• 응용통계연구
• /
• 제25권6호
• /
• pp.1037-1047
• /
• 2012

The generalized linear mixed model(GLMM) is widely used in fitting categorical responses of clustered data. In the numerical approximation of likelihood function the normality is assumed for the random effects distribution; subsequently, the commercial statistical packages also routinely fit GLMM under this normality assumption. We may also encounter departures from the distributional assumption on the response variable. It would be interesting to investigate the impact on the estimates of parameters under misspecification of distributions; however, there has been limited researche on these topics. We study the sensitivity or robustness of the maximum likelihood estimators(MLEs) of GLMM for counts data when the true underlying distribution is normal, gamma, exponential, and a mixture of two normal distributions. We also consider the effects on the MLEs when we fit Poisson-normal GLMM whereas the outcomes are generated from the negative binomial distribution with overdispersion. Through a small scale Monte Carlo study we check the empirical coverage probabilities of parameters and biases of MLEs of GLMM.

• 반도체디스플레이기술학회지
• /
• 제17권4호
• /
• pp.51-55
• /
• 2018

As the OLED industry develops, display equipment is becoming larger. As a result, the stage required for display equipment is getting bigger. This enlargement led to increase in OLED production and industrial development. However, due to the large scale of the stage, other problems due to overheating and overheating caused by heavy load on the linear motor, which is mainly used in the stage, must be solved. In this study, a linear motor equipped with a cooling channel is modeled and the three - dimensional heat conduction flow analysis for this model is simulated using Fluent to analyze the cooling efficiency and cooling efficiency according to the cooling water flow rate. As a result, the cooling channel was effective and the cooling effect and efficiency were the best when the flow rate was about 5 ~ 10 L./min. In addition, the cooling effect is increased when the flow rate is increased, but the efficiency is significantly lowered when the flow rate is more than the predetermined value.

• Smart Structures and Systems
• /
• 제23권1호
• /
• pp.71-79
• /
• 2019

In general, it may be advantageous to measure the pressure pulsation near a valve to detect a valve defect in a linear compressor. However, the acceleration signals are more advantageous for rapid classification in a mass-production line. This paper deals with the performance improvement of fault classification using only the compressor-shell acceleration signal based on the relation between the refrigerant pressure pulsation and the shell acceleration of the compressor. A transfer function was estimated experimentally to take into account the signal noise ratio between the pressure pulsation of the refrigerant in the suction pipe and the shell acceleration. The shell acceleration signal of the compressor was modified using this transfer function to improve the defect classification performance. The defect classification of the modified signal was evaluated in the acceleration signal in the frequency domain using Fisher's discriminant ratio (FDR). The defect classification method was validated by experimental data. By using the method presented, the classification of valve defects can be performed rapidly and efficiently during mass production.

• 대한한방부인과학회지
• /
• 제21권1호
• /
• pp.216-230
• /
• 2008

Purpose: The purpose of this study is to analysis on the Stress Response Inventory(SRI) and Heart Rate Variability (HRV) of some dysmenorrhoea patients. Methods: We studied 34 patients visiting OO Medical Center from May 2007 to November 2007. And the severity of dysmenorrhoea were measured by Multidimensional Verbal Rating scale(MVRS), Verbal Rating scale (VRS) and Visual Analog Scale(VAS). And SRI and HRV were recorded. Results: According to comparison of Means of HRV values among the groups, most of them were not statistically significant. But the comparison of Means of SRI, the points of almost all values were kept by order of Severe-Moderate-Mild-None group. Most of them are statistically significant. According to correlation analysis between dysmenorrhoea scale and HRV, most of them were not statistically significant. But the correlation analysis between HRV and SRI, there were some correlations. And the correlation analysis between SRI and dysmenorrhoea scale, most of them were statistically significant. According to General Linear Model of Dysmenorrhoea $scale^{\ast}SRI$ and HRV. Dysmenorrhoea scale and SRI influenced values of HRV. But it is hard to conclude the relationship between Dysmenorrhoea $scale^{\ast}SRI$ and HRV Conclusion: The results suggest that stress is related to dysmenorrhoea. But the relation between dysmenorrhoea and HRV was hard to conclude. We need more study for settling the relation between dysmenorrhoea and HRV.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1986년도 하계학술대회논문집
• /
• pp.136-139
• /
• 1986

• Journal of the Korean Data and Information Science Society
• /
• 제14권4호
• /
• pp.799-803
• /
• 2003

We obtained the best linear unbiased estimator for the scale parameter of the generalized Pareto Distribution by the order statistics.

• 대한전기학회논문지
• /
• 제35권8호
• /
• pp.333-340
• /
• 1986

This paper presents an approach for determining the discrete reduced-order models for largescale system by using matrix sign function. We define projection operators based on the matrix sign function and develop the algorithm for model-reduction by using them. Simulation studies show that the proposed altgorithm is very useful.

• 한국자기학회:학술대회 개요집
• /
• 한국자기학회 2002년도 동계연구발표회 논문개요집
• /
• pp.16-16
• /
• 2002

Granular metal-insulator alloys, consisting of nano-scale magnetic particles in an insulating matrix are of unique consideration for the technological application and fundamental physics. They display a wide variety of unusual both linear and nonlinear electric-transport, optical and magnetooptical properties, especially for compositions close to the percolation threshold. (omitted)

• 대한기계학회논문집A
• /
• 제30권1호
• /
• pp.66-75
• /
• 2006

Nonlinear response structural optimization using equivalent static loads (NROESL) has been proposed. Nonlinear response optimization is solved by sequential linear response optimization with equivalent static loads which are generated from the nonlinear responses and linear stiffness matrix. The linear stiffness matrix should be obtained in NROESL, and this process can be fairly difficult for some applications. Proportional transformation of loads (PTL) is proposed to overcome the difficulties. Equivalent static loads are obtained by PTL. It is the same as NROESL except for the process of calculating equivalent static loads. PTL is developed for large-scale probems. First, linear and nonlinear responses are evaluated from linear and nonlinear analyses, respectively. At a DOF of the finite element method, the ratio of the two responses is calculated and an equivalent static load is made by multiplying the ratio and the loads for linear analysis. Therefore, the mumber of the equivalent static loads is as many as that of DOF's and an equivalent static load is used with the reponse for the corresponding DOF in the optimization process. All the equivalent static loads are used as multiple loading conditions during linear response optimization. The process iterates until it converges. Examples are solved by using the proposed method and the results are compared with conventional methods.

• Coupled systems mechanics
• /
• 제7권5호
• /
• pp.509-524
• /
• 2018

A hierarchical multi-scale modeling strategy devoted to the study of a Bitumen-Bound Gravel (BBG) is presented in this paper. More precisely, the paper investigates the temperature-dependent linear viscoelastic of the material when submitted to low deformations levels and moderate number of cycles. In such a hierarchical approach, 3D digital Representative Elementary Volumes are built and the outcomes at a scale (here, the sub-mesoscale) are used as input data at the next higher scale (here, the mesoscale). The viscoelastic behavior of the bituminous phases at each scale is taken into account by means of a generalized Maxwell model: the bulk part of the behavior is separated from the deviatoric one and bulk and shear moduli are expanded into Prony series. Furthermore, the viscoelastic phases are considered to be thermorheologically simple: time and temperature are not independent. This behavior is reproduced by the Williams-Landel-Ferry law. By means of the FE simulations of stress relaxation tests, the parameters of the various features of this temperature-dependent viscoelastic behavior are identified.