• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.150-150
• /
• 2018

The Numerical Weather Prediction (NWP) models provide information for weather forecasts. The highly nonlinear and complex interactions in the atmosphere are simplified in meteorological models through approximations and parameterization. Therefore, the simplifications may lead to biases and errors in model results. Although the models have improved over time, the biased outputs of these models are still a matter of concern in meteorological and hydrological studies. Thus, bias removal is an essential step prior to using outputs of atmospheric models. The main idea of statistical bias correction methods is to develop a statistical relationship between modeled and observed variables over the same historical period. The Model Output Statistics (MOS) would be desirable to better match the real time forecast data with observation records. Statistical post-processing methods relate model outputs to the observed values at the sites of interest. In this study three methods are used to remove the possible biases of the real-time outputs of the Weather Research and Forecast (WRF) model in Imjin basin (North and South Korea). The post-processing techniques include the Linear Regression (LR), Linear Scaling (LS) and Power Scaling (PS) methods. The MOS techniques used in this study include three main steps: preprocessing of the historical data in training set, development of the equations, and application of the equations for the validation set. The expected results show the accuracy improvement of the real-time forecast data before and after bias correction. The comparison of the different methods will clarify the best method for the purpose of the forecast skill enhancement in a real-time case study.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1D
• /
• pp.59-66
• /
• 2006

This study was to construct the linear density predictive models on the on-ramp junctions in urban freeway. From the analyses of the real-time traffic characteristic data, and the construction and verification of the linear density predictive models, the models showed a considerable explanatory power with the determination coefficients ($R^2$) of over 0.7 between the density and speed data. Also, they showed a considerably high correlativeness with the correlation coefficients (r) of over 0.8 between the calculated density data and the expected ones estimated by the models.

• The Journal of Information Systems
• /
• v.5
• /
• pp.21-41
• /
• 1996

Linear programming has become an important tool in decision-making of modern business management. This remarkable growth can be traced to the pioneering efforts of many individuals and research organizations. The popular using of personal computers make it very easy to process those complicated linear programming models. Furthermore advanced linear programming software packages assist us to solve L.P. models without any difficult process. Even though the advanced L.P. professional packages, the needs of more detailed deterministic elements for business decisions have forced us to apply dynamic approaches for more resonable solutions. For the purpose of these problems applying to the "Mathematica" packages which is composed of mathematic tools, the simplex processes show us the flexible and dynamic decision elements included to any other professional linear programming tools. Especially we need proper dynamic variables to analyze the shadow prices step by step. And applying SAS(Statistical Analysis System) packages to the L.P. problems, it is also one of the best way to get good solution. On the way trying to the other L.P. packages which are prepared for Spreadsheets i.e., MS-Excel, Lotus-123, Quatro etc. can be applied to linear programming models. But they are not so much useful for the problems. Calculating simplex tableau is an important method to interpret L.P. format for the optimal solution. In this paper we find out that the more detailed and efficient techniques to interpret useful software of mathematica and SAS for business decision making of linear programming. So it needs to apply more dynamic technique of using of Mathematica and SAS multiple software to get more efficient deterministic factors for the sophiscated L.P. solutions.

• Coupled systems mechanics
• /
• v.12 no.6
• /
• pp.539-555
• /
• 2023

Although some prediction models have successfully developed for ultra-high performance concrete (UHPC), they do not provide insights and explicit relations between all constituents and its consistency, and compressive strength. In the present study, based on the experimental results, several mathematical models have been evaluated to predict the consistency and the 28-day compressive strength of UHPC. The models used were Linear, Logarithmic, Inverse, Power, Compound, Quadratic, Cubic, Mixed, Sinusoidal and Cosine equations. The applicability and accuracy of these models were investigated using experimental data, which were collected from literature. The comparisons between the models and the experimental results confirm that the majority of models give acceptable prediction with a high accuracy and trivial error rates, except Linear, Mixed, Sinusoidal and Cosine equations. The assessment of the models using numerical methods revealed that the Quadratic and Inverse equations based models provide the highest predictability of the compressive strength at 28 days and consistency, respectively. Hence, they can be used as a reliable tool in mixture design of the UHPC.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.289-298
• /
• 1999

We consider a minimax approach to make a design robust to many types or uncertainty arising in reality when dealing with non-normal linear models. We try to build a design to protect against the worst case, i.e. to improve the "efficiency" of the worst situation that can happen. In this paper, we especially deal with the generalized linear model. It is a known fact that the generalized linear model is a universal approach, an extension of the normal linear regression model to cover other distributions. Therefore, the optimal design for the generalized linear model has very similar properties as the normal linear model except that it has some special characteristics. Uncertainties regarding the unknown parameters, link function, and the model structure are discussed. We show that the suggested approach is proven to be highly efficient and useful in practice. In the meantime, a computer algorithm is discussed and a conclusion follows.

• Journal of Ocean Engineering and Technology
• /
• v.31 no.4
• /
• pp.288-298
• /
• 2017

A study of the damage evolution laws for ductile materials was carried out to predict the ductile fracture behavior of a marine structural steel (EH36). We conducted proportional and non-proportional stress tests in the experiments. The existing 3-D fracture strain surface was newly calibrated using two fracture parameters: the average stress triaxiality and average normalized load angle taken from the proportional tests. Linear and non-linear damage evolution models were taken into account in this study. A damage exponent of 3.0 for the non-linear damage model was determined based on a simple optimization technique, for which proportional and non-proportional stress tests were simultaneously used. We verified the validity of the three fracture models: the newly calibrated fracture strain model, linear damage evolution model, and non-linear damage evolution model for the tensile tests of the asymmetric notch specimens. Because the stress evolution pattern for the verification tests remained at mode I in terms of the linear elastic fracture mechanics, the three models did not show significant differences in their fracture initiation predictions.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.8
• /
• pp.388-394
• /
• 2024

Since recommendation systems play a key role in increasing the revenue of companies, various approaches and models have been studied in the past. However, this diversity also leads to a complexity in the types of recommendation systems, which makes it difficult to select a recommendation model. Therefore, this study aims to solve the difficulty of selecting an appropriate recommendation model for recommendation systems by providing a unified criterion for categorizing various recommendation models and comparing their performance in a unified environment. The experiments utilized MovieLens and Coursera datasets, and the performance of linear models(ADMM-SLIM, EASER, LightGCN) and non-linear models(Caser, BERT4Rec) were evaluated using HR@10 and NDCG@10 metrics. This study will provide researchers and practitioners with useful information for selecting the best model based on dataset characteristics and recommendation context.

• Journal of the Korean Data and Information Science Society
• /
• v.8 no.2
• /
• pp.247-260
• /
• 1997

The quasi-likelihood models which greatly widened the scope of generalized linear models are widely used in data analysis where a likelihood is not available. Since a quasi-likelihood may not appear to be an ordinary likelihood for any known distribution in the natural exponential family, to fit the quasi-likelihood models the standard statistical packages such as GLIM, GENSTAT, S-PLUS and so on may not directly applied. SAS/IML is very useful for fitting of such models. In this paper, we present simple SAS/IML(version 6.11) program which helps to fit and analyze the quasi-likelihood models applied to the leaf-blotch data introduced by Wedderburn(1974), and the problem with deviance useful generally to model checking is pointed out, and then its solution method is mention through the data analysis based on this quasi-likelihood models checking.

• Journal of the Korean Statistical Society
• /
• v.27 no.4
• /
• pp.407-420
• /
• 1998

This paper is concerned with selecting covariates to be included in building linear random effects models designed to analyze clustered response normal data. It is based on a Bayesian approach, intended to propose and develop a procedure that uses probabilistic considerations for selecting premising subsets of covariates. The approach reformulates the linear random effects model in a hierarchical normal and point mass mixture model by introducing a set of latent variables that will be used to identify subset choices. The hierarchical model is flexible to easily accommodate sign constraints in the number of regression coefficients. Utilizing Gibbs sampler, the appropriate posterior probability of each subset of covariates is obtained. Thus, In this procedure, the most promising subset of covariates can be identified as that with highest posterior probability. The procedure is illustrated through a simulation study.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.4
• /
• pp.377-384
• /
• 2007

This paper studies on the relation between linearization methods and controller gains in the looper ILQ(lnverse Linear Quadratic optimal control) system for hot strip finishing mills. Firstly, two linear models arc respectively derived by a linearization method using Taylor's series expansion and a static state feedback linearization method, respectively, and the linear models are compared with the nonlinear model. Secondly, the looper servo controllers are respectively designed on the basis of two linearization models. Finally, the relation between the performances of two ILQ servo controllers and the linearization methods, and the structures and control gains of two controllers are evaluated by a computer simulation.