• Journal of Korean Society on Water Environment
• /
• v.36 no.4
• /
• pp.300-313
• /
• 2020

The Bayesian approach can be used to estimate hydrologic model parameters from the prior expert knowledge about the parameter values and the observed data. The purpose of this study was to compare the performance of the two Bayesian methods, the Metropolis-Hastings (MH) algorithm and the Generalized Likelihood Uncertainty Estimation (GLUE) method. These two methods were applied to the TANK model, a hydrological model comprising 13 parameters, to examine the uncertainty of the parameters of the model. The TANK model comprises a combination of multiple reservoir-type virtual vessels with orifice-type outlets and implements a common major hydrological process using the runoff calculations that convert the rainfall to the flow. As a result of the application to the Nam River A watershed, the two Bayesian methods yielded similar flow simulation results even though the parameter estimates obtained by the two methods were of somewhat different values. Both methods ensure the model's prediction accuracy even when the observed flow data available for parameter estimation is limited. However, the prediction accuracy of the model using the MH algorithm yielded slightly better results than that of the GLUE method. The flow duration curve calculated using the limited observed flow data showed that the marginal reliability is secured from the perspective of practical application.

• Journal of KIISE
• /
• v.44 no.10
• /
• pp.1026-1033
• /
• 2017

In this paper a Bayesian modeling and duration-based prediction method is proposed for health clinic time series data using the Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM). HDP-HMM is a Bayesian extension of HMM which can find the optimal number of health states, a number which is highly uncertain and even difficult to estimate under the context of health dynamics. Test results of HDP-HMM using simulated data and real health clinic data have shown interesting modeling behaviors and promising prediction performance over the span of up to five years. The future of health change is uncertain and its prediction is inherently difficult, but experimental results on health clinic data suggests that practical long-term prediction is possible and can be made useful if we present multiple hypotheses given dynamic contexts as defined by HMM states.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• Communications for Statistical Applications and Methods
• /
• v.30 no.5
• /
• pp.517-530
• /
• 2023

Recent studies revealed that fine dust in ambient air may cause various health problems such as respiratory diseases and cancer. To prevent the toxic effects of fine dust, it is important to predict the concentration of fine dust in advance and to identify factors that are closely related to fine dust. In this study, we developed a Bayesian network model for predicting PM10 concentration in Seoul, Korea, and visualized the relationship between important factors. The network was trained by using air quality and meteorological data collected in Seoul between 2018 and 2021. The study results showed that current PM10 concentration, season, carbon monoxide (CO) were the top 3 effective factors in 24 hours ahead prediction of PM10 concentration in Seoul, and that there were interactive effects.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.8
• /
• pp.1446-1452
• /
• 1994

In this paper, Weibull distribution is applied to the lifetme distribution of a device. The method of Bayesian estimate used to estimate requiring parameter in order to predict lifetime of device using accelerated lifetime test data, namely failure time of device. The method of Bayesian estimate needs prior information in order to estimate parameter. But this paper proposed the method of parameter estimate without prior information. As stress is temperature, Arrhenius model is applied and the method of linear estimate is applied to predict lifetime of device at the state of normal operation.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.407-416
• /
• 2001

Sample surveys are usually designed and analyzed to produce estimates for a large area or populations. Therefore, for the small area estimations, sample sizes are often not large enough to give adequate precision. Several small area estimation methods were proposed in recent years concerning with sample sizes. Here, we will compare simple Bayesian approach with Bayesian prediction for small area estimation based on linear regression model. The performance of the proposed method was evaluated through unemployment population data form Economic Active Population(EAP) Survey.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.05a
• /
• pp.171-176
• /
• 2003

This paper deals with the problem of predicting order statistics in samples from a Rayleigh population when an outlier is present. Bayesian predictive distribution and prediction bounds of the p-th order statistics is obtained where an outlier of type $\theta\delta$ is present. In this connection, some identies are derived.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.411-423
• /
• 2009

In the current paper, by extending Verall (1990)'s work, we propose a new Bayesian model for analyzing run-off triangle data. While Verall's (1990) work only account for the calendar year and evolvement time effects, our model further accounts for the "absolute time" effects. We also suggest a Markov Chain Monte Carlo method that can be used for estimating the proposed model. We apply our proposed method to analyzing three empirical examples. The results demonstrate that our method significantly reduces prediction error when compared with the existing methods.

• Geomechanics and Engineering
• /
• v.20 no.2
• /
• pp.113-120
• /
• 2020

Rock damage is the main cause of accidents in underground engineering. It is difficult to predict rock damage accurately by using only one parameter. In this study, a rock failure prediction model was established by using stress, energy, and damage. The prediction level was divided into three levels according to the ratio of the damage threshold stress to the peak stress. A classification predicting model was established, including the stress, energy, damage and AE impact rate using Bayesian method. Results show that the model is good practicability and effectiveness in predicting the degree of rock failure. On the basis of this, a multi-parameter classification predicting deterioration model of rock failure was established. The results provide a new idea for classifying and predicting rockburst.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.437-437
• /
• 2022

The prediction of dam inflow rate is crucial for the management of the largest multi-purpose dam in South Korea, the Soyang Dam. The main issue associated with the management of water resources is the stochastic nature of the reservoir inflow leading to an increase in uncertainty associated with the inflow prediction. The Autoregressive (AR) model is commonly used to provide the simulation and forecast of hydrometeorological data. However, because its estimation is based solely on the time-series data, it has the disadvantage of being unable to account for external variables such as climate information. This study proposes the use of the Autoregressive Exogenous Stochastic Volatility (ARXSV) model within a Bayesian modeling framework for increased predictability of the monthly dam inflow by addressing the exogenous and stochastic factors. This study analyzes 45 years of hydrological input data of the Soyang Dam from the year 1974 to 2019. The result of this study will be beneficial to strengthen the potential use of data-driven models for accurate inflow predictions and better reservoir management.