• Journal of Korea Water Resources Association
• /
• v.40 no.9
• /
• pp.677-685
• /
• 2007

The objective of this study is to evaluate the applicability of multi-objective genetic algorithm(MOGA) in order to calibrate the parameters of conceptual rainfall-runoff model, Tank model. NSGA-II, one of the most imitating MOGA implementations, is combined with Tank model and four multi-objective functions such as to minimize volume error, root mean square error (RMSE), high flow RMSE, and low flow RMSE are used. When NSGA-II is employed with more than three multi-objective functions, a number of Pareto-optimal solutions usually becomes too large. Therefore, selecting several preferred Pareto-optimal solutions is essential for stakeholder, and preference-ordering approach is used in this study for the sake of getting the best preferred Pareto-optimal solutions. Sensitivity analysis is performed to examine the effect of initial genetic parameters, which are generation number and Population size, to the performance of NSGA-II for searching the proper paramters for Tank model, and the result suggests that the generation number is 900 and the population size is 1000 for this study.

• The KIPS Transactions:PartB
• /
• v.12B no.5 s.101
• /
• pp.567-576
• /
• 2005

This paper proposes an image-based modeling method which recovers 3D models using projected line segments in multiple images. Using the method, a user obtains accurate 3D model data via several steps of simple manual works. The embedded nonlinear minimization technique in the model parameter estimation stage is based on the distances between the user provided image line segments and the projected line segments of primitives. We define an error using a finite line segment and thus increase accuracy in the model parameter estimation. The error is defined as the sum of differences between the observed image line segments provided by the user and the predicted image line segments which are computed using the current model parameters and camera parameters. The method is robust in a sense that it recovers 3D structures even from partially occluded objects and it does not be seriously affected by small measurement errors in the reconstruction process. This paper also describesexperimental results from real images and difficulties and tricks that are found while implementing the image-based modeler.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.9 no.3 s.43
• /
• pp.33-42
• /
• 2005

Frequency domain Volterra model is applied to nonlinear parameter identification procedure for dynamic systems modeled by nonlinear function. The frequency domain Volterra kernels, which correspond io linear, quadratic, and cubic transfer functions in lime domain, are incorporated in nonlinear parametric identification procedure. The nonlinear transfer functions, which can be derived from the Volterra series representation of the nonlinear differential equation of the system by Schetzen's method(1980), are directly used for modeling input output relation. The error is defined by the difference between the observed output and the estimated output which is calculated by substituting the observed input to nonlinear frequency domain model. The system parameters are searched by minimizing the error. Volterra model guarantees enough accuracy and convergence and the estimated coefficients have a good agreement with their actual values not only in the linear frequency region but also in the legion where the $2^{nd}\;or\;3^{rd}$ order nonlinearity is dominant.

• Journal of Navigation and Port Research
• /
• v.29 no.5 s.101
• /
• pp.409-413
• /
• 2005

The existing control techniques for the operation of a container crane satisfy the terminal condition of controlled variables, but the outcome of input computation is inadequate for the operation of the crane due to heavy movement of inputs. In this study, a new control technique employing a nonlinear model of the crane is proposed to compute the inputs approximated with the 4th-order Chevyshev function. The control objective of sum of absolute deviations is minimized, and the optimization is conducted with the simplex algorithm. The inputs and outputs computed from the proposed technique were compared with the results of the previous study to show that they give more stable crane operation than the existing control technique.

• Journal of the Korean Data and Information Science Society
• /
• v.9 no.2
• /
• pp.345-355
• /
• 1998

The back propagation(BP) algorithm allows multilayer feedforward neural networks to learn input-output mappings from training samples. It iteratively adjusts the network parameters(weights) to minimize the sum of squared approximation errors using a gradient descent technique. However, the mapping acquired through the BP algorithm may be corrupt when errorneous training data are employed. In this paper two types of robust backpropagation algorithms are discussed both from a theoretical point of view and in the case studies of nonlinear regression function estimation and handwritten Korean character recognition. For future research we suggest Bayesian learning approach to neural networks and compare it with two robust backpropagation algorithms.

• Journal of KIISE:Information Networking
• /
• v.32 no.4
• /
• pp.433-442
• /
• 2005

An increase In traffic has a large Influence on the performance of a total network. Therefore, traffic management has become an important issue of network management. In this paper, we propose a new routing algorithm that attempts to analyze network conditions using time series prediction models and to propose predictive optimal routing decisions. Traffic congestion is assumed when the predicting result is bigger than the permitted bandwidth. By collecting traffic in real network, the predictable model is obtained when it minimizes statistical errors. In order to predict network traffic based on time series models, we assume that models satisfy a stationary assumption. The stationary assumption can be evaluated by using ACF(Auto Correlation Function) and PACF(Partial Auto Correlation Function). We can obtain the result of these two functions when it satisfies the stationary assumption. We modify routing oaths by predicting traffic in order to avoid traffic congestion through experiments. As a result, Predicting traffic and balancing load by modifying paths allows us to avoid path congestion and increase network performance.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.733-745
• /
• 2017

Local composite quantile regression is a useful non-parametric regression method widely used for its high efficiency. Data smoothing methods using kernel are typically used in the estimation process with performances that rely largely on the smoothing parameter rather than the kernel. However, $L_2$-norm is generally used as criterion to estimate the performance of the regression function. In addition, many studies have been conducted on the selection of smoothing parameters that minimize mean square error (MSE) or mean integrated square error (MISE). In this paper, we explored the optimality of selecting smoothing parameters that determine the performance of non-parametric regression models using local linear composite quantile regression. As evaluation criteria for the choice of smoothing parameter, we used mean absolute error (MAE) and mean integrated absolute error (MIAE), which have not been researched extensively due to mathematical difficulties. We proved the uniqueness of the optimal smoothing parameter based on MAE and MIAE. Furthermore, we compared the optimal smoothing parameter based on the proposed criteria (MAE and MIAE) with existing criteria (MSE and MISE). In this process, the properties of the proposed method were investigated through simulation studies in various situations.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2329-2331
• /
• 2004

본 논문에서는 이동 로봇의 경로 추종 제어를 위해 웨이블릿 신경 회로망에 기반한 예측 제어기의 설계 방법을 제안하고자 한다. 제안한 방법에 의해 설계된 제어기는 이동 로봇의 동특성을 예측하기 위한 웨이블릿 신경회로망 기반 예측기와 예측 제어기로 구성된다. 제안한 방법에서 모델링 및 제어기로 적용되는 신경 회로망의 장점과 우수한 해석 능력을 가진 웨이블릿 변환의 장점을 결합한 웨이블릿 신경 회로망을 이용하여 이동 로븟의 동특성을 모델링하여 예측 제어기에서의 비용 함수 최소화에 적용한다. 경로 추종 제어의 목적인 이동 로봇의 실제 출력과 예측기의 출력 오차를 최소화하기 위해 웨이블릿 신경 회로망의 파라미터 동정 및 예측 제어기는 경사 하강법을 이용하여 학습한다. 마지막으로 컴퓨터 모의 실험을 통하여 제안한 예측 제어 시스템의 적용가능성 및 효율성을 검증하고자 한다.

• The Korean Journal of Rheology
• /
• v.9 no.2
• /
• pp.66-72
• /
• 1997

사출성형품의 품질특성으로 외관, 치수, 기계적 강도 등이 있으나 조립부품으로써 사 될경우에는 치수가 주요한 품질이 된다. 성형품은 용융수지의 특성상 사출공정 중 수축을 일으키므로 이를 고려해서 금형설계가 이루어지지만 실제 사출과정에서 공정변수를 최적화 하여 관리하지 않으면 허용오차 내의 치수를 얻기가 힘들다. 본 논문에서는 주요조립부의 치수가 허용오차 내에서 얻어지도록 설계시 적용된 수축률과 측정된 수축률의 차이를 목적 함수로 하여 최소화 시키며 반복이차계획 알고리즘을 채택한 IDESIGN 프로그램을 이용해 최적 사출성형조건을 구하였다. 제약조건은 성형품의 부위별 수축률 편차 및 싱크마크 깊이 가 공정변수의 부등호 제약식으로 도출되었고 성형이 이루어지는 공정변수의 상하한 값이 최대 및 최소 경계값으로 적용되었다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.430-433
• /
• 2004

The ophthalmic lens manufacturing processes need to extract the aspherical surface equation from the unknown surface since its real profile can be adjusted by the process variables to make the ideal curve without the optical aberration. This paper presents a procedure to get the aspherical surface equation of an aspherical ophthalmic lens. Aspherical form generally consists of the Schulz formula to describe its profile. Therefore, the base curvature, conic constant, and high-order polynomial coefficient should be set to the original design equation. To find an estimated aspherical profile, firstly lens profile is measured by a contact profiler, which has a sub-micrometer measurement resolution. A mathematical tool is based on the minimization of the error function to get the estimated aspherical surface equation from the scanned aspherical profile. Error minimization step uses the Nelder-Mead simplex (direct search) method. The result of the refractive power measurement is compared with the curvature distribution on the estimated aspherical surface equation