• Journal of Korea Water Resources Association
• /
• v.46 no.5
• /
• pp.449-463
• /
• 2013

This study proposes the method for determining the Muskingum channel routing model parameters based on the assumption of linear system. The proposed method was applied to the Chungju dam basin for the evaluation. Additionally, the rainfall-runoff was repeated for the Yeongchun-Chungju dam reach using seven rainfall events observed. Summarizing the results is as follows. First, the concentration time and storage coefficient of a channel reach formed by the subdivision can be expressed as the difference between the concentration times and storage coefficients of upstream and downstream basins. The storage coefficients of the channel reach estimated is equal to the storage coefficient of the Muskingum channel routing model and the weight factor can be simply estimated using the ratio between the concentration time and storage coefficient. Second, the weight factor of the Muskingum model is in inverse proportion to the Russel coefficient, which is in between 0.4166 and 0.625 when considering the Russel coefficients generally applied. Finally the application to the Yeongchun-Chungju dam reach showed that the proposed method is still valid regardless of the limitations such as the uncertainty of the observed data.

• Annual Conference of KIPS
• /
• 2008.11a
• /
• pp.27-29
• /
• 2008

시스템 분석에 주로 사용하는 자료 중에는 비선형 자료와 시계열 등이 있다. 이들 자료는 그 함축적인 관계가 매우 복잡하여 전통적인 통계분석 도구로 분석하는데 어려움이 많다. 본 연구에서는 현실 세계에서 다양하게 나타나는 복잡성을 다루기 위하여 하이브리드 진화 신경망 모델링 접근 방법으로 자료를 모형화 하고 이를 통한 학습의 적합도를 살펴본다. 비선형 자료 등을 모형화하기 위한 학습은 역전파 신경망 기법을 이용한다. 학습의 효율을 높이기 의해서 격자감소 학습 알고리즘과 함께 이용하는 유전자 알고리즘은 네트워크 구조를 최적화 시킬 수 있는 초기가중값을 이용한 전역 최소값을 찾는데 이용한다. 학습 결과를 통해 제안된 하이브리드형 접근방법의 학습이 보다 효율적임을 살펴보기 위하여 유전자 알고리즘으로 최적화된 신경망 학습 알고리즘을 비선형 모의자료의 학습에 적용하여 보았다.

• The Korean Journal of Applied Statistics
• /
• v.16 no.1
• /
• pp.55-69
• /
• 2003

In this article, we propose the weighted LAD (least absolute deviations) estimators for multi-dimensional contingency tables and drive an estimation method to estimate the proposed estimators. To illustrate the robustness of the estimators, simulation results are presented for several models Including log-linear models and models for ordinal variables in multidimensional contingency tables. Examples were also introduced.

• Journal of Wetlands Research
• /
• v.18 no.2
• /
• pp.148-153
• /
• 2016

Hydraulic and hydrological flood routing methods are commonly used to analyze temporal and spatial flood influences of flood wave through a river reach. Hydrological flood routing method has relatively more simple and reasonable performance accuracy compared to the hydraulic method. Storage constant used in Muskingum method widely applied in hydrological flood routing is very similar to the travel time. Focusing on this point, in this study, we estimate the travel time from HEC-RAS results to estimate storage constant, and develop a non-linear regression equation for the travel time using reach length, channel slope, and discharge. The estimated flow by Muskingum model with storage constant of nonlinear equation is compared with the flow calculated by applying the HEC-RAS 1-D unsteady flow simulation. In addition, this study examines the effect on the weighting factor changes and interval reach divisions; peak discharge increases with the bigger weighting factor, and RMSE decreases with the fragmented division.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.141-150
• /
• 2015

Graphical paradigms for assessing the adequacy of models in logistic regression are discussed. The residual plot has been widely used as a graphical tool for evaluating the adequacy of the model. However, this approach works well only for linear models with constant variance, and the alternative approach, the marginal model plot, has its defects as well. We suggest a Chi-residual plot that overcomes the potential shortcomings of the marginal model plot.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.595-611
• /
• 2016

We use nonlinear regression models (such as the Hill Model) when we analyze data in toxicology and/or pharmacology. In nonlinear regression models an estimator of parameters and estimation of measurement about uncertainty of the estimator are influenced by the variance structure of the error. Thus, estimation methods should be different depending on whether the data are homoscedastic or heteroscedastic. However, we do not know the variance structure of the error until we actually analyze the data. Therefore, developing estimation methods robust to the variance structure of the error is an important problem. In this paper we propose a method to estimate parameters in nonlinear regression models based on a preliminary test. We define an estimator which uses either the ordinary least square estimation method or the iterative weighted least square estimation method according to the results of a simple preliminary test for the equality of the error variance. The performance of the proposed estimator is compared to those of existing estimators by simulation studies. We also compare estimation methods using real data obtained from the National Toxicology program of the United States.

• The Korean Journal of Applied Statistics
• /
• v.36 no.4
• /
• pp.295-307
• /
• 2023

The heterogeneous autoregressive (HAR) model is a simple linear model that is commonly used to explain long memory in the realized volatility. However, as realized volatility has more complicated features such as conditional heteroscedasticity, leverage effect, and volatility clustering, it is necessary to extend the simple HAR model. Therefore, to better incorporate the stylized facts, we propose a threshold HAR model with GARCH errors, namely the THAR-GARCH model. That is, the THAR-GARCH model is a nonlinear model whose coefficients vary according to a threshold value, and the conditional heteroscedasticity is explained through the GARCH errors. Model parameters are estimated using an iterative weighted least squares estimation method. Our simulation study supports the consistency of the iterative estimation method. In addition, we show that the proposed THAR-GARCH model has better forecasting power by applying to the realized volatility of major 21 stock indices around the world.

• The Korean Journal of Applied Statistics
• /
• v.23 no.6
• /
• pp.1235-1243
• /
• 2010

This study proposes a trimmed LAD(least absolute deviation) estimators for multi-dimensional contingency tables and suggests an algorithm to estimate it. In addition, a method to determine the trimming quantity of the estimators is suggested. A Monte Carlo study shows that the propose method yields a better trimming rate and coverage rate than the previously suggest method based on the determinant of the covariance matrix.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.446-446
• /
• 2022

본 연구에서는 MODIS(MODerate resolution Imaging Spectroradiometer) 다중 위성영상을 기반으로 전국 시공간 토양수분 및 토양수분 기반의 가뭄지수 SWDI(Soil Water Deficit Index)를 산정하였다. 시공간 토양수분의 산정을 위해 입력자료로 MODIS 위성의 지표면온도(Land Surface Temperature, LST), 증발산 및 식생(Enhanced Vegetation Index, EVI; Fraction of Photosynthetically Active Radiation, FPAR; Leaf Area Index, LAI; Normalized Difference Vegetation Index, NDVI) 관련 산출물 자료와 지상 관측자료인 일 단위 강수량 자료를 구축하였다. MODIS 위성영상은 산출물별로 제공되는 QC(Quality Control) 영상을 활용해 보정을 수행하였고, 공간 강수량 자료는 기상청에서 제공하는 전국 92개 지점의 종관기상관측자료를 구축하여 공간보간기법인 역거리가중법을 적용해 생성하였다. 실측 토양수분은 농촌진흥청에서 제공하는 76개 지점의 토양 깊이 10 cm에 설치된 TDR(Time Domain Reflectomerty) 센서에서 측정된 토양수분 자료를 활용하였으며, 토양수분 모의 시 토양 속성을 고려하기 위해 국립농업과학원에서 제공하는 토양도를 구축하여 활용하였다. 토양수분 산정 모형은 다중선형회귀모형(Multiple Linear Regression Model, MLRM)을 활용하였으며, 계절 및 토성에 따른 회귀식을 산정하였다. 회귀식 기반의 토양수분과 토성별 포장용수량 및 영구위조점 값을 이용하여 SWDI를 산정하고, 실제 가뭄 발생 시기 및 지역과의 비교하고자 한다.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.343-348
• /
• 2005

The goal of this paper is to study the joint effect of factors of neural network teaming procedure. There are many factors, which may affect the generalization ability and teaming speed of neural networks, such as the initial values of weights, the learning rates, and the regularization coefficients. We will apply a constructive training algerian for neural network, then patterns are trained incrementally by considering them one by one. First, we will investigate the effect of these factors on generalization performance and learning speed. Based on these factors' effect, we will propose a joint method that simultaneously considers these three factors, and dynamically hue the learning rate and regularization coefficient. Then we will present the results of some experimental comparison among these kinds of methods in several simulated nonlinear data. Finally, we will draw conclusions and make plan for future work.