• Proceedings of the Korea Concrete Institute Conference
• /
• 1999.10a
• /
• pp.285-288
• /
• 1999

Creep is a major parameter to represent long-term behavior of concrete structures concerning serviceability and durability. The effect of creep is recently taking account into crack resistance analysis of early-age concrete concerning durability evaluation. Since existing creep prediction models were proposed to predict creep for hardened concrete, most of them cannot consider effectively the information on microstructure formation and hydration developed in the early-age concrete. In this study, creep tests for early-age concrete made of the type I cement and the type V cement are carried out respectively and creep prediction models are evaluated for the prediction of creep behavior in early-age concrete. A creep prediction model is modified for the prediction of creep in early-age concrete and also verified by comparing prediction results with results of creep tests on early-age concrete.

• Atmosphere
• /
• v.17 no.3
• /
• pp.269-279
• /
• 2007

This study investigates the possibility of seasonal prediction for tropical cyclone activity in the western North Pacific by using a dynamical modeling approach. We use data from the SMIP/HFP (Seasonal Prediction Model Inter-comparison Project/Historical Forecast Project) experiment with the Korea Meteorological Administration's GDAPS (Global Data Assimilation and Prediction System) T106 model, focusing our analysis on model-generated tropical cyclones. It is found that the prediction depends primarily on the tropical cyclone (TC) detecting criteria. Additionally, a scaling factor and a different weighting to each ensemble member are found to be essential for the best predictions of summertime TC activity. This approach indeed shows a certain skill not only in the category forecast but in the standard verifications such as Brier score and relative operating characteristics (ROC).

• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.439-450
• /
• 2010

In this paper, we propose a new idea to evaluate the prediction accuracy of user's preference generated by memory-based collaborative filtering algorithm before prediction process in the recommender system. Our analysis results show the possibility of a pre-evaluation before the prediction process of users' preference of item's transaction on the web. Classification functions proposed in this study generate a user's rating pattern under certain conditions. In this research, we test whether classification functions select users who have lower prediction or higher prediction performance under collaborative filtering recommendation approach. The statistical test results will be based on the differences of the prediction accuracy of each user group which are classified by classification functions using the generative probability of specific rating. The characteristics of rating patterns of classified users will also be presented.

• Asia pacific journal of information systems
• /
• v.26 no.1
• /
• pp.66-79
• /
• 2016

The availability of detailed data on customers' online behaviors and advances in big data analysis techniques enable us to predict consumer behaviors. In the past, researchers have built purchase prediction models by analyzing clickstream data; however, these clickstream-based prediction models have had several limitations. In this study, we propose a new method for purchase prediction that combines information theory with machine learning techniques. Clickstreams from 5,000 panel members and data on their purchases of electronics, fashion, and cosmetics products were analyzed. Clickstreams were summarized using the 'entropy' concept from information theory, while 'random forests' method was applied to build prediction models. The results show that prediction accuracy of this new method ranges from 0.56 to 0.83, which is a significant improvement over values for clickstream-based prediction models presented in the past. The results indicate further that consumers' information search behaviors differ significantly across product categories.

• International journal of advanced smart convergence
• /
• v.7 no.2
• /
• pp.67-72
• /
• 2018

On the internal based search, the big data inference, which is failed in the president's election in the United States of America in 2016, is failed, because the prediction method is used on the base of the searching numerical value of a candidate for the presidency. Also the Flu Trend service is opened by the Google in 2008. But the Google was embarrassed for the fame's failure for the killing flu prediction system in 2011 and the prediction of presidential election in 2016. In this paper, using the virtual vote algorithm for virtual election and data mining method, the election prediction algorithm is proposed and unpacked. And also the WEKA DB is unpacked. Especially in this paper, using the K means algorithm and XEDOS tools, the prediction of election results is unpacked efficiently. Also using the analysis of the WEKA DB, the smart election prediction system is proposed in this paper.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.05a
• /
• pp.1050-1055
• /
• 2001

A software for prediction of apartment noise level ihas been improved. The program is based on the ray tracing technique which has been widely used in the environmental noise analysis and prediction. Especially for prediction of environmental noise in apartment complex, this program is advanced in the graphics routine by bilinear interpolation. In this paper, we analyze the railway noise distribution in apartment environment and develop a 3D graphics routine for illustrating the noise level.

• Communications for Statistical Applications and Methods
• /
• v.7 no.3
• /
• pp.937-943
• /
• 2000

Data mining usually deal with undesigned massive data containing many variables for which their characteristics and association rules are unknown, therefore it is actually not easy to interpret the results of analysis. In this paper, it is shown that decision tree can be very useful in interpreting data mining prediction model using two real examples.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.05a
• /
• pp.191-194
• /
• 2001

The ozone forecasting systems have many problems because the mechanism of the ozone concentration is highly complex, nonlinear, and nonstationary. Also, the results of prediction are not a good performance so far, especially in the high-level ozone concentration. This paper describes the modeling method of the ozone prediction system using neuro-fuzzy approaches and fuzzy clustering. The dynamic polynomial neural network (DPNN) based upon a typical algorithm of GMDH (group method of data handling) is a useful method for data analysis, identification of nonlinear complex system, and prediction of a dynamical system.

• Journal of Korean Society for Quality Management
• /
• v.47 no.4
• /
• pp.687-700
• /
• 2019

Purpose: The purpose of this study is to investigate the interaction effects between price determinants of artworks. We expand the methodology in art market by applying machine learning techniques to estimate the price of artworks and compare linear regression and machine learning in terms of prediction accuracy. Methods: Moderated regression analysis was performed to verify the interaction effects of artistic characteristics on price. The moderating effects were studied by confirming the significance level of the interaction terms of the derived regression equation. In order to derive price estimation model, we use multiple linear regression analysis, which is a parametric statistical technique, and k-nearest neighbor (kNN) regression, which is a nonparametric statistical technique in machine learning methods. Results: Mostly, the influences of the price determinants of art are different according to the auction types and the artist 's reputation. However, the auction type did not control the influence of the genre of the work on the price. As a result of the analysis, the kNN regression was superior to the linear regression analysis based on the prediction accuracy. Conclusion: It provides a theoretical basis for the complexity that exists between pricing determinant factors of artworks. In addition, the nonparametric models and machine learning techniques as well as existing parameter models are implemented to estimate the artworks' price.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.23 no.2
• /
• pp.51-56
• /
• 2015

This paper presents the procedure of drag prediction for EAV-1, based on a numerical analysis correlated to an in-flight test. EAV-1, developed by Korea Aerospace Research Institute, is a small-sized UAV to test a hydrogen-fuel cell power system. The long-endurance test flight of 4.5 hours provides numerous in-flight data. The thrust and drag of EAV-1 during the flight test are estimated based on the wind-tunnel test results for EAV-1's propeller performance. In addition, the CFD analysis using a commercial Navier-Stokes code is carried out for the full-scale EAV-1. The computational result suggests that the initial CFD analysis substantially under-predicts the in-flight drag in that the discrepancy is up to 27.6%. Therefore, additional investigation for more accurate drag prediction is performed; the effect of propeller slipstream is included in the CFD analysis through "fan disk" modelling. Also, the additional drag from airplane trim and load factor that actually exists during the flight test in a circular path is considered. These supplemental analyses for drag prediction turn out to be effective since the drag discrepancy reduces to 2.3%.