• Korean Management Science Review
• /
• v.10 no.2
• /
• pp.27-42
• /
• 1993

Markov chain models can be used to predict the state of the system in the future. We extend the existing Markov chain models in two ways. For the stationary model, we propose a procedure that obtains the transition probabilities by appling the empirical Bayes method, in which the parameters of the prior distribution in the Bayes estimator are obtained on the collaternal micro data. For non-stationary model, we suggest a procedure that obtains a time-varying transition probabilities as a function of the exogenous variables. To illustrate the effectiveness of our extended models, the models are applied to the macro and micro time-series data generated from actual survey. Our stationary model yields reliable parameter values of the prior distribution. And our non-stationary model can predict the variable transition probabilities effectively.

• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.117-129
• /
• 2012

Road safety audit is the preventive enhancement strategy for safety. : it gets rid of beforehand the potential factor of a traffic accident in the stage of road planning and design and it evaluates the appropriation for road geometric structure or safety facility to prevent traffic accident in the stage of operation after the construction. Since this strategy is introduced to our country in the early 2000s, various projects have been processed and it was legislated recently. And now, the evaluation of past project for its continuation is needed. Therefore, in this study the evaluation of road safety audit on existing freeway is performed. The spatial extent of this study is Yong-dong line on which the safety treatment was executed in 2005 and 2006. And, the temporal range of this study is each 2-year of before and after from 2005 and 2006. The empirical bayes method of observational evaluation studies is applied to analyze. As a result, there is an effect of improvement on most of treated sections. But there is ineffective or negligible on some sections. Compared with the detail of treatment on each section, the effect of multiple or various treatments is good for that section. On the other hand, the section on which effect doesn't appear is the result of single or unimportant treatments. Throughout these results, the concrete analysis can be performed and the countermeasures designed for the section on which effect doesn't appear. Also it is used as reference to the future plan and direction of road safety audit on existing freeway.

• Journal of Korean Society of Transportation
• /
• v.24 no.2 s.88
• /
• pp.113-124
• /
• 2006

Among tile traffic safety facilities, median barriers are installed above 4-lane national roads due to the awareness of haying an effect on preventing the front collision. Studies about the installation effect analysis of median harrier have been carried out through both at home and outside, mainly indicating total accident reduction effect on pertinent sections. In sum, study about how the accident occurrence form is changed at the point classified by the accident type or severity is insignificant. In the case of outside the country, calculating the accident reduction effect according to the type of median barriers is main research and in domestic, though there is a part of researches assessing reduction effect by accident types, it is not reliable in the view or statistics because of using only 1year's before-aftev data installing the facility, So in this Paper. it is the main purpose to presume the accident conversion effect. For this, we conduct an investigation and collect data about 7-year's accident data containing before-after Project, safety facilities foundation records and index of road alignment on the subject of 4-1ane national roads(108.6km) existing median barrier. Next. using the empirical bayes method, we estimate a model construction and accident conversion effect of accident type severity. We expect the result or this Paper will be applied for a policy execution and Presentation of facility standard related to median barrier from now on.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.5D
• /
• pp.453-459
• /
• 2010

In the study of traffic safety, it is utmost important to obtain more reliable estimates of the expected crashes for a site (or a segment). The observed crashes have been mainly used as the estimate of the expected crashes in Korea, while the empirical Bayes (EB) estimates based on the Poisson-gamma mixture model have been used in the USA and several European countries. Although numerous studies have used the EB method for estimating the expected crashes and/or the effectiveness of the safety countermeasures, no past studies examine the difference in the estimation errors between the two estimates. Thus, this study compares the estimation errors of the two estimates using a Monte Carlo simulation study. By analyzing the crash dataset at 3,000,000 simulated sites, this study reveals that the estimation errors of the EB estimates are always less than those of the observed crashes. Hence, it is imperative to incorporate the EB method into the traffic safety research guideline in Korea. However, the results show that the differences in the estimation errors between the two estimates decrease as the uncertainty of the prior distribution increases. Consequently, it is recommended that the EB method be used with reliable hyper-parameter estimates after conducting a comprehensive examination on the estimated negative binomial model.

• Journal of KIISE:Software and Applications
• /
• v.29 no.12
• /
• pp.966-978
• /
• 2002

There are two important problems in improving text classification systems based on machine learning approach. The first one, called "selection problem", is how to select a minimum number of informative documents from a given document collection. The second one, called "composition problem", is how to reorganize selected training documents so that they can fit an adopted learning method. The former problem is addressed in "active learning" algorithms, and the latter is discussed in "boosting" algorithms. This paper proposes a new learning method, called AdaBUS, which proactively solves the above problems in the context of Naive Bayes classification systems. The proposed method constructs more accurate classification hypothesis by increasing the valiance in "weak" hypotheses that determine the final classification hypothesis. Consequently, the proposed algorithm yields perturbation effect makes the boosting algorithm work properly. Through the empirical experiment using the Routers-21578 document collection, we show that the AdaBUS algorithm more significantly improves the Naive Bayes-based classification system than other conventional learning methodson system than other conventional learning methods

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.05a
• /
• pp.1-5
• /
• 2002

We consider the problem of optimal bandwidth choice for nonparametric classification, based on kernel density estimators, where the problem of interest is distinguishing between two univariate distributions. When the densities intersect at a single point, optimal bandwidth choice depends on curvatures of the densities at that point. The problem of empirical bandwidth selection and classifying data in the tails of a distribution are also addressed.

• Communications for Statistical Applications and Methods
• /
• v.4 no.1
• /
• pp.33-39
• /
• 1997

Tsutakawa(1988) proposed a mixed model for using empirical Bayes method to study the geographic variability in mortality rates of a disease. In particular cases of the analysis in mortality rate, we need to consider the effect of time. If observed data are collected annually for the time period, then time effect will be emphasized. Here, an extended model for estimating the geographic effect and the mortality rates of the disease with time effect is proposed.

• The Mathematical Education
• /
• v.23 no.1
• /
• pp.45-50
• /
• 1984

A problem of estimating the means of Poisson populations using independent samples is considered. The total loss is the sum of component, normalized squared error losses. An empirical Bayes estimator is derived and compared, by Monte Carlo methods, with existing estimators which are proposed as improving estimators upon the usual one. Monte Carlo results show that the performance of the derived estimator is satisfactory over the whole parameter space.

• Journal of the Korean Statistical Society
• /
• v.36 no.3
• /
• pp.367-372
• /
• 2007

Classification as a tool to extract information from data plays an important role in science and engineering. Among various classification methodologies, support vector machine has recently seen significant developments. The central problem this paper addresses is the accuracy of support vector machine. In particular, we are interested in the situations where fast rates of convergence to the Bayes risk can be achieved by support vector machine. Through learning examples, we illustrate that support vector machine may yield fast rates if the space spanned by an adopted kernel is sufficiently large.

• Journal of Korean Society for Quality Management
• /
• v.29 no.1
• /
• pp.11-23
• /
• 2001

This paper is concerned with suggesting a Bayesian method for variable selection in multinomial logit model. It is based upon an optimal rule suggested by use of Bayes rule which minimizes a risk induced by selecting the multinomial logit model. The rule is to find a subset of variables that maximizes the marginal likelihood of the model. We also propose a Laplace-Metropolis algorithm intended to suggest a simple method forestimating the marginal likelihood of the model. Based upon two examples, artificial data and empirical data examples, the Bayesian method is illustrated and its efficiency is examined.