• Journal of the Korean Statistical Society
• /
• v.32 no.4
• /
• pp.411-423
• /
• 2003

In this paper we develop a method for calculating a probability that a particular generalized variance is the smallest of all the K multivariate normal generalized variances. The method gives a way of comparing K multivariate populations in terms of their dispersion or spread, because the generalized variance is a scalar measure of the overall multivariate scatter. Fully parametric frequentist approach for the probability is intractable and thus a Bayesian method is pursued using a variant of weighted Monte Carlo (WMC) sampling based approach. Necessary theory involved in the method and computation is provided.

• Journal of the Korean Statistical Society
• /
• v.31 no.1
• /
• pp.77-91
• /
• 2002

This paper considers a functional regression model with truncated errors in explanatory variables. We show that the ordinary least squares (OLS) estimators produce bias in regression parameter estimates under misspecified models with ignored errors in the explanatory variable measurements, and then propose methods for analyzing the functional model. Fully parametric frequentist approaches for analyzing the model are intractable and thus Bayesian methods are pursued using a Markov chain Monte Carlo (MCMC) sampling based approach. Necessary theories involved in modeling and computation are provided. Finally, a simulation study is given to illustrate and examine the proposed methods.

• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• 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.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1587-1596
• /
• 2020

The location selection for nuclear power plants (NPP) is a strategic decision, which has significant impact operation of the plant and sustainable development of the region. Further, the ranking of the alternative locations and selection of the most suitable and efficient locations for NPPs is an important multi-criteria decision-making problem. In this paper, the non-sequential Monte Carlo probabilistic method and the Latin hypercube sampling probabilistic method are used to evaluate and select the optimal locations for NPP. These locations are identified by the power plant's onsite loads and the average of the lowest number of relay protection after the NPP's trip, based on electricity considerations. The results obtained from the proposed method indicate that in selecting the optimal location for an NPP after a power plant trip with the purpose of internal onsite loads of the power plant and the average of the lowest number of relay protection power system, on the IEEE RTS 24-bus system network given. This paper provides an effective and systematic study of the decision-making process for evaluating and selecting optimal locations for an NPP.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1993.10a
• /
• pp.248-255
• /
• 1993

Recently, due to the increasing attention to the structural safety under uncertain environments, many researches on the structural reliability analysis have been peformed. Some useful methods are available to evaluate performance reliability of structures with explicit limit states. However, for large structures, in which structural behaviors can be analyzed with finite element models and the limit states are only expressed implicitly, Monte-Carlo simulation method has been mainly used. However, Monte-Carlo simulation method spends too much computational time on repetitive structural analysis. Many alternative methods are suggested to reduce the computational work required in Monte-Carlo simulation. Response surface method is widely used to improve the efficiency of structural reliability analysis. Response surface method is based on the concept of approximating simple polynomial function of basic random variables for the limit state which is not easily expressed in explicit forms of design random variables. The response surface method has simple algorithm. However, the accuracy of results highly depends on how properly the stochastic characteristics of the original limit state has been represented by approximated function, In this study, an improved response surface method is proposed in which the sampling points for creating response surface are modified to represent the failure surface more adequately and the combined use of a linear response surface function and Rackwitz-Fiessler method has been employed. The method is found to be more effective and efficient than previous response surface methods. In addition more consistent convergence is achieved, Accuracy of the proposed method has been investigated through example.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.10
• /
• pp.154-160
• /
• 2001

For major structural components periodic inspections and integrity assessments are needed for the safety. However, many flaws are undetectable because sampling inspection is carried out during in-service inspection. Probabilistic integrity assessment is applied to take into consideration of uncertainty and variance of input parameters arise due to material properties and undetectable cracks. This paper describes a Probabilistic Fracture Mechanics(PFM) analysis based on the Monte Carlo(MC) algorithms. Taking a number of sampling data of probabilistic variables such as fracture toughness value, crack depth and aspect ratio of an initial surface crack, a MC simulation of failure judgement of samples is performed. for the verification of this analysis, a comparison study of the PFM analysis using a commercial code, mathematical method is carried out and a good agreement was observed between those results.

• Journal of Satellite, Information and Communications
• /
• v.9 no.4
• /
• pp.104-110
• /
• 2014

This paper considers two reconstruction schemes of structured-sparse signals, turbo inference and Markov chain Monte Carlo (MCMC) inference, in compressed sensing(CS) technique that is recently getting an important issue for an efficient video wireless transmission system using multi-copter as an unmanned aerial vehicle. Proposed reconstruction algorithms are setting importance on reduction of image data sizes, fast reconstruction speed and errorless reconstruction. As a result of experimentation with twenty kinds of images, we can find turbo reconstruction algorithm based on loopy belief propagation(BP) has more excellent performances than MCMC algorithm based on Gibbs sampling as aspects of average reconstruction computation time, normalized mean squared error(NMSE) values.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3355-3372
• /
• 2022

Composing music is an inspired yet challenging task, in that the process involves many considerations such as assigning pitches, determining rhythm, and arranging accompaniment. Algorithmic composition aims to develop algorithms for music composition. Recently, algorithmic composition using artificial intelligence technologies received considerable attention. In particular, computational intelligence is widely used and achieves promising results in the creation of music. This paper attempts to provide a survey on the music generation based on the Monte Carlo (MC) algorithm. First, transform the MIDI music format files to digital data. Among these data, use the logistic fitting method to fit the time series, obtain the time distribution regular pattern. Except for time series, the converted data also includes duration, pitch, and velocity. Second, using MC simulation to deal with them summed up their distribution law respectively. The two main control parameters are the value of discrete sampling and standard deviation. Processing the above parameters and converting the data to MIDI file, then compared with the output generated by LSTM neural network, evaluate the music comprehensively.

• Journal of computational fluids engineering
• /
• v.4 no.3
• /
• pp.63-70
• /
• 1999

A Direct simulation Monte-Carlo (DSMC) code is developed, which employs the Monte-Carlo statistical sampling technique to investigate hypersonic rarefied gas flows accompanying chemical reactions. The DSMC method is a numerical simulation technique for analyzing the Boltzmann equation by modeling a real gas flow using a representative set of molecules. Due to the limitations in computational requirements. the present method is applied to a flow around a simple two-dimensional object in exit velocity of 7.6 km/sec at an altitude of 90 km. For the calculation of chemical reactions an air model with five species (O₂, N₂, O, N, NO) and 19 chemical reactions is employed. The simulated result showed various rarefaction effects in the hypersonic flow with chemical reactions.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.263-266
• /
• 2007

This paper discusses the Bayesian statistical inference. This paper discusses the Bayesian inference, MCMC (Markov Chain Monte Carlo) integration, MCMC method, Metropolis-Hastings algorithm, Gibbs sampling, Maximum likelihood estimation, Expectation Maximization algorithm, missing data processing, and BMA (Bayesian Model Averaging). The Bayesian statistical inference is used to process a large amount of data in the areas of biology, medicine, bioengineering, science and engineering, and general data analysis and processing, and provides the important method to draw the optimal inference result. Lastly, this paper discusses the method of principal component analysis. The PCA method is also used for data analysis and inference.