• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.7 no.4
• /
• pp.321-328
• /
• 1995

The FIT(fully implicit tidal) model which adopts PCGCS (preconditioned conjugate gradient squared) method is developed and is applied to near Mokpo Harbor. Comparing computational results with observed velocities and elevations for the M$_2$ tidal constituent, agreeable correspondence is detected. The validity of the model is also proven by applying it to such areas which have narrow width (therefore showing rapid velocity), irregular topography and complex geometry. Tidal amplification phenomenon according to the constructions of seadike and sea-walls is considered by analyzing the 'filter effect' of Mokpo-ku using the model.

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.351-364
• /
• 2003

This paper derives Lagrange multiplier tests based on Double-Length Artificial Regression and Outer-Product Gradient for testing linear and log-linear panel regressions against Box-Cox alternatives. The proposed DLR based LM tests are easy to implement in an error component model. From the Monte Carlo study, the DLR based LM tests are recommended for testing functiona forms.

• Ecology and Resilient Infrastructure
• /
• v.10 no.4
• /
• pp.107-115
• /
• 2023

High turbidity in source water can have adverse effects on water treatment plant operations and aquatic ecosystems, necessitating turbidity management. Consequently, research aimed at predicting river turbidity continues. This study developed a multi-class classification model for prediction of turbidity using LightGBM (Light Gradient Boosting Machine), a representative ensemble machine learning algorithm. The model utilized data that was classified into four classes ranging from 1 to 4 based on turbidity, from low to high. The number of input data points used for analysis varied among classes, with 945, 763, 95, and 25 data points for classes 1 to 4, respectively. The developed model exhibited precisions of 0.85, 0.71, 0.26, and 0.30, as well as recalls of 0.82, 0.76, 0.19, and 0.60 for classes 1 to 4, respectively. The model tended to perform less effectively in the minority classes due to the limited data available for these classes. To address data imbalance, the SMOTE (Synthetic Minority Over-sampling Technique) algorithm was applied, resulting in improved model performance. For classes 1 to 4, the Precision and Recall of the improved model were 0.88, 0.71, 0.26, 0.25 and 0.79, 0.76, 0.38, 0.60, respectively. This demonstrated that alleviating data imbalance led to a significant enhancement in Recall of the model. Furthermore, to analyze the impact of differences in input data composition addressing the input data imbalance, input data was constructed with various ratios for each class, and the model performances were compared. The results indicate that an appropriate composition ratio for model input data improves the performance of the machine learning model.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.6 no.3
• /
• pp.216-225
• /
• 1994

By use of laboratory experiment data set for an elliptic shoal by Berkhoff et al. (1982), both accuracy and Performance tests of numerical results between PCGM (Preconditioned Conjugate Gradient Method) and PA(Parabolic Approximation) are compared. Although both results show good agreement with the experimental data the PA model gives better reproduction of the relatively high amplitudes in the section 4-5 downwave of the shoal, in comparison with the PCGM. The PA model has been proved to be a useful tool for predicting wave transformationsin large shallow water region, but it can be applied only to the case of negligible reflection. On the other hand, there is a need to improve the computational efficiency of the PCGM model which is a finite difference scheme directly derived from the mild slope equation and can handle reflection. By taking the results of th PA model as an input data of the PCGM, the CPU time can be reduced by about 40%.

• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.977-990
• /
• 2015

Food delivery services are well developed in the Republic of Korea, The increase of one person households and the success of app applications influence delivery services these days. We consider a prediction model for the food delivery service based on weather and dates to predict the number of food delivery services in 2014 using various data mining techniques. We use linear regression, random forest, gradient boosting, support vector machines, neural networks, and logistic regression to find the best prediction model. There are four categories of food delivery services and we consider two methods. For the first method, we estimate the total number of delivery services and the posterior probabilities of each delivery service. For the second method, we use different models for each category and combine them to estimate the total number of delivery services. The neural network and linear regression model perform best in the first method, this is followed by the neural network which is the best for the second method. The result shows that we can estimate the number of deliveries accurately based on dates and weather information.

• Journal of the Korea Society for Simulation
• /
• v.18 no.2
• /
• pp.49-55
• /
• 2009

In this paper, we investigate an optimal allocation of constant service resources in stochastic system to optimize the expected performance of interest. For this purpose, we use the control variates to estimate the gradients of expected performance with respect to given resource parameters, and apply these estimated gradients in stochastic optimization algorithm to find the optimal allocation of resources. The proposed gradient estimation method is advantageous in that it uses simulation results of a single design point without increasing the number of design points in simulation experiments and does not need to describe the logical relationship among realized performance of interest and perturbations in input parameters. We consider the applications of this research to various models and extension of input parameter space as the future research.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.180-188
• /
• 2006

수리 전도도는 hydraulic gradient에 대한 flux의 비율 또는, flux-hydraulic gradient 직선의 기울기를 나타내며, 포화된 토양에서의 물의 이동이 포화수리 전도도이고 불포화된 토양에서의 이동이 불포화수리전도도이다. 일반적인 밭 상태에서의 토양수분 조건은 불포화수리 전도도로 표시하는 것이 적절하나 그 상태를 표현하기가 쉽지 않다. 토양의 불포화 상태를 나타내는데 가장 많이 쓰이고 있는 VGM(van Genuchten Mualem) 모형은 토양수분 포텐셜과 수분함량의 함수로 구성된 모형이며 몇 가지 매개변수가 필요하다. VGM 모형의 매개변수를 얻기 위해 본 연구에서는 VGM 모형의 매개변수를 계산해주는 프로그램인 Rosetta를 사용하였다. Rosetta 모형은 신경그물 얼개(neural network)를 이용하여 토양의 물리적 자료들인 토성이나 모래, 미사, 점토 함량 또는 용적밀도나 33kPa, 1500kPa에서의 토양수분 함량 자료를 가지고 VGM의 매개변수인 Ko(effective saturated hydraulic conductivity), ${\theta}r$(residual soil water content), ${\theta}s$(saturated soil water content), L, n, m(=1-1/n)을 예측하는 모형으로 미국 농무성(USDA-ARS)에서 개발한 프로그램이다. Rosetta를 이용하여 10kPa에서의 불포화수리 전도도를 예측하였다. 또한 Gardner(1958)와 Wooding (1968)의 모형을 기반으로 하여 만들어진 tension infiltrometer의 포화수리 전도도 값을 Gardner 식에 적용하여 1, 3, 5, 7kPa에서의 불포화수리 전도도 값을 17개 토양통을 대상으로 하여 구했다. 토양수분 potential이 3kPa에서는 물의 이동이 거의 없는 토양들이 있었는데 반해 남계통을 비롯한 학곡통, 회곡통, 백산통, 상주통, 석천통, 예산통 등 7개의 토양은 3kPa에서도 약간의 물의 이동이 있었다. 이는 모암이 화강 편마암인 관계로 토양 내에 물의 이동에 영향을 미치는 자갈의 함량이 높았기 때문일 것으로 생각되고 추후의 연구에서는 이 부분에 대한 내용도 검토되어야 할 것이다. 또한, 1kPa에서 물의 이동은 삼각통에서 35.21 cm/day로 이동 속도가 가장 컸으며 그 뒤로 예산통, 화봉통, 학곡통, 백산통 등이 토양에서 빠른 속도로 이동하였다. 가천통이나 석천통 및 우곡통은 1kPa에서의 이동 속도가 아주 느린 토양으로 판단되었다. 또한, 포화되지 않은 상태인 1kPa에서 물의 이동 속도를 VGM 모형에 의해 예측된 값과 측정된 값으로 비교하였을 때 불포화 수리 전도도가 예측되지 않은 토양(석천통, 지곡통, 풍천통)이 존재하여 불포화 수리 전도도 특성평가에 대한 VGM 모형의 적용성에 문제를 보였다. 이는 결과적으로 논이라는 영농형태가 존재하는 우리나라에서 토양의 수리적 특성해석을 위한 VGM 모형의 적용성에 한계가 있을 것으로 판단되었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.12
• /
• pp.7350-7356
• /
• 2014

To study the reasonable design thermal loads, a steel box girder bridge specimen, which has no concrete slab, was manufactured with real size dimensions. The temperature data was obtained at the web and diaphragm using thermo gauges that were attached according to height. In the hottest day, the temperature differences between the top and bottom of the bridge model were calculated. The temperatures in the actual bridge were measured and the temperature of the bridge specimen was compared. The temperature gradient models were proposed in both the web and the diaphragm. The proposed models showed a correlation of approximately 95.8% compared to the Euro code. This study can provide basis data for temperature-load design in the nation.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.5
• /
• pp.526-534
• /
• 2004

A new second-moment closure model for turbulent heat fluxes is proposed on the basis of the elliptic equation. The new model satisfies the near-wall balance between viscous diffusion, viscous dissipation and temperature-pressure gradient correlation, and also has the characteristics of approaching its respective conventional high Reynolds number model far away from the wall. The predictions of turbulent heat transfer in a channel flow have been carried out with constant wall heat flux and constant wall temperature difference boundary conditions respectively. The velocity field variables are supplied from the DNS data and the differential equations only fur the mean temperature and the scalar flux are solved by the present calculations. The present model is tested by direct comparisons with the DNS to validate the performance of the model predictions. The prediction results show that the behavior of the turbulent heat fluxes in the whole region is well captured by the present model.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.851-865
• /
• 2017

Ransomware such as WannaCry is a global issue and methods to defend against malware attacks are important. We have to be able to classify the malware types efficiently in order to minimize the damage from malwares. This study makes models to classify malware properly with various statistical techniques. Several classification techniques such as logistic regression, random forest, gradient boosting, and support vector machine are used to construct models. This study also helps us understand key variables to classify the type of malicious software.