• Journal of the Korean Statistical Society
• /
• 제23권2호
• /
• pp.463-482
• /
• 1994

In Bayesian analysis of randomized response models, the likelihood function does not combine tractably with typical priors for the parameters of interest, causing computational difficulties in posterior analysis of the parameters of interest. In this article, the difficulties are solved by introducing appropriate latent variables to the model and using the Gibbs sampling algorithm.

• Nuclear Engineering and Technology
• /
• 제46권1호
• /
• pp.55-62
• /
• 2014

A method for estimating software reliability for nuclear safety software is proposed in this paper. This method is based on the software reliability growth model (SRGM), where the behavior of software failure is assumed to follow a non-homogeneous Poisson process. Two types of modeling schemes based on a particular underlying method are proposed in order to more precisely estimate and predict the number of software defects based on very rare software failure data. The Bayesian statistical inference is employed to estimate the model parameters by incorporating software test cases as a covariate into the model. It was identified that these models are capable of reasonably estimating the remaining number of software defects which directly affects the reactor trip functions. The software reliability might be estimated from these modeling equations, and one approach of obtaining software reliability value is proposed in this paper.

• 한국지능시스템학회논문지
• /
• 제11권9호
• /
• pp.849-854
• /
• 2001

Bishop이 제안한 Generative Topographic Mapping(GTM)은 Kohonen이 제안한 자율 학습 신경망인 Self Organizing Maps(SOM)의 확률 버전이다. GTM은 데이터가 생성되는 확률 분포를 잠재 변수, 혹은 은닉 변수를 사용하여 모형화한다. 이것은 SOM에서는 구현될 수 없는 GTM만의 특징이며, 이러한 특징으로 인하여 SOM의 한계들을 극복할 수 있게 된다. 본 논문에서는 이러한 GTM 모형에 베이지안 학습(Bayesian learning)을 결합하여 작은 오분류율을 가지는 분류 알고리즘인 베이지안 GTM(Bayesian GTM)을 제안한다. 이 알고리즘은 기존의 GTM의 빠른 계산 처리 능력과 데이터에 대한 확률 분포, 그리고 베이지안 추론의 정확성을 이용하여 기존의 분류 알고리즘보다 우수한 결과를 얻게 된다. 본 논문에서는 기존의 분류 알고리즘에서 많이 실험하였다. 학습 데이터를 통하여 이를 확인하였다.

• Communications for Statistical Applications and Methods
• /
• 제6권1호
• /
• pp.169-180
• /
• 1999

A Markov Chain Monte Carlo method with development of computation is used to be the software system reliability probability model. For Bayesian estimator considering computational problem and theoretical justification we studies relation Markov Chain with Gibbs sampling. Special case of GOS with Superposition for Goel-Okumoto and Weibull models using Gibbs sampling and Metropolis algorithm considered. In this paper discuss Bayesian computation and model selection using posterior predictive likelihood criterion. We consider in this paper data using method by Cox-Lewis. A numerical example with a simulated data set is given.

• Journal of the Korean Data and Information Science Society
• /
• 제27권5호
• /
• pp.1133-1146
• /
• 2016

공간통계 방법 중 지역에 대한 어떤 집합체 자료나 평균자료들을 분석하는데 일반적으로 공간적 자기회귀 (conditionally autoregressive) 모형을 사용한다. 공간적 자기회귀 모형에 정의되는 공간적 이웃 소지역들은 중점의 거리나 근접성으로 정의된다. Kyung과 Ghosh (2009)는 방향에 따라서 이웃간 자기상관성의 크기가 다른 확장된 공간 모형을 제시하였다. 제안된 방향적 조건부 자기회귀 (directional conditionally autoregressive) 모형은 고유 이방성을 모형화하여 기존의 CAR과정을 일반화한다. 제시한 방향적 조건부 자기회귀모형의 모수추정으로 마르코프 체인 몬테 카를로 방법을 기반으로 한 베이즈 추정법을 제시한다. 제시한 모형을 스코틀랜드 그레이터 글래스고우의 로그변환된 부동산 가격에 적용하여 조건부 자기회귀모형과 비교하였다.

• 한국환경과학회지
• /
• 제20권12호
• /
• pp.1541-1551
• /
• 2011

This study applied the Bayesian method for the quantification of the parameter uncertainty of spatial linear mixed model in the estimation of the spatial distribution of probability rainfall. In the application of Bayesian method, the prior sensitivity analysis was implemented by using the priors normally selected in the existing studies which applied the Bayesian method for the puppose of assessing the influence which the selection of the priors of model parameters had on posteriors. As a result, the posteriors of parameters were differently estimated which priors were selected, and then in the case of the prior combination, F-S-E, the sizes of uncertainty intervals were minimum and the modes, means and medians of the posteriors were similar to the estimates using the existing classical methods. From the comparitive analysis between Bayesian and plug-in spatial predictions, we could find that the uncertainty of plug-in prediction could be slightly underestimated than that of Bayesian prediction.

• 한국지구과학회지
• /
• 제35권5호
• /
• pp.362-374
• /
• 2014

This study investigated the initial mass function (IMF) and star formation history of high-mass stars in the Small Magellanic Cloud (SMC) using a population synthesis technique. We used the photometric survey catalog of Lee (2013) as the observable quantities and compare them with those of synthetic populations based on Bayesian inference. For the IMF slope (${\Gamma}$) range of -1.1 to -3.5 with steps of 0.1, five types of star formation models were tested: 1) continuous; 2) single burst at 10 Myr; 3) single burst at 60 Myr; 4) double bursts at those epochs; and 5) a complex hybrid model. In this study, a total of 125 models were tested. Based on the model calculations, it was found that the continuous model could simulate the high-mass stars of the SMC and that its IMF slope was -1.6 which is slightly steeper than Salpeter's IMF, i.e., ${\Gamma}=-1.35$.

• ETRI Journal
• /
• 제43권1호
• /
• pp.74-81
• /
• 2021

The mixture model is a very powerful and flexible tool in clustering analysis. Based on the Dirichlet process and parsimonious Gaussian distribution, we propose a new nonparametric mixture framework for solving challenging clustering problems. Meanwhile, the inference of the model depends on the efficient online variational Bayesian approach, which enhances the information exchange between the whole and the part to a certain extent and applies to scalable datasets. The experiments on the scene database indicate that the novel clustering framework, when combined with a convolutional neural network for feature extraction, has meaningful advantages over other models.

• Communications for Statistical Applications and Methods
• /
• 제6권3호
• /
• pp.801-812
• /
• 1999

Change-point hazard rate models arise for example in applying "burn-in" techniques to screen defective items and in studing times until undesirable side effects occur in clinical trials. Sometimes in screening defectives it might be sensible to model two stages of burn-in. In a clinical trial there might be an initial hazard rate for a side effect which after a period of time changes to an intermediate hazard rate before settling into a long term hazard rate. In this paper we consider the multiple change points hazard rate model. The classical approach's asymptotics can be poor for the small to all moderate sample sizes often encountered in practice. We propose a Bayesian approach avoiding asymptotics to provide more reliable inference conditional only upon the data actually observed. The Bayesian models can be fitted using simulation methods. Model comparison is made using recently developed Bayesian model selection criteria. The above methodology is applied to a generated data and to a generated data and the Lawless(1982) failure times of electrical insulation.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2009년도 추계학술대회
• /
• pp.95-98
• /
• 2009

본 연구는 주관 감성에 따른 생리 데이터의 패턴을 분류하고, 임의의 생리 데이터의 패턴을 확인하여 각성-이완, 쾌-불쾌의 감성을 추론하기 위해 베이지안 이론(Bayesian learning)을 기반으로 한 추론 모델을 제안하는 것이 목적이다. 본 연구에서 제안하는 모델은 학습데이터를 분류하여 사전확률을 도출하는 학습 단계와 사후확률로 임의의 생리 데이터의 패턴을 분류하여 감성을 추론하는 추론 단계로 이루어진다. 자율 신경계 생리변수(PPG, GSR, SKT) 각각의 패턴 분류를 위해 1~7로 정규화를 시킨 후 선형 관계를 구하여 분류된 패턴의 사전확률을 구하였다. 다음으로 임의의 사전 확률 분포에 대한 사후 확률 분포의 계산을 위해 베이지안 이론을 적용하였다. 본 연구를 통해 주관적 평가를 실시하지 않고 다중 생리변수 인식을 통해 감성을 추론 할 수 있는 모델을 제안하였다.