• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (C)
• /
• pp.263-266
• /
• 2007

본 논문은 베이지안 통계 추론에 대하여 논의한다. 논문은 베이지안 추론, Markov Chain과 Monte Carlo 적분, MCMC(Markov Chain Monte Carlo) 기법, Metropolis-Hastings 알고리즘, Gibbs 샘플링, Maximum Likelihood Estimation, EM 알고리즘, 상실된 데이터 보완 기법, BMA(Bayesian Model Averaging) 순서로 논의를 진행한다. 이러한 통계적 기법들은 대용량의 데이터를 처리하는 생물학, 의학, 생명 공학, 과학과 공학, 그리고 일반 데이터 조사와 처리 등에 사용되고 있으며, 최적의 추론 결과를 이끌어 내는데 중요한 방법을 제공하고 있다. 그리고 마지막으로 PC(Principal Component) 분석 기법에 대하여 논의한다. PC 분석 기법도 데이터 분석과 연구에 많이 활용된다.

• 한국의학물리학회:학술대회논문집
• /
• 한국의학물리학회 2004년도 제29회 추계학술대회 발표논문집
• /
• pp.43-46
• /
• 2004

The commissioning of a treatment planning system of model-based dose calculation algorithm requires a lot of parameters to be selected to fit measured data, in which process physical insights for the parameters are often forgotten. We present the photon beam commissioning of Pinnacle$^3$ with the help of Monte Carlo (MC) simulation and evaluate the parameters Pinnacle$^3$ demands. Even though the MC calculation produces reasonable values for the commissioning, the thorough physical basis of the Pinnacles$^3$'s commissioning process is needed to use the MC derived parameters directly.

• 전기학회논문지P
• /
• 제54권1호
• /
• pp.29-33
• /
• 2005

Energy distribution function for electrons in $SF_6$-Ar mixtures gas by MCS-BEq algorithm has been analysed over the E/N range $30{\sim}300$[Td] by a two term Boltana equation and by a Monte Carlo Simulation using a set of electron cross sections determined by other, authors, experimentally the electron swarm parameters for 0.2[%} and 0.5[%] $SF_6$-Ar mixtures were measured by time-of-flight(TOF) method. The result show that the deduced electron drift velocities, the electron ionization or attachment coefficients, longitudinal and transverse diffusion coefficients and mean energy agree reasonably well with theoretical for a rang of E/N values. The results obtained from Booltemann equation method and Monte Carlo simulation have been compared with present and previously obtained data and respective set of electron collision cross sections of the molecules.

• 전기의세계
• /
• 제24권5호
• /
• pp.72-80
• /
• 1975

In this paper an application of the Monte Carlo method to optimum circuit design is discussed. T. Tsuda and T. Kiyono's algorithm based on the Monte Carlo method for solving multiple simul-taneous nonlinear equations is generalized to apply it to finding solutions of the constrained nonlinear optimization problem. The generalized algorithm derived here is directly applied to economical circuit design. In the cirsuit design, the object function is a cost function which is related to the cost of each circuit component. The constraint is the variance of the total system expressed by the variances of each circuit component. The design is to be determined so that the circuit has specified drift reliability with minimum cost. A practical example of economical circuit design and a general nonlinear function minimization is presented with food results.

• 대한전기학회논문지:전력기술부문A
• /
• 제55권12호
• /
• pp.536-543
• /
• 2006

This paper uses Monte Carlo technique, which is one of probabilistic methods of estimating the economical quantity of electric power generation in consideration of voltage stability in the aspect of power generation companies. In the power exchange system in Korea, when power generation companies participate in tenders for power generation capacity at the power exchange, they need to determine their power supply capacity considering the stability of electric power system. Thus, we purposed to propose an algorithm for estimating economical power generation capacity in theaspect of power generation companies, through which we can estimate the margin for voltage stability through P-V curve analysis by capacity according to the change of power generation capacity in a simulated system and to conduct Monte Carlo simulation in consideration of the margin

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.34-46
• /
• 2019

A method for detecting foreign substances in mould based on scatter grams was presented to protect moulds automatically during moulding production. This paper proposes a wavelet transform foreign detection method based on Monte Carlo analysis mechanism to identify foreign objects in the tube. We use the Monte Carlo method to evaluate the image, and obtain the width of the confidence interval by the deviation statistical gray histogram to divide the image type. In order to stabilize the performance of the algorithm, the high-frequency image and the low-frequency image are respectively drawn. By analyzing the position distribution of the pixel gray in the two images, the suspected foreign object region is obtained. The experiments demonstrate the effectiveness of our approach by evaluating the labeled data.

• Communications for Statistical Applications and Methods
• /
• 제31권1호
• /
• pp.65-85
• /
• 2024

The tail probability of a function of a multivariate random variable is not easy to estimate by the crude Monte Carlo simulation. When the occurrence of the function value over a threshold is rare, the accurate estimation of the corresponding probability requires a huge number of samples. When the explicit form of the cumulative distribution function of each component of the variable is known, the inverse transform likelihood ratio method is directly applicable scheme to estimate the tail probability efficiently. The method is a type of the importance sampling and its efficiency depends on the selection of the importance sampling distribution. When the cumulative distribution of the multivariate random variable is represented by a copula and its marginal distributions, we develop an iterative algorithm to find the optimal importance sampling distribution, and show the convergence of the algorithm. The performance of the proposed scheme is compared with the crude Monte Carlo simulation numerically.

• 응용통계연구
• /
• 제25권1호
• /
• pp.183-196
• /
• 2012

결측자료(missing data), 절단분포(truncated distribution), 중도절단자료(censored data) 등 불완전한 자료(incomplete data)하의 추론문제(incomplete problems)는 통계학에서 자주 발생되는 현상이다. 이런 문제의 해결방법으로 Expectation Maximization, Monte Carlo Expectation Maximization, Stochastic Expectation Maximization 알고리즘 등을 이용하는 방법이 있지만, 정형화된 분포의 가정이 필요하다는 단점을 가지고 있다. 본 연구에서는 정형화된 분포의 가정이 없는 경우에 사용할 수 있는 Metropolis-Hastings Expectation Maximization(MHEM) 알고리즘을 제안하고자 한다. MHEM 알고리즘의 효율성은 중도절단자료(censored data)를 이용한 모의실험과 KOSPI 200 수익률의 실증자료분석를 통해 알수 있었다.

• Nuclear Engineering and Technology
• /
• 제52권11호
• /
• pp.2667-2677
• /
• 2020

A domain decomposition (DD) scheme for GPU-based Monte Carlo (MC) calculation which is essential for whole-core depletion is introduced within the framework of the modified history-based tracking algorithm. Since GPU-offloaded MC calculations suffer from limited memory capacity, employing DDMC is inevitable for the simulation of depleted cores which require large storage to save hundreds of newly generated isotopes. First, an automated domain decomposition algorithm named wheel clustering is devised such that each subdomain contains nearly the same number of fuel assemblies. Second, an innerouter iteration algorithm allowing overlapped computation and communication is introduced which enables boundary neutron transactions during the tracking of interior neutrons. Third, a bank update scheme which is to include the boundary sources in a way to be adequate to the peculiar data structures of the GPU-based neutron tracking algorithm is presented. The verification and demonstration of the DDMC method are done for 3D full-core problems: APR1400 fresh core and a mock-up depleted core. It is confirmed that the DDMC method performs comparably with the standard MC method, and that the domain decomposition scheme is essential to carry out full 3D MC depletion calculations with limited GPU memory capacities.

• Structural Engineering and Mechanics
• /
• 제21권5호
• /
• pp.507-518
• /
• 2005

In the shear-lag analysis of structures deterministic procedure is insufficient to provide complete information. Probabilistic analysis is a holistic approach for analyzing shear-lag effects considering uncertainties in structural parameters. This paper proposes an efficient and accurate algorithm to analyze shear-lag effects of structures with parameter uncertainties. The proposed algorithm integrated the advantages of the response surface method (RSM), finite element method (FEM) and Monte Carlo simulation (MCS). Uncertainties in the structural parameters can be taken into account in this algorithm. The algorithm is verified using independently generated finite element data. The proposed algorithm is then used to analyze the shear-lag effects of a simply supported beam with parameter uncertainties. The results show that the proposed algorithm based on the central composite design is the most promising one in view of its accuracy and efficiency. Finally, a parametric study was conducted to investigate the effect of each of the random variables on the statistical moment of structural stress response.