• Communications of the Korean Mathematical Society
• /
• v.21 no.3
• /
• pp.543-558
• /
• 2006

We consider a type of large deviation Principle(LDP) using Freidlin-Wentzell exponential estimates for the solutions to perturbed stochastic differential equations(SDEs) driven by Martingale measure(Gaussian noise). We are using exponential tail estimates and exit probability of a diffusion process. Referring to Freidlin-Wentzell inequality, we want to show another approach to get LDP for the solutions to SDEs.

• Communications for Statistical Applications and Methods
• /
• v.20 no.2
• /
• pp.137-145
• /
• 2013

The use of pooled standard deviation can reduce the efficiency loss in optimum allocation when strata standard deviations are estimated and several of them are equal. Also shown is that the pooled standard deviation is useful in optimum allocation under a multivariate setting. In addition to theoretical development, we provide the result of simulation study to support the theory.

• Communications of the Korean Mathematical Society
• /
• v.17 no.1
• /
• pp.71-80
• /
• 2002

We give a formulation of the large deviation property for rescalings of random measures on the d-dimensional Euclidean space R$^{d}$ . The approach is global in the sense that the objects are Radon measures on R$^{d}$ and the dual objects are the continuous functions with compact support. This is applied to the cluster random measures with Poisson centers, a large class of random measures that includes the Poisson processes.

• Proceedings of the KIPE Conference
• /
• 1999.07a
• /
• pp.315-318
• /
• 1999

In the 3-phase PWM converter, accurate detection of the supplied voltage phase is very important. But a detecting circuit cannot avoid generating the deviation of phase detector so that we need to compensate it. In this paper, an accurate and simple compensating method of deviation of phase detector is proposed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.473-476
• /
• 1989

Quadratic weighting matrices have an effect on the transition and steady state responses in a LQ tracking problem. They are usually decided on trial and error in order to get a good response. In this paper a method is presented which calculates a steady - state deviation without solving Riccati equation. By using this method, a new procedure for selecting the weighting matrices is proposed when a tolerance on the steady - state deviation is given.

• Proceedings of the KSR Conference
• /
• 2000.11a
• /
• pp.450-457
• /
• 2000

This paper establishes a scheme to estimate track quality using standard deviation and deterioration rate of track irregularities. To provide index of quality, standard deviation and deterioration rate of track irregularities are analyed. As an index, standard deviation and deterioration rate were applied to decision of corrective maintenance and replacement maintenance, respectively. Further, this paper proposes a basic scheme for a modernization of mechanize track maintenance that using MTT(Multiple Tie Tamper) and Ballast Cleaner.

• Journal of the Korean Mathematical Society
• /
• v.36 no.3
• /
• pp.509-525
• /
• 1999

In this paper we obtain sharp upper and lower bounds of samll ball and large deviation probabilities for the increments of Gaussian processes with stationary increments, whose results are essential to establish Chung type laws of iteratted logarithm.

• Communications for Statistical Applications and Methods
• /
• v.18 no.6
• /
• pp.733-739
• /
• 2011

The linear absolute shrinkage and selection operator(Lasso) method improves the low prediction accuracy and poor interpretation of the ordinary least squares(OLS) estimate through the use of $L_1$ regularization on the regression coefficients. However, the Lasso is not robust to outliers, because the Lasso method minimizes the sum of squared residual errors. Even though the least absolute deviation(LAD) estimator is an alternative to the OLS estimate, it is sensitive to leverage points. We propose a robust Lasso estimator that is not sensitive to outliers, heavy-tailed errors or leverage points.

• Communications for Statistical Applications and Methods
• /
• v.17 no.6
• /
• pp.803-810
• /
• 2010

The singular value decomposition of a rectangular matrix is a basic tool to understand the structure of the data and particularly the relationship between row and column factors. However, conventional singular value decomposition used the least squares method and is not robust to outliers. We propose a simple robust singular value decomposition algorithm based on the weighted least absolute deviation which is not sensitive to leverage points. Its implementation is easy and the computation time is reasonably low. Numerical results give the data structure and the outlying information.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.117-118
• /
• 2022

High-strength concrete is used for building durability on the coast. It is common to order and produce the concrete from several ready mixed concrete companies. The concrete in Busan was also commissioned by 12 ready mixed concrete companies. The compressive strength and salt diffusion coefficient were measured. The average value and deviation were analyzed.