• Smart Structures and Systems
• /
• v.15 no.3
• /
• pp.735-749
• /
• 2015

The major difficulty of using Bayesian probabilistic inference for system identification is to obtain the posterior probability density of parameters conditioned by the measured response. The posterior density of structural parameters indicates how plausible each model is when considering the uncertainty of prediction errors. The Markov chain Monte Carlo (MCMC) method is a widespread medium for posterior inference but its convergence is often slow. The differential evolution adaptive Metropolis-Hasting (DREAM) algorithm boasts a population-based mechanism, which nms multiple different Markov chains simultaneously, and a global optimum exploration ability. This paper proposes an improved differential evolution adaptive Metropolis-Hasting algorithm (IDREAM) strategy to estimate the posterior density of structural parameters. The main benefit of IDREAM is its efficient MCMC simulation through its use of the adaptive Metropolis (AM) method with a mutation strategy for ensuring quick convergence and robust solutions. Its effectiveness was demonstrated in simulations on identifying the structural parameters with limited output data and noise polluted measurements.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.239-239
• /
• 2015

This study presents a bivariate extension of the goodness-of-fit measure for regional frequency distributions developed by Hosking and Wallis [1993] for use with the method of L-moments. Utilising the approximate joint normal distribution of the regional L-skewness and L-kurtosis, a graphical representation of the confidence region on the L-moment diagram can be constructed as an ellipsoid. Candidate distributions can then be accepted where the corresponding the oretical relationship between the L-skewness and L-kurtosis intersects the confidence region, and the chosen distribution would be the one that minimises the Mahalanobis distance measure. Based on a set of Monte Carlo simulations it is demonstrated that the new bivariate measure generally selects the true population distribution more frequently than the original method. An R-code implementation of the method is available for download free-of-charge from the GitHub code depository and will be demonstrated on a case study of annual maximum series of peak flow data from a homogeneous region in Italy.

• Journal of Environmental Health Sciences
• /
• v.45 no.5
• /
• pp.557-557
• /
• 2019

• Proceeding of EDISON Challenge
• /
• 2017.03a
• /
• pp.677-687
• /
• 2017

Caffeine has a long history of human consumption but the consumption of caffeine due to caffeinated energy drinks(CEDs) is rapidly growing. Marketing targets of CED sales are children, adolescents and young adults, possibly caffeine-sensitive groups and its effect for them can be significantly different from healthy adults. Caffeine-related toxicities among these groups are growing in number and a number of countries are recognizing severity of caffeine toxicities. Previous research showed prediction of maximal plasma caffeine concentration profiles after the single CED ingestion and the primary aim of this study is to visually predict plasma caffeine concentration after the single and multiple ingestion of standard servings of CED. Based on the population pharmacokinetic model using Monte Carlo simulation, prediction of caffeine concentration leading to caffeine intoxication in the sensitive groups is quantitatively presented and visualized. This research also broadens the perspective by creating and utilizing diverse open science tools including R package, Edison Science App and Shiny apps.

• Nuclear Engineering and Technology
• /
• v.16 no.3
• /
• pp.136-140
• /
• 1984

A new medal is presented in order to evaluate the risk from a nuclear facility following accidents directly combining the on-site meteorological data using the Monte Carlo Method. To estimate the radiological detriment to the surrounding population-at-large (collective dose equivalent), in this study the probability distribution of each meteorological element based upon on-site data is analyzed to generate atmospheric dispersion conditions. The random sampling is used to select the dispersion conditions at any given time of effluent releases. In this study it is considered that the meteorological conditions such as wind direction, speed and stability are mutually independent and each condition satisfies the Markov condition. As a sample study, the risk of KNU-1 following the large LOCA was calculated, The calculated collective dose equivalent in the 50 mile region population from the large LOCA with 50 percent confidence level is 2.0$\times$10$^2$ man-sievert.

• Journal of Environmental Science International
• /
• v.28 no.1
• /
• pp.19-35
• /
• 2019

This study investigates the performance of four Bayesian methods, Random Walk Metropolis (RWM), Hit-And-Run Metropolis (HARM), Adaptive Mixture Metropolis (AMM), and Population Monte Carlo (PMC), for estimating the parameters and uncertainties of probability rainfall distribution, and the results are compared with those of conventional parameter estimation methods; namely, the Method Of Moment (MOM), Maximum Likelihood Method (MLM), and Probability Weighted Method (PWM). As a result, Bayesian methods yield similar or slightly better results in parameter estimations compared with conventional methods. In particular, PMC can reduce parameter uncertainty greatly compared with RWM, HARM, and AMM methods although the Bayesian methods produce similar results in parameter estimations. Overall, the Bayesian methods produce better accuracy for scale parameters compared with the conventional methods and this characteristic improves the accuracy of probability rainfall. Therefore, Bayesian methods can be effective tools for estimating the parameters and uncertainties of probability rainfall distribution in hydrological practices, flood risk assessment, and decision-making support.

• Structural Engineering and Mechanics
• /
• v.66 no.6
• /
• pp.677-691
• /
• 2018

Reliability assessment of complex structures using simulation methods is time-consuming. Thus, surrogate models are usually employed to reduce computational cost. AK-MCS is a surrogate-based Active learning method combining Kriging and Monte-Carlo Simulation for structural reliability analysis. This paper proposes three modifications of the AK-MCS method to reduce the number of calls to the performance function. The first modification is related to the definition of an initial Design of Experiments (DoE). In the original AK-MCS method, an initial DoE is created by a random selection of samples among the Monte Carlo population. Therefore, samples in the failure region have fewer chances to be selected, because a small number of samples are usually located in the failure region compared to the safe region. The proposed method in this paper is based on a uniform selection of samples in the predefined domain, so more samples may be selected from the failure region. Another important parameter in the AK-MCS method is the size of the initial DoE. The algorithm may not predict the exact limit state surface with an insufficient number of initial samples. Thus, the second modification of the AK-MCS method is proposed to overcome this problem. The third modification is relevant to the type of regression trend in the AK-MCS method. The original AK-MCS method uses an ordinary Kriging model, so the regression part of Kriging model is an unknown constant value. In this paper, the effect of regression trend in the AK-MCS method is investigated for a benchmark problem, and it is shown that the appropriate choice of regression type could reduce the number of calls to the performance function. A stepwise approach is also presented to select a suitable trend of the Kriging model. The numerical results show the effectiveness of the proposed modifications.

• The Korean Journal of Applied Statistics
• /
• v.18 no.1
• /
• pp.1-13
• /
• 2005

Latent Class model has been considered recently by many researchers and practitioners as a tool for identifying heterogeneous segments or groups in a population, and grouping objects into the segments. In this paper we consider data on prostate cancer patients from Korean National Cancer Institute and propose a method for grouping prostate cancer patients by using latent class Poisson model. A Bayesian approach equipped with a Markov chain Monte Carlo method is used to overcome the limit of classical likelihood approaches. Advantages of the proposed Bayesian method are easy estimation of parameters with their standard errors, segmentation of objects into groups, and provision of uncertainty measures for the segmentation. In addition, we provide a method to determine an appropriate number of segments for the given data so that the method automatically chooses the number of segments and partitions objects into heterogeneous segments.

• Nuclear Engineering and Technology
• /
• v.49 no.4
• /
• pp.710-720
• /
• 2017

In Korea, many nuclear power plants operate at a single site based on geographical characteristics, but the population density near the sites is higher than that in other countries. Thus, multiunit accidents are a more important consideration than in other countries and should be addressed appropriately. Currently, there are many issues related to a multiunit probabilistic safety assessment (PSA). One of them is the quantification of a multiunit PSA model. A traditional PSA uses a Boolean manipulation of the fault tree in terms of the minimal cut set. However, such methods have some limitations when rare event approximations cannot be used effectively or a very small truncation limit should be applied to identify accident sequence combinations for a multiunit site. In particular, it is well known that seismic risk in terms of core damage frequency can be overestimated because there are many events that have a high failure probability. In this study, we propose a quantification method based on a Monte Carlo approach for a multiunit PSA model. This method can consider all possible accident sequence combinations in a multiunit site and calculate a more exact value for events that have a high failure probability. An example model for six identical units at a site was also developed and quantified to confirm the applicability of the proposed method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.6
• /
• pp.1357-1363
• /
• 1994

A Monte-Carlo simulation model is developed to predict size distribution produced by the coalescence of air bubbles in turbulent shear f1ow. The simulation consists of generating a population of air bubbles into the initial positions at each time step and tracking them by simulating motions and checking collisions. The radial displacement of air bubbles in the simulation model is produced by numerically solving an advective diffusion equation. Longitudinal displacements are generated from the logarithmic flow velovity distribution and the bubble rise velocity. Collision of air bubbles for each time step is detected by a geometric test using their relative positions at the beginning of the time step and relative displacements during the time step. At the end of the time step, the total number of bubbles, their positions, and sizes are updated. The computer program is coded such that minimum storages for sizes and positions of bubbles are required.