• Communications for Statistical Applications and Methods
• /
• v.19 no.3
• /
• pp.495-500
• /
• 2012

We consider a Bayesian test of independence in a two-way contingency table that has some zero cells. To do this, we take a three-stage hierarchical Bayesian model under each hypothesis. For prior, we use Dirichlet density to model the marginal cell and each cell probabilities. Our method does not require complicated computation such as a Metropolis-Hastings algorithm to draw samples from each posterior density of parameters. We draw samples using a Gibbs sampler with a grid method. For complicated posterior formulas, we apply the Monte-Carlo integration and the sampling important resampling algorithm. We compare the values of the Bayes factor with the results of a chi-square test and the likelihood ratio test.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.104-110
• /
• 2016

Dense local image descriptors like SIFT are fruitful for capturing salient information about image, shown to be successful in various image-related tasks when formed in bag-of-words representation (i.e., histograms). In this paper we consider to utilize these dense local descriptors in the object tracking problem. A notable aspect of our tracker is that instead of adopting a point estimate for the target model, we account for uncertainty in data noise and model incompleteness by maintaining a distribution over plausible candidate models within the Bayesian framework. The target model is also updated adaptively by the principled Bayesian posterior inference, which admits a closed form within our Dirichlet prior modeling. With empirical evaluations on some video datasets, the proposed method is shown to yield more accurate tracking than baseline histogram-based trackers with the same types of features, often being superior to the appearance-based (visual) trackers.

• Structural Engineering and Mechanics
• /
• v.45 no.4
• /
• pp.495-519
• /
• 2013

This paper investigates properties of integral operators in complex variable boundary integral equation in plane elasticity, which is derived from the Somigliana identity in the complex variable form. The generalized Sokhotski-Plemelj's formulae are used to obtain the BIE in complex variable. The properties of some integral operators in the interior problem are studied in detail. The Neumann and Dirichlet problems are analyzed. The prior condition for solution is studied. The solvability of the formulated problems is addressed. Similar analysis is carried out for the exterior problem. It is found that the properties of some integral operators in the exterior boundary value problem (BVP) are quite different from their counterparts in the interior BVP.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.05a
• /
• pp.157-162
• /
• 2003

Estimates from an EM algorithm are somewhat sensitive to the initial values for the estimates, and it is more likely when the model becomes larger and more complicated. In this article, we examined how the estimates fluctuate during an EM procedure for a recursive model of categorical variables. It is found that the fluctuation takes place mostly during the first half of the procedure and that it can be subdued by applying the Bayesian method of estimation. Both simulation data and real data are used for illustration.

• Communications for Statistical Applications and Methods
• /
• v.7 no.1
• /
• pp.65-86
• /
• 2000

The estimates from an EM when it is applied to a large causal model of 10 or more categorical variables are often subject to the initial values for the estimates. This phenomenon becomes more serious as the model structure becomes more serious as the model structure becomes more complicated involving more variables. In this regard Wu(1983) recommends among others that EMs are implemented several times with different sets of initial values to obtain more appropriate estimates. in this paper a new approach for initial values is proposed. The main idea is that we use initials that are calibrated to data. A simulation result strongly indicates that the calibrated initials give rise to the estimates that are far closer to the true values than the initials that are not calibrated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.10
• /
• pp.5095-5111
• /
• 2016

The Probability Hypothesis Density (PHD) filter is a suboptimal approximation and tractable alternative to the multi-target Bayesian filter based on random finite sets. However, the PHD filter fails to track newborn targets when the target birth intensity is unknown prior to tracking. In this paper, a dual detection-guided newborn target intensity PHD algorithm is developed to solve the problem, where two schemes, namely, a newborn target intensity estimation scheme and improved measurement-driven scheme, are proposed. First, the newborn target intensity estimation scheme, consisting of the Dirichlet distribution with the negative exponent parameter and target velocity feature, is used to recursively estimate the target birth intensity. Then, an improved measurement-driven scheme is introduced to reduce the errors of the estimated number of targets and computational load. Simulation results demonstrate that the proposed algorithm can achieve good performance in terms of target states, target number and computational load when the newborn target intensity is not predefined in multi-target tracking systems.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1547-1555
• /
• 2017

This paper studies Bayesian test of homogeneity in contingency tables made by discretizing a continuous variable. Sometimes when we are considering events of interest in small area setup, we can think of discretization approaches about the continuous variable. If we properly discretize the continuous variable, we can find invisible relationships between areas (groups) and a continuous variable of interest. The proper discretization of the continuous variable can support the alternative hypothesis of the homogeneity test in contingency tables even if the null hypothesis was not rejected through k-sample tests involving one-way ANOVA. In other words, the proportions of variables with a particular level can vary from group to group by the discretization. If we discretize the the continuous variable, it can be treated as an analysis of the contingency table. In this case, the chi-squared test is the most commonly employed method. However, further discretization gives rise to more cells in the table. As a result, the count in the cells becomes smaller and the accuracy of the test becomes lower. To prevent this, we can consider the Bayesian approach and apply it to the setup of the homogeneity test.

• Korea Trade Review
• /
• v.45 no.3
• /
• pp.55-69
• /
• 2020

This study examines the research trends and knowledge structure of international trade studies using topic modeling method, which is one of the main methodologies of text mining. We collected and analyzed English abstracts of 1,868 papers of three Korean major journals in the area of international trade from 2003 to 2019. We used the Latent Dirichlet Allocation(LDA), an unsupervised machine learning algorithm to extract the latent topics from the large quantity of research abstracts. 20 topics are identified without any prior human judgement. The topics reveal topographical maps of research in international trade and are representative and meaningful in the sense that most of them correspond to previously established sub-topics in trade studies. Then we conducted a regression analysis on the document-topic distributions generated by LDA to identify hot and cold topics. We discovered 2 hot topics(internationalization capacity and performance of export companies, economic effect of trade) and 2 cold topics(exchange rate and current account, trade finance). Trade studies are characterized as a interdisciplinary study of three agendas(i.e. international economy, International Business, trade practice), and 20 topics identified can be grouped into these 3 agendas. From the estimated results of the study, we find that the Korean government's active pursuit of FTA and consequent necessity of capacity building in Korean export firms lie behind the popularity of topic selection by the Korean researchers in the area of int'l trade.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.57-68
• /
• 2017

Clustering algorithms attempt to find a partition of a finite set of objects in to a potentially predetermined number of nonempty subsets. Gibbs sampling of a normal mixture of linear mixed regressions with a Dirichlet prior distribution calculates posterior probabilities when the number of clusters was known. Our approach provides simultaneous partitioning and parameter estimation with the computation of classification probabilities. A Monte Carlo study of curve estimation results showed that the model was useful for function estimation. Examples are given to show how these models perform on real data.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.1
• /
• pp.74-86
• /
• 2019

As many existing research fields are matured academically, researchers have encountered numbers of academic, social and other problems that cannot be addressed by internal knowledge and methodologies of existing disciplines. Earlier, pioneers of researchers thus are following a new paradigm that breaks the boundaries between the prior disciplines, fuses them and seeks new approaches. Moreover, developed countries including Korea are actively supporting and fostering the convergence research at the national level. Nevertheless, there is insufficient research to analyze convergence trends in national R&D support projects and what kind of content the projects mainly deal with. This study, therefore, collected and preprocessed the research proposal data of National Research Foundation of Korea, transforming the proposal documents to term-frequency matrices. Based on the matrices, this study derived detailed research topics through Latent Dirichlet Allocation, a kind of topic modeling algorithm. Next, this study identified the research topics each proposal mainly deals with, visualized the convergence relationships, and quantitatively analyze them. Specifically, this study analyzed the centralities of the detailed research topics to derive clues about the convergence of the near future, in addition to visualizing the convergence relationship and analyzing time-varying number of research proposals per each topic. The results of this study can provide specific insights on the research direction to researchers and monitor domestic convergence R&D trends by year.