• Communications for Statistical Applications and Methods
• /
• v.26 no.6
• /
• pp.611-622
• /
• 2019

This paper considers the estimation of the long memory parameter in nonparametric regression with strongly correlated errors. The key idea is to minimize a unified mean squared error of long memory parameter to select both kernel bandwidth and the number of frequencies used in exact local Whittle estimation. A unified mean squared error framework is more natural because it provides both goodness of fit and measure of strong dependence. The block bootstrap is applied to evaluate the mean squared error. Finite sample performance using Monte Carlo simulations shows the closest performance to the oracle. The proposed method outperforms existing methods especially when dependency and sample size increase. The proposed method is also illustreated to the volatility of exchange rate between Korean Won for US dollar.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.11a
• /
• pp.209-214
• /
• 2001

Most reinforce concrete Columns of Building structure are subjected to both axial load and biaxial bending. However, It is hard to estimate the moment capacity of biaxial bending by exact solution. Thus, columns under biaxial bending are designed by approximate methods in practice. The purpose of this study is to compare experimental result with approximate methods and exact solution by computer. Parameters of the present test are compressive strength of concrete (350, 585, 650kgf/$\textrm{cm}^2$) and shape ratio of rectangular section. Ultimately, an experimental shape factor for rectangular RC column section is obtained through the test program. The shape of load contour is dominated by this shape factor obtained experimentally. So, reasonable design of RC columns subjected to both axial compression and biaxial bending depends on load contour.

• Journal of the Korean Mathematical Society
• /
• v.57 no.5
• /
• pp.1239-1266
• /
• 2020

In this paper, some novel discrete formulations for stabilizing the mixed finite element method Q1-Q0 (bilinear velocity and constant pressure approximations) are introduced and discussed for the generalized Stokes problem. These are based on stabilizing discontinuous pressure approximations via local jump operators. The developing idea consists in a reduction of terms in the local jump formulation, introduced earlier, in such a way that stability and convergence properties are preserved. The computer implementation aspects and numerical evaluation of these stabilized discrete formulations are also considered. For illustrating the numerical performance of the proposed approaches and comparing the three versions of the local jump methods alongside with the global jump setting, some obtained results for two test generalized Stokes problems are presented. Numerical tests confirm the stability and accuracy characteristics of the resulting approximations.

• Publications of The Korean Astronomical Society
• /
• v.13 no.1 s.14
• /
• pp.167-180
• /
• 1998

We have carried out high precision orbit calculation, by using various numerical techniques with accuracy of higher than fourth order, in order for exact prediction on position and velocity of celestial bodies and artificial satellites. General second order ordinary differential equation has been solved numerically to test the performance for each of numerical methods. We have compared computed values with exact solution obtained by using universal variables for two body problem and discussed overall results of numerical methods used in our calculation. As a result, it is found that high order difference table method called as Gauss-Jackson method is best one with easiness and efficiency in the increase of accuracy by number of initial values.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1997.10a
• /
• pp.799-803
• /
• 1997

Smell and sound are closely connected with our life. But there is no way to represent the exact numerical value of smell. On the contary, there is a method of represent the exact numerical value of sound. In this thesis, using and adapting this method about sound, a new method of expressing the numercal value of smell is going to be derived. These two methods are similar, but there are so many substances which emit smells and the methods of measuring the density of the substances are various according to kinds of the substances. So the new method about smell will be derived by a new idea.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.193-196
• /
• 1992

When there exist parameter uncertainty, modelling errors and nonminimum phase zeros in control object system. the stability robustness of conventional LQG and LOG/LTR methods are not satisfactory[2, 8]. Since these methods are performed on the infinite horizon, it is very hard to establish exact design parameters and thus they have lots of problems to be applied to real systems, So in this paper we propose RHLQG/FIRF optimal controller which has robust stability against parameter uncertainty, nonminimum phase zeros and modelling errors. This method uses only the information around at present and therefore shows good performance even when we do not know exact design parameters. We here compare LQG and LQG/LTR method with RHLQG/FIRF controller and exemplify that RHLQG/FIRF controller has better robust stability performance via simulations.

• Korean Journal of Hydrosciences
• /
• v.5
• /
• pp.85-97
• /
• 1994

A hybrid finite difference method for the longitudinal dispersion equation, which is based on combining the Holly-Preissmann scheme with fifth-degree Hermite interpolating polynomial and the generalized Crank-Nicholson scheme, is described and comparatively evaluated with other characteristics-based numerical methods. Longitudinal dispersion of an instantaneously-loaded pollutant source is simulated, and computational results are compared with the exact solution. The present method is free from wiggles regardless of the Courant number, and exactly reproduces the location of the peak concentration. Overall accuracy of the computation increases for smaller value of the weighting factor, $\theta$of the model. Larger values of $\theta$ overestimates the peak concentration. Smaller Courant number yields better accuracy, in general, but the sensitivity is very low, especially when the value of $\theta$ is small. From comparisons with the hybrid method using cubic interpolating polynomial and with splitoperator methods, the present method shows the best performance in reproducing the exact solution as the advection becomes more dominant.

• Bulletin of the Korean Chemical Society
• /
• v.6 no.3
• /
• pp.168-170
• /
• 1985

The pairing properties of electronic structure are investigated from ab initioists' point of view. Numerical results of exact ab initio effective valence shell Hamiltonian are compared with simple semiempirical Hamiltonian calculations. In the oxygen atom case it was found that effective three-electron interaction terms break the similarity between electron-states and hole-states. With the trans-butadiene as an example the pairing theorem was studied. Even for alternant hydrocarbons, the deviation from the pairing was found to be enormous. The pairing theorem, which is usually stated for semiempirical Hamiltonians, is not valid when the exact effective Hamiltonian is considered. The present study indicates that comparisons between the pairing theorem of semiempirical methods and ab initio effective Hamiltonian give important information on the accuracy of semiempirical methods.

• Honam Mathematical Journal
• /
• v.45 no.4
• /
• pp.619-628
• /
• 2023

In this paper, the fractional order time-varying linear dynamical systems are investigated by using a residual power series method. A residual power series method (RPSM) is constructed for this problem. The exact solution is obtained by the Laplace transform method and the analytical solution is calculated via the residual power series method (RPSM). As an application, some examples are tested to show the accuracy and efficacy of the proposed methods. The obtained result showed that the proposed methods are effective and accurate for this type of problem.

• Communications of the Korean Mathematical Society
• /
• v.17 no.4
• /
• pp.693-708
• /
• 2002

We generalize algebraic results of Nielsen fixed point theory to Nielsen coincidence theory. We use the algebraic methods of D. Ferrario in Nielsen fixed point theory.