• Journal of the Korean Data and Information Science Society
• /
• 제21권2호
• /
• pp.363-369
• /
• 2010

In this paper we propose a mixed-effects least squares support vector regression (LS-SVR) for longitudinal data. We add a random-effect term in the optimization function of LS-SVR to take random effects into LS-SVR for analyzing longitudinal data. We also present the model selection method that employs generalized cross validation function for choosing the hyper-parameters which affect the performance of the mixed-effects LS-SVR. A simulated example is provided to indicate the usefulness of mixed-effect method for analyzing longitudinal data.

• 자원환경지질
• /
• 제52권2호
• /
• pp.199-212
• /
• 2019

머신러닝 기법을 활용한 분석에서 훈련 데이터의 샘플링 전략은 예측 정확도 뿐 만 아니라 일반화 능력에도 많은 영향을 미친다. 특히, 산사태 취약성 분석의 경우, 산사태 발생부에 대한 정보에 비해 산사태 미발생부에 대한 정보가 과도하게 많은 데이터 불균형 현상이 발생하며, 이에 따라 분석 모델의 훈련 데이터 설계 시 데이터 샘플링 과정이 필수적이다. 그러나 기존의 연구들은 대부분 산사태 미발생부 선택 시 발생부 데이터와 1:1의 비율을 갖도록 무작위로 선택하는 방법을 적용하였을 뿐, 특정한 선택 기준에 따라 분석을 수행하지 않았다. 따라서 본 연구에서는 훈련 데이터의 샘플링 전략이 모델의 예측 성능에 미치는 결과를 확인하기 위하여 산사태 발생부와 미발생부의 샘플링 전략기준에 따라 서로 다른 6개의 시나리오를 만들어 Random Forest 모델의 훈련에 사용하였다. 또한 Random Forest의 결과 중 하나인 변수 중요도를 각 산사태 유발인자들에 가중치로 곱하여 줌으로써 산사태 취약지수 값을 산정하였으며, 취약지수 값을 이용해 산사태 취약성도를 제작하고 각 결과 지도의 정확도를 비교 분석하였다. 분석 결과, 훈련데이터의 샘플링 방법에 상관없이 두 지역의 산사태 취약성 분석 결과는 모두 70~80%의 정확도를 보였다. 이를 통해 Random Forest 기법의 산사태 취약성 분석기법으로서의 적용 가능성을 확인하였으며, Random Forest 모델이 제공하는 입력변수의 중요도를 산사태 유발인자 가중치로 활용할 수 있음을 확인하였다. 또한 훈련 시나리오 간의 정확도를 비교한 결과, 특정한 기준에 의해 훈련 데이터를 설계하는 것이 기존의 랜덤 선택 방법보다 높은 예측 정확도를 기대할 수 있음을 확인하였다.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제16권2호
• /
• pp.185-190
• /
• 2016

A 70-${\AA}$ nanowire field-effect transistor (FET) for sub-10-nm CMOS technology is designed and simulated in order to investigate the impact of an oxide trap on random telegraph noise (RTN) in the device. It is observed that the drain current fluctuation (${\Delta}I_D/I_D$) increases up to a maximum of 78 % due to the single electron trapping. In addition, the effect of various trap positions on the RTN in the nanowire FET is thoroughly analyzed at various drain and gate voltages. As the drain voltage increases, the peak point for the ${\Delta}I_D/I_D$ shifts toward the source side. The distortion in the electron carrier density and the conduction band energy when the trap is filled with an electron at various positions in the device supports these results.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.115-117
• /
• 2022

피드백 전계 효과 트랜지스터(feedback field-effect transistor; FBFET)로 구성된 모놀리식 3차원 정적 랜덤 액세스 메모리(monolithic 3-dimensional static random access memory; M3D-SRAM)에 대해 TCAD(technology computer-aided design) 프로그램을 사용하여 전기적 특성을 조사하였다. FBFET로 구성된 M3D-SRAM(M3D-SRAM-FBFET)는 FDSOI(fully depleted silicon on insulator) 구조의 N형 FBFET와 N형 MOSFET(metal oxide semiconductor field effect transistor)로 이루어져 있으며 각각 하부와 상부에 위치한다. M3D-SRAM-FBFET의 메모리 동작 시, 공급 전압이 1.9 V에서 감소함에 따라 읽기 전류가 낮아졌으며, 공급 전압이 1.6 V 일 때 읽기 전류가 약 10배 감소하였다.

• Communications for Statistical Applications and Methods
• /
• 제1권1호
• /
• pp.33-40
• /
• 1994

The conditional expectation of a random variable in a multivariate normal random vector is a multiple linear regression on its predecessors. Using this fact, the least median of squares estimation method developed in a multiple linear regression is adapted to a multivariate data to identify influential observations. The resulting method clearly detect outliers and it avoids the masking effect.

• Communications for Statistical Applications and Methods
• /
• 제9권3호
• /
• pp.835-844
• /
• 2002

For the one-way random model when the ratio of the variance components is of interest, Bayesian analysis is often appropriate. In this paper, we develop the noninformative priors for the ratio of the variance components under the balanced one-way random effect model. We reveal that the second order matching prior matches alternative coverage probabilities up to the second order (Mukerjee and Reid, 1999) and is a HPD(Highest Posterior Density) matching prior. It turns out that among all of the reference priors, the only one reference prior (one-at-a-time reference prior) satisfies a second order matching criterion. Finally we show that one-at-a-time reference prior produces confidence sets with expected length shorter than the other reference priors and Cox and Reid (1987) adjustment.

• Structural Engineering and Mechanics
• /
• 제43권6호
• /
• pp.835-845
• /
• 2012

This paper focuses on the stochastic response analysis of industrial masonry chimneys to surface blast-induced random ground motions by using a three dimensional finite element model. Underground blasts induce ground shocks on nearby structures. Depending on the distance between the explosion centre and the structure, masonry structures will be subjected to ground motions due to the surface explosions. Blast-induced random ground motions can be defined in terms of the power spectral density function and applied to each support point of the 3D finite element model of the industrial masonry system. In this paper, mainly a parametric study is conducted to estimate the effect of the blast-induced ground motions on the stochastic response of a chimney type masonry structure. With this purpose, different values of charge weight and distance from the charge centre are considered for the analyses of the chimney. The results of the study underline the remarkable effect of the surface blast-induced ground motions on the stochastic behaviour of industrial masonry type chimneys.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 춘계 학술발표회 논문집
• /
• pp.79-84
• /
• 2003

Likelihood estimation in random-effect models is often complicated because the marginal likelihood involves an analytically intractable integral. Numerical integration such as Gauss-Hermite quadrature is an option, but is generally not recommended when the dimensionality of the integral is high. An alternative is the use of hierarchical likelihood, which avoids such burdensome numerical integration. These two approaches for fitting binary data are compared and the advantages of using the hierarchical likelihood are discussed. Random-effect models for binary outcomes and for bivariate binary-continuous outcomes are considered.

• Asian-Australasian Journal of Animal Sciences
• /
• 제15권5호
• /
• pp.622-626
• /
• 2002

Growth records over six generations of 686 pigs in SD-II Swine Line were used to estimate the genetic and phenotypic covariance functions for body weight as longitudinal data. A random regression model with Legendre polynomials of age as independent variables was used to estimate the (co)variances among the regression coefficients, thus the coefficients of genetic and permanent environmental covariance functions by restricted maximum likelihood employing the average information algorithm. The results showed that, using litter effect as additional random effect, a reduced order of fit did not describe the data adequately. For all five orders of fit, however, the change trends of genetic and phenotypic (co)variances were very similar from ${\kappa}$=3 onwards.

• Journal of the Korean Data and Information Science Society
• /
• 제27권4호
• /
• pp.1083-1090
• /
• 2016

In clinical studies, different types of outcomes (e.g. repeated measures data and time-to-event data) for the same subject tend to be observed, and these data can be correlated. For example, a response variable of interest can be measured repeatedly over time on the same subject and at the same time, an event time representing a terminating event is also obtained. Joint modelling using a shared random effect is useful for analyzing these data. Inferences based on marginal likelihood may involve the evaluation of analytically intractable integrations over the random-effect distributions. In this paper we propose a joint HGLM approach for analyzing such outcomes using the HGLM (hierarchical generalized linear model) method based on h-likelihood (i.e. hierarchical likelihood), which avoids these integration itself. The proposed method has been demonstrated using various numerical studies.