• Structural Engineering and Mechanics
• /
• 제5권2호
• /
• pp.115-126
• /
• 1997

Importance sampling methods have been developed with the aim of reducing the computational costs inherent in Monte Carlo methods. This study proposes a new algorithm called the adaptive kernel method which combines and modifies some of the concepts from adaptive sampling and the simple kernel method to evaluate the structural reliability of time variant problems. The essence of the resulting algorithm is to select an appropriate starting point from which the importance sampling density can be generated efficiently. Numerical results show that the method is unbiased and substantially increases the efficiency over other methods.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1999년도 가을 학술발표회 논문집
• /
• pp.351-358
• /
• 1999

The structural responses of underground structures are examined in probability by using the elasto-plastic stochastic finite element method in which the spatial distributions of material properties are assumed to be stochastic fields. In addition, the adaptive importance sampling method using the response surface technique is used to improve simulation efficiency. The method is found to provide appropriate information although the nonlinear Limit State involves a large number of basic random variables and the failure probability is small. The probability of plastic local failures around an excavated area is effectively evaluated and the reliability for the limit displacement of the ground is investigated. It is demonstrated that the adaptive importance sampling method can be very efficiently used to evaluate the reliability of a large scale stochastic finite element model, such as the underground structures located in the multi-layered ground.

• 한국기계가공학회지
• /
• 제19권12호
• /
• pp.70-79
• /
• 2020

This paper describes a comparative study of characteristics of probabilistic design using various reliability analysis methods in the structure design of an automatic salt collector. The thickness sizing variables of the main structural member were considered to be random variables, including the uncertainty of corrosion, which would be an inevitable hazard in the work environment of the automatic salt collector. Probabilistic performance functions were selected from the strength performances of the automatic salt collector structure. First-order reliability method, second-order reliability method, mean value reliability method, and adaptive importance sampling method were applied during the reliability analyses. The probabilistic design performances such as reliability probability and numerical costs based on the reliability analysis methods were compared to the Monte Carlo simulation results. The adaptive importance sampling method showed the most rational results for the probabilistic structure design of the automatic salt collector.

• Structural Engineering and Mechanics
• /
• 제75권6호
• /
• pp.771-784
• /
• 2020

Reliability analysis techniques combining with various surrogate models have attracted increasing attention because of their accuracy and great efficiency. However, they primarily focus on the structures with continuous response, while very rare researches on the reliability analysis for structures with discontinuous response are carried out. Furthermore, existing adaptive reliability analysis methods based on importance sampling (IS) still have some intractable defects when dealing with small failure probability, and there is no related research on reliability analysis for structures involving discontinuous response and small failure probability. Therefore, this paper proposes a novel reliability analysis method called AGPC-IS for such structures, which combines adaptive Gaussian process classification (GPC) and adaptive-kernel-density-estimation-based IS. In AGPC-IS, an efficient adaptive strategy for design of experiments (DoE), taking into consideration the classification uncertainty, the sampling uniformity and the regional classification accuracy improvement, is developed with the purpose of improving the accuracy of Gaussian process classifier. The adaptive kernel density estimation is introduced for constructing the quasi-optimal density function of IS. In addition, a novel and more precise stopping criterion is also developed from the perspective of the stability of failure probability estimation. The efficiency, superiority and practicability of AGPC-IS are verified by three examples.

• Communications for Statistical Applications and Methods
• /
• 제16권3호
• /
• pp.479-485
• /
• 2009

When a part of data is unobserved the marginal likelihood of parameters given the observed data often involves analytically intractable high dimensional integral and hence it is hard to find the maximum likelihood estimate of the parameters. Simulated maximum likelihood(SML) method which estimates the marginal likelihood via Monte Carlo importance sampling and optimize the estimated marginal likelihood has been used in many applications. A key issue in SML is to find a good proposal density from which Monte Carlo samples are generated. The optimal proposal density is the conditional density of the unobserved data given the parameters and the observed data, and attempts have been given to find a good approximation to the optimal proposal density. Algorithms which adaptively improve the proposal density have been widely used due to its simplicity and efficiency. In this paper, we describe a fully adaptive algorithm which has been used by some practitioners but has not been well recognized in statistical literature, and evaluate its estimation performance and robustness via a simulation study. The simulation study shows a great improvement in the order of magnitudes in the mean squared error, compared to non-adaptive or partially adaptive SML methods. Also, it is shown that the fully adaptive SML is robust in a sense that it is insensitive to the starting points in the optimization routine.

• 한국산업융합학회 논문집
• /
• 제23권5호
• /
• pp.799-807
• /
• 2020

This paper deals with identification of probabilistic design using reliability based robust optimization in structure design of automatic salt collector. The thickness sizing variables of main structure member in the automatic salt collector were considered the random design variables including the uncertainty of corrosion that would be an inevitable hazardousness in the saltern work environment. The probabilistic constraint functions were selected from the strength performances of the automatic salt collector. The reliability based robust optimum design problem was formulated such that the random design variables were determined by minimizing the weight of the automatic salt collector subject to the probabilistic strength performance constraints evaluating from reliability analysis. Mean value reliability method and adaptive importance sampling method were applied to the reliability evaluation in the reliability based robust optimization. The three sigma level quality was considered robustness in side constraints. The probabilistic optimum design results according to the reliability analysis methods were compared to deterministic optimum design results. The reliability based robust optimization using the mean value reliability method showed the most rational results for the probabilistic optimum structure design of the automatic salt collector.

• 전산구조공학
• /
• 제11권4호
• /
• pp.309-320
• /
• 1998

중요표본추출기법중에서도 층화표본추출법을 이용한 적응적 중요표본추출기법이 일반적으로 가장 합리적인 것으로 알려져 있다. 그러나 확률장 유한요소모형문제와 같이 기본 확률변수의 규모가 큰 경우에는 층화표본추출법에서 요구되는 기본적인 표본점의 규모가 급증하여 효율성이 떨어지게 된다. 본 연구에서는 이러한 한계성을 극복하기 위하여 층화표본추출에서 기본확률변수를 사용하는 대신에 기본확률변수들의 함수이며 새로운 확률변수인 응답값을 이용하는 방법을 개발하였다. 여기에서 응답값은 일반적인 함수형태로 표시되지 않으며, 한 번의 응답계산에 많은 계산량이 소요되므로 이러한 문제점을 해결하기 위하여 응답면식을 이용한 층화표본추출법을 개발하였다. 개발된 기법에서는 기본확률변수의 모의발생규모는 기본의 기본확률변수를 이용한 층화표본추출법에서 보다 증가하지만 매우 많은 계산량을 요구하는 실제응답해석규모는 응답면식을 이용함으로써 획기적으로 감소되었다. 특히 본 기법은 기본확률변수의 규모가 크고 대상한계상태의 파괴확률이 낮을수록 기존의 방법과 비교해 효율성이 증대되는 것으로 분석되었다.

• 정보처리학회논문지B
• /
• 제10B권6호
• /
• pp.711-718
• /
• 2003

얼굴 인식 시스템과 표정인식 시스템과 같은 고차원 처리를 수행하는 시스템의 전처리 과정으로써 이미지 영역 내에서 얼굴을 추적하는 것은 중요한 과정이다. 본 논문에서는 피부색과 얼굴의 형태 정보를 단서로 하는 CONDENSATION 알고리즘을 사용하여 얼굴의 위치를 추적하였다. 컬러의 가중치와 형태의 가중치를 결합시키는데 어려움이 있으므로 각각을 단서로 사용하는 두 개의 추적기를 가진 시스템을 제안한다. 제안된 시스템은 복잡한 배경, 피부색의 물체가 이미지 내에 존재하는 경우, 다른 얼굴이 이미지 내에 존재하는 경우 모두에 대해서 훌륭한 성능을 보여 주었다.

• 응용통계연구
• /
• 제33권4호
• /
• pp.379-393
• /
• 2020

사망과 같은 종말 사건은 중간 사건을 중도절단 시킬 수 있지만 재발과 같은 중간 사건은 종말 사건을 중도절단 시킬 수 없는 자료를 준경쟁위험 자료라고 하는데 의학 및 보건, 역학 분야에서는 이와 같은 자료를 자주 접하게 된다. 본 논문에서는 질병-사망 모형에 포함된 세 가지 전이 시간이 모두 구간중도절단된 준경쟁위험 자료를 분석하기 위해 정규 프레일티를 가진 와이블 회귀모형을 제안하였다. 각 개체는 중간 사건과 종말 사건의 발생 여부에 따라 다섯 가지 유형으로 구분되는데 유형별로 조건부 우도함수를 유도하였다. 조정중요표본추출법을 써서 주변 우도함수를 유도한 후 반복의사뉴톤 알고리즘을 써서 최적 추정량을 얻었다. 제안한 추정 방법의 소표본 성질을 살펴보기 위해 모의실험을 수행하였으며 또한 제안한 추정 방법을 Personnes Agées Quid (PAQUID) 자료에 적용하였다.

• 응용통계연구
• /
• 제30권4호
• /
• pp.539-553
• /
• 2017

본 논문에서는 사망과 같은 종말사건의 발생 유무는 알고 있지만 치매 발병과 같은 중간사건이 구간중도절단 되었거나 연구 기간 도중에 추적이 끊겨 결측된 준경쟁적위험 자료에 대해 다중상태모형을 적용하여 모수를 추정하는 방법을 제안하였다. 이를 위해 본 논문에서는 상태 간의 전이강도는 로그정규 프레일티를 랜덤효과로 가진 Lin과 Ying(1994)의 가산위험모형을 따른다고 가정하였다. 다섯 가지 상태를 가진 다중상태모형에서 가능한 여섯 가지 경로별로 조건부우도를 정의하였고, 주변우도를 구하기 위해 조정중요표본추출법을 적용하였으며 반복유사뉴튼 방법으로 최적해를 구하였다. 소표본 모의실험을 통해 모수의 95% 신뢰구간 포함률이 명목값에 얼마나 가까운지 살펴보았으며, 제안한 모형을 Persones $Ag{\acute{e}}es$ Quid (PAQUID) 자료 (Helmer 등, 2001)에 적용하고 그 결과를 해석하였다.