• Structural Engineering and Mechanics
• /
• 제84권3호
• /
• pp.323-335
• /
• 2022

The main idea of the framework is to seamlessly combine a reasonably accurate and fast surrogate model with the importance sampling strategy. Developing a surrogate model for predicting structures' dynamic responses is challenging because it involves high-dimensional inputs and outputs. For this purpose, a novel surrogate model based on cutting-edge deep learning architectures specialized for capturing temporal relationships within time-series data, namely Long-Short term memory layer and Transformer layer, is designed. After being properly trained, the surrogate model could be utilized in place of the finite element method to evaluate structures' responses without requiring any specialized software. On the other hand, the importance sampling is adopted to reduce the number of calculations required when computing the failure probability by drawing more relevant samples near critical areas. Thanks to the portability of the trained surrogate model, one can integrate the latter with the Importance sampling in a straightforward fashion, forming an efficient framework called TTIS, which represents double advantages: less number of calculations is needed, and the computational time of each calculation is significantly reduced. The proposed approach's applicability and efficiency are demonstrated through three examples with increasing complexity, involving a 1D beam, a 2D frame, and a 3D building structure. The results show that compared to the conventional Monte Carlo simulation, the proposed method can provide highly similar reliability results with a reduction of up to four orders of magnitudes in time complexity.

• Structural Engineering and Mechanics
• /
• 제32권1호
• /
• pp.21-36
• /
• 2009

An importance sampling method is presented for computing the first passage probability of elasto-plastic structures under stochastic excitations. The importance sampling distribution corresponds to shifting the mean of the excitation to an 'adapted' stochastic process whose future is determined based on information only up to the present. A stochastic control approach is adopted for designing the adapted process. The optimal control law is determined by a control potential, which satisfies the Bellman's equation, a nonlinear partial differential equation on the response state-space. Numerical results for a single-degree-of freedom elasto-plastic structure shows that the proposed method leads to significant improvement in variance reduction over importance sampling using design points reported recently.

• 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.

• Communications for Statistical Applications and Methods
• /
• 제13권1호
• /
• pp.39-47
• /
• 2006

The Bayesian approach to multiple testing procedure for one sample testing problem proposed by Scott and Berger (2003) is extended to two-sample comparison problem in microarray experiments. The prior distribution of each gene's mean for one sample is given conditionally on the corresponding gene's mean for the other sample. Posterior distributions of interesting parameters are derived and estimated based on an importance sampling method. A simulated example is given for illustration.

• Journal of Genetic Medicine
• /
• 제11권2호
• /
• pp.43-48
• /
• 2014

Chorionic villus sampling has gained importance as a tool for early cytogenetic diagnosis with a shift toward first trimester screening. First trimester screening using nuchal translucency and biomarkers is effective for screening. Chorionic villus sampling generally is performed at 10-12 weeks by either the transcervical or transabdominal approach. There are two methods of analysis; the direct method and the culture method. While the direct method may prevent maternal cell contamination, the culture method may be more representative of the true fetal karyotype. There is a concern for mosaicism which occurs in approximately 1% of cases, and mosaic results require genetic counseling and follow-up amniocentesis or fetal blood sampling. In terms of complications, procedure-related pregnancy loss rates may be the same as those for amniocentesis when undertaken in experienced centers. When the procedure is performed after 9 weeks gestation, the risk of limb reduction is not greater than the risk in the general population. At present, chorionic villus sampling is the gold standard method for early fetal karyotyping; however, we anticipate that improvements in noninvasive prenatal testing methods, such as cell free fetal DNA testing, will reduce the need for invasive procedures in the near future.

• Journal of the Korean Statistical Society
• /
• 제26권4호
• /
• pp.493-505
• /
• 1997

The analysis of binary data appears to many areas such as statistics, biometrics and econometrics. In many cases, data are often collected in which some observations are incomplete. Assume that the missing covariates are missing at random and the responses are completely observed. A method to Bayesian analysis of the binary regression model with incomplete data is presented. In particular, the desired marginal posterior moments of regression parameter are obtained using Meterpolis algorithm (Metropolis et al. 1953) within Gibbs sampler (Gelfand and Smith, 1990). Also, we compare logit model with probit model using Bayes factor which is approximated by importance sampling method. One example is presented.

• 한국통신학회논문지
• /
• 제25권5A호
• /
• pp.668-673
• /
• 2000

본 논문에서는 센트럴 모우먼트 알고리즘을 디지틀 통신 채널에 적용함으로써 기존의 시뮬레이션인 기법인 Conventional Importance Samping와 Improved Importance Sampling 으로 해결할 수 없었던 문제점들의 해결 뿐 아니라 수행시간의 획기적인 개선도 가능하게 하였다. 즉 디지털 통신 채널의 수신단에서 잡음이 혼합된 수신신호의 센트랄 모우멘트를 측정하여 수신 신호의 확률적인 특성인 누적확률분포를 구함으로써 채널의 성능을 평가한다. 제안 알고리즘을 검증하기 위하여 Cadence사의 시뮬레이션 프로그램인 SPW를 이용하여 QPSK 위성통신 채널을 구현한 후 시뮬레이션 수행시간의 개선 효과를 확인하였다.

• Structural Engineering and Mechanics
• /
• 제20권6호
• /
• pp.609-630
• /
• 2005

A reliability analysis method is proposed in this paper through a combination of the advantages of the response surface method (RSM), finite element method (FEM), first order reliability method (FORM) and the importance sampling updating method. The accuracy and efficiency of the method is demonstrated through several numerical examples. Then the method is used to estimate the serviceability reliability of cable-stayed bridges. Effects of geometric nonlinearity, randomness in loading, material, and geometry are considered. The example cable-stayed bridge is the Second Nanjing Bridge with a main span length of 628 m built in China. The results show that the cable sag that is part of the geometric nonlinearities of cable-stayed bridges has a major effect on the reliability of cable-stayed bridge. Finally, the most influential random variables on the reliability of cable-stayed bridges are identified by using a sensitivity analysis.

• 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.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1997년도 춘계 학술대회 발표집
• /
• pp.8-8
• /
• 1997

최근 시뮬레이션은 높은 신뢰도를 요구하는 통신망시스템이나, 높음 품질수준을 요 구하는 제조시스템의 분석 및 설계에 적용되어지고 있다. 이러한 신뢰도가 높은 시스템에 대한 시뮬레이션 적용의 난제는 실제 시스템과 시뮬레이션 모형이 얼마나 정확히 모델링을 하는가 하는 문제와 실제 모델링을 하여 시뮬레이션을 수행하여 얼마나 빠른 시간내에 정확 히 결과를 산출해 낼 수 있는가를 하는 것이다. 이러한 문제점을 극복하기 위해서 속산시뮬 레이션(fast simulation) 기법들이 연구되고 있다. 그러한 기법들로 Importance Sampling (IS), Regenerative Method (RM), Parallel Simulation 등이 연구되고 있다. IS는 잘 알려진 분산축소 기법으로 속산시뮬레이션을 위하여 많이 사용되고 있으나 실제로 복잡한 모델에 적용하기에는 많은 어려움이 따른다. 그 이유는 최적 표본분포 (Optimal Sampling Distribution)를 찾기 위한 방법이 정형화되어 있지 않아 모델마다 최적표본분포를 유사하게 추정해야 하는 어려움이 따르기 때문이다. 이러한 단점을 극복하기 위하여 Nonparametric Improtance Sampling을 제안하고 실제로 M/M/1 대기행렬 모형에 적용하여 보았다.