• The Pure and Applied Mathematics
• /
• v.23 no.4
• /
• pp.339-345
• /
• 2016

The set of priors in the representation of Choquet expectation is expressed as the one of equivalent martingale measures under some conditions. We show that the set of priors, $\mathcal{Q}_c$ in (1.1) is the same set of $\mathcal{Q}^{\theta}$ in (1.3).

• The Pure and Applied Mathematics
• /
• v.2 no.2
• /
• pp.83-89
• /
• 1995

A Bayes estimator of the survival distribution function due to Susarla and Van Ryzin(1976) is used to estimate the mth moment of a survival time on the basis of censored observations in a random censorship model. Asymptotic normality of the estimator is proved using the functional version of the delta method.

• Journal of Korean Society for Quality Management
• /
• v.26 no.4
• /
• pp.151-165
• /
• 1998

Consider the linear multivariate regression model $Y=X_1B_1＋X_2B_2＋U$, where Vec(U)~N(0, $\sum \bigotimes I_N$). This paper is concerned with Bayes infreence of the model when it is suspected that the elements of $B_2$ are constrained in the form of intervals. The use of the Gibbs sampler as a method for calculating Bayesian marginal posterior desnities of the parameters under a generalized conjugate prior is developed. It is shown that the a, pp.oach is straightforward to specify distributionally and to implement computationally, with output readily adopted for required inference summaries. The method developed is a, pp.ied to a real problem.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.415-420
• /
• 2002

This paper presents an efficient text categorization algorithm that generates high quality bigrams by using the information gain metric, combined with various frequency thresholds. The bigrams, along with unigrams, are then given as features to a Naive Bayes classifier. The experimental results suggest that the bigrams, while small in number, can substantially contribute to improving text categorization. Upon close examination of the results, we conclude that the algorithm is most successful in correctly classifying more positive documents, but may cause more negative documents to be classified incorrectly.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.469-476
• /
• 2001

As the service of information through web system increases in modern society, many questions and consultations are going on through Home page and E-mail in the hospital. But there are some burdens for the management and postponements for answering the questions. In this paper, we investigate the document classification methods as a primary research of the auto-answering system. On the basis of 1200 documents which are questions of patients, 66% are used for the learning documents and 34% for test documents. All of are also used for the document classification using NBC (Naive Bayes Classifier), common words and coefficient of correlation. As the result of the experiments, the two methods proposed in this paper, that is, common words and coefficient of correlation are higher as much as 3% and 5% respectively than the basic NBC methods. This result shows that the correlation between indexes and categories is more effective than the word frequency in the document classification.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.11
• /
• pp.53-61
• /
• 1996

In this paper, efficient techniques for solder joint inspection have been described. Using three layers of ring shaped LED's with different illumination angles, three frames of images are sequentially obtained. From these images the regions of interest (soldered regions) are segmented, and their characteristic features including the average gray level and the percentage of highlights - refereed to as 2D features - are extracted. Based on the backpropagation algorithm of neural networks, each solder joint is classified intor one of the pre-defined types. If the output value is not in the confidence interval, the distribution of tilt angles-referred to as 3D features - is claculated, and the solder joint is classified based on the bayes classfier. The second classifier requires more computation while providing more information and better performance. The proposed inspection system has been implemented and tested with various types of solder joints in SMDs. The experimental results have verified the validity of this scheme in terms of speed and recognition rate.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.12
• /
• pp.108-115
• /
• 1994

Most pattern classifiers have been designed based on the ML (Maximum Likelihood) training algorithm which is simple and relatively powerful. The ML training is an efficient algorithm to individually estimate the model parameters of each class under the assumption that all class models in a classifier are statistically independent. That assumption, however, is not valid in many real situations, which degrades the performance of the classifier. In this paper, we propose a minimum-error-rate training algorithm based on the MAP (Maximum a Posteriori) approach. The algorithm regards the normalized outputs of the classifier as estimates of the a posteriori probability, and tries to maximize those estimates. According to Bayes decision theory, the proposed algorithm satisfies the condition of minimum-error-rate classificatin. We apply this algorithm to NPM (Neural Prediction Model) for speech recognition, and derive new disrminative training algorithms. Experimental results on ten Korean digits recognition have shown the reduction of 37.5% of the number of recognition errors.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.9
• /
• pp.37-49
• /
• 1992

The standard definition of computational vision is a set of inverse problems of recovering surfaces from images. Thus the common characteristics of the most early vision problems are ill-posed. The main idea for solving ill-posed problems is to restrict the class of admissible solutions by introducing suitable a priori knowledge. Standard regurarization methods lead to satisfactory solutions of early vision problems but cannot deal effectively and directly with a few general problems, such as discontinuity and fusion of information from multiple modules. In this paper, we discuss limitations of standard regularization theory and present new stochastic method. We will outline a rigorous approach to overcome part of ill-posedness of image restoration, edge detection, and stereo vision problems, based on Bayes estimation and MRF(Markov random field) model, that effectively deals with the problems. This result makes one hope that this framework could be useful in the solution of other vision problems.

• The KIPS Transactions:PartB
• /
• v.11B no.7 s.96
• /
• pp.849-854
• /
• 2004

This paper proposes an algorithm to enhance the execution time of kNN in the document classification. The proposed algorithm is to enhance the execution time by minimizing the computing cost of the similarity between two documents by using the list of pairs, while the conventional kNN uses the iist of pairs. The 1ist of pairs can be obtained by applying the matrix transposition to the list of pairs at the training phase of the document classification. This paper analyzed the proposed algorithm in the time complexity and compared it with the conventional kNN. And it compared the proposed algorithm with the conventional kNN by using routers-21578 data experimentally. The experimental results show that the proposed algorithm outperforms kNN about $90{\%}$ in terms of the ex-ecution time.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.27-30
• /
• 2012

One of the most fundamental functions required for an intelligent agent is to estimate its current position based upon uncertain sensor data. In this paper, we explain the implementation of a robot localization system using Particle filters, which are the most effective one of the probabilistic localization methods, and then present the result of experiments for evaluating the performance of our system. Through conducting experiments to compare the effect of the noise-free model with that of the noisy state transition model considering inherent errors of robot actions, we show that it can help improve the performance of the Particle filter localization to apply a state transition model closely approximating the uncertainty of real robot actions.