visual search process. The more conspicuous the target is, the more ratio of the whole visual lobe size human subjects use. The model that can predict human performance in multiple-target search may facilitate visual inspection plan in manufacturing.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.11 no.3
• /
• pp.46-54
• /
• 2012

The accuracy of cost estimation at an early stage in school building project is one of the critical factors for successful completion. So various of techniques are developed to predict the construction cost accurately and expeditely. Among the techniques, Support Vector Machine(SVM) has an excellent ability for generalization performance. Therefore, the purpose of this study is to construct the prediction model for construction cost of educational building project using support vector machine technique. And to verify the accuracy of prediction model for construction cost. The performance data used in this study are 217 school building project cost which have been completed from 2004 to 2007 in Gyeonggi-Do, Korea. The result shows that average error rate was 7.48% for SVM prediction model. So using SVM model on predicting construction cost of educational building project will be a considerably effective way at the early project stage.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.10 no.5
• /
• pp.223-227
• /
• 2002

Wind tunnel test or CFD is used for predicting aerodynamic drag coefficient in domestic motor companies. But, wind tunnel test requires much cost and time, and CFD has a relatively large error. In this study a predicting program of the aerodynamic drag coefficient based on empirical techniques was developed. Also GRG method was added to the program in order to decide optimal values of some parameters. The program was applied to 24 cars and the aerodynamic drag coefficients were predicted with 4.82% average error. Optimization was also accomplished to 6 cars. Some parameters to be modified were determined (1) to reduce the afterbody drag coefficient to the value established by a designer and (2) to preserve the same drag coefficient as the original automotive when some parameters have to be changed in the viewpoint of design. It was verified that the developed program can predict the aerodynamic drag coefficient appropriately and determine optimal values of some parameters.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2013.05a
• /
• pp.107-108
• /
• 2013

In this study, combustibles investigation and fire growth rate experiment were performed for predicting initial fire behavior in buildings. Combustibles investigation was performed for residential buildings, which is most frequently affected by fire in Korea. Spatial characteristics and combustibles properties were separately investigated, and occupied area and layout characteristics of combustibles were identified to produce general layout models. Of the layout models, room was selected for fire test of a single compartment. From this test, fire propagation for each combustible was identified, which was delayed compared to the summed heat release rate of a single combustible.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2013.11a
• /
• pp.64-65
• /
• 2013

Recently, people are concerned about how to maintain structure well because of safety. For effective maintenance of the structure, it should be resolved about carbonation, Durability, and Service Life issues. Solving that problem will Increase Safety of Structure. The carbonation velocity is produced an effect on carbon dioxide density of surrounding near structures, the concrete quality Therefore, This study compares the Velocity of carbonation due to maintenance of the structure. Also, this study will find Service Life of Concrete Structure through Predicting Carbonation Depth.

• Journal of Information Technology Applications and Management
• /
• v.13 no.4
• /
• pp.273-290
• /
• 2006

This study suggests a frequency matrix technique to predict personal credit rate more efficiently using incomplete data sets. At first this study test on multiple discriminant analysis and logistic regression analysis for predicting personal credit rate with incomplete data sets. Missing values are predicted with mean imputation method and regression imputation method here. An artificial neural network and frequency matrix technique are also tested on their performance in predicting personal credit rating. A data set of 8,234 customers in 2004 on personal credit information of Bank A are collected for the test. The performance of frequency matrix technique is compared with that of other methods. The results from the experiments show that the performance of frequency matrix technique is superior to that of all other models such as MDA-mean, Logit-mean, MDA-regression, Logit-regression, and artificial neural networks.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.1136-1138
• /
• 2014

Recently, predicting personality with the help of smartphone usage is become very interesting and attention grabbing topic in the field of research. At present there are some approaches towards detecting a user's personality which uses the smartphones usage data, such as call detail records (CDRs), the usage of short message services (SMSs) and the usage of social networking services application. In this paper, we focus on the predicting user attitude based on MBTI theory by using their smartphone usage data. We used Naïve Bayes and SVM classifier for classifying user personalities by extracting some features from smartphone usage data. From analysis it is observed that, SVM classifier works well as compared to Naïve Bayes.