• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2003년도 추계학술대회 및 정기총회
• /
• pp.346-349
• /
• 2003

This paper is intended to assess a system reliability that is changed as time passes. The proposed methodology consists of two steps: (1) predicting probabilities that each component fails at specific time by using a Markov Chain model and (2) calculating reliability of the whole system via Bayesian network. The proposed methodology includes extended Bayesian network model reflecting the case that components are mutually dependent.

• Communications for Statistical Applications and Methods
• /
• 제24권6호
• /
• pp.543-559
• /
• 2017

Tree-based regression and classification ensembles form a standard part of the data-science toolkit. Many commonly used methods take an algorithmic view, proposing greedy methods for constructing decision trees; examples include the classification and regression trees algorithm, boosted decision trees, and random forests. Recent history has seen a surge of interest in Bayesian techniques for constructing decision tree ensembles, with these methods frequently outperforming their algorithmic counterparts. The goal of this article is to survey the landscape surrounding Bayesian decision tree methods, and to discuss recent modeling and computational developments. We provide connections between Bayesian tree-based methods and existing machine learning techniques, and outline several recent theoretical developments establishing frequentist consistency and rates of convergence for the posterior distribution. The methodology we present is applicable for a wide variety of statistical tasks including regression, classification, modeling of count data, and many others. We illustrate the methodology on both simulated and real datasets.

• 산업경영시스템학회지
• /
• 제7권10호
• /
• pp.47-51
• /
• 1984

In many forecasting problem, there is little or no useful historical information available at the time the initial forecast is required, The propose of this paper is study on Bayesian Method in forecasting. I : Introduction. II : Bayesian estimation. III : Constant Model. IV : General time series Models. V : Conclusion. The Bayesian procedure are then used to revise parameter estimates when time series information is available, in this paper we give a general description of the bayesian approach and demonstrate the methodology with several specific cases.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2013년도 춘계 학술논문 발표대회
• /
• pp.21-22
• /
• 2013

Construction industry has become higher, larger and more complicated. Construction projects demand precise planning and management prior and during actual operation. However, it has been analyzed that the process planning in the construction site has been made by the site engineer experience mostly that usually results in unreliable results. Numerous studies in this field have been conducted trying to solve such problems developing methodologies to suggest quantitative results. It has been analyzed that many studies have focused on limited data only and neglected suggesting an appropriate methodology for changing data applications. Therefore, this study suggests a methodology that effectively manages construction productivity by applying bayesian approach focusing on the high-rise curtain wall operations.

• Journal of Radiation Protection and Research
• /
• 제30권2호
• /
• pp.91-97
• /
• 2005

베이지안 기법은 객관적 자료 이외에 주관적 지식도 평가에 반영하는 특성으로 인해 최근 PRA에서 널리 사용되고 있다. 본 연구에서는 비파괴검사 장비 분실에 대한 방사선 위험도를 평가하기 위해 베이지안 기법을 활용하였다. U.S. NRC에서 제시한 선원분실 피폭 시나리오를 국내 실정에 맞게 재구성하였고 안전인자의 사고발생 확률에 국한하여 적용하였다. 사고발생 확률수정의 경우 Jeffreys사전분포를 사용한 결과가 모호사전분포를 사용한 결과보다 5 % 베이즈 하한치가 더 낮아서 방사선 사고와 같은 낮은 사고발생 확률을 가지는 시스템에 대한 위험도 평가에 적합하다. 위험도의 결과를 보면 일반인의 연간 예상되는 평균선량은 베이지안 기법이 고전적인 기법에 의거한 평가보다 높은 선량을 나타내는데 이는 수정된 안전인자 확률의 평균이 고전적 확률 참보다 높게 평가된 것에 기인한다. 국내의 경우 방사선 위험도 평가를 위한 자료구축이 미비한 바 베이지안 기법은 위험도 평가에 유용한 대안으로 활용할 수 있으며 이러한 연구는 위험도 정보-기반 규제에 기여할 것이다.

• 한국정보통신학회논문지
• /
• 제19권7호
• /
• pp.1750-1758
• /
• 2015

본 논문은 일회성 시스템인 유도무기의 신뢰성을 평가하기 위해 베이지안 방법론을 활용하는 내용이며, 유도무기 서브시스템 및 부품의 평가결과를 그 다음 단계의 사전분포로 활용하였다. 각 서브시스템 및 부품의 시험평가 결과를 활용하여 전체 유도무기체계의 신뢰성을 분석하는 베이지안 방법론을 제시하였고, 이를 활용하면 유도무기쳬계의 신뢰성을 확보하기 위한 샘플수를 적절히 선정할 수 있다.

• Nuclear Engineering and Technology
• /
• 제54권1호
• /
• pp.414-422
• /
• 2022

Presented in this paper is a methodology for combining a Bayesian statistical approach with Data Quality Objectives (a structured decision-making method) to provide increased levels of confidence in analytical data when approaching a waste boundary. Development of sampling and analysis plans for the characterisation of radioactive waste often use a simple, one pass statistical approach as underpinning for the sampling schedule. Using a Bayesian statistical approach introduces the concept of Prior information giving an adaptive sample strategy based on previous knowledge. This aligns more closely with the iterative approach demanded of the most commonly used structured decision-making tool in this area (Data Quality Objectives) and the potential to provide a more fully underpinned justification than the more traditional statistical approach. The approach described has been developed in a UK regulatory context but is translated to a waste stream from the Fukushima Daiichi Nuclear Power Station to demonstrate how the methodology can be applied in this context to support decision making regarding the ultimate disposal option for radioactive waste in a more global context.

• Journal of the Korean Statistical Society
• /
• 제25권1호
• /
• pp.81-94
• /
• 1996

This paper suggests a new criterion for testing the general linear hypothesis about coefficients in multivariate growth curve model. It is developed from a Bayesian point of view using the highest posterior density region methodology. Likelihood ratio test criterion(LRTC) by Khatri(1966) results as an approximate special case. It is shown that under the simple case of vague prior distribution for the multivariate normal parameters a LRTC-like criterion results; but the degrees of freedom are lower, so the suggested test criterion yields more conservative test than is warranted by the classical LRTC, a result analogous to that of Berger and Sellke(1987). Moreover, more general(non-vague) prior distributions will generate a richer class of tests than were previously available.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2014년도 추계 학술논문 발표대회
• /
• pp.94-95
• /
• 2014

Construction industry has become higher, larger and more complicated. It has been analyzed that the process planning in the construction site has been made by the site engineer experience mostly and some were made based on historical data. However, such plans have been investigated that require numerous revisions during construction which means that the plans made through such methods are not reliable. Numerous studies in this field have been conducted trying to solve such problems developing methodologies to overcome such limitations. It has been analyzed that many studies have focused on suggesting prediction models only that cannot be used for both actual planning prior to construction and process monitoring during construction. Therefore, this study suggests a methodology that effectively manages construction productivity by applying simulation methodology combined with bayesian approach focusing on the high-rise curtain wall operations.

• 산업기술연구
• /
• 제9권
• /
• pp.51-56
• /
• 1989

A methodology for determining optimal sampling plans for Bayesian multiattribute curtailed inspection models is proposed, whereby sampling inspection is terminated as soon as the disposition of the inspection lot is determined. An iterative solution procedure is developed for obtaining optimal multiattribute acceptance sampling plans under cuntailed sampling inspection.