• Journal of Korea Multimedia Society
• /
• v.8 no.6
• /
• pp.783-789
• /
• 2005

This paper is proposed a watermarking technique for copyright protection of multimedia contents. We proposed adaptive watermark detection algorithm using stochastic perceptual model and statistical decision method in DMWT(discrete multi wavelet transform) domain. The stochastic perceptual model calculates NVF(noise visibility function) based on statistical characteristic in the DMWT. Watermark detection algorithm used the likelihood ratio depend on Bayes' decision theory by reliable detection measure and Neyman-Pearson criterion. To reduce visual artifact of image, in this paper, adaptively decide the embedding number of watermark based on DMWT, and then the watermark embedding strength differently at edge and texture region and flat region embedded when watermark embedding minimize distortion of image. In experiment results, the proposed statistical decision method based on multiwavelet domain could decide watermark detection.

• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.605-616
• /
• 2000

Three primary interests frequently raised by mortgage companies are introduced and the corresponding statistical approaches for the default probability in mortgage companies are examined. Statistical models considered in this paper are time series, logistic regression, decision tree, neural network, and discrete time models. Usage of the models is illustrated using an artificially modified data set and the corresponding models are evaluated in appropriate manners.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.7
• /
• pp.1411-1418
• /
• 1997

This paper presents a statistical analysis of the decision throeshold for derect-sequence spread-spectrum (DS-SS) prallel Pseudo-Noise (PN) code acquistion with a reference filter. The probabilities of detection and false alarm are derived, and the mean acquistion time is evaluated as a measure of the system performance in both nonfading and Rician fiding channels. From the statistical sresults, it is shown that in the performance analysis of the parallel acquisition system with reference filtering, the statistical evaluaion of the decision threshold seems more appropriate than the approximation of the decision threshold adopted in the other schemes[2,3].

• The Korean Journal of Applied Statistics
• /
• v.10 no.2
• /
• pp.385-401
• /
• 1997

Cumulative sum (CUSUM) control charts are widely used in industry for the statistical process control. The statistical design procedure in CUSUM charts tells how to choose the decision interval value. The decision interval is primarily determied by the desired in - control ARL - that is, by the acceptable frequency of false out-of-control signals. In this paper we propose a new approximation method for calculating the ARL and determining the decision interval. The performance of the proposed method is examined by evaluating the accuracy of estimated ARLs and decision intervals in normal and exponential cases.

• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• pp.959-969
• /
• 2009

Decision tree is a typical tool for data classification. This tool is implemented in DAVIS (Huh and Song, 2002). All the visualization tools and statistical clustering tools implemented in DAVIS can communicate with the decision tree. This paper presents methods to apply data visualization techniques to the decision tree using a real data set.

• Communications for Statistical Applications and Methods
• /
• v.8 no.3
• /
• pp.823-829
• /
• 2001

Even though a rapid development of modem medical science, paralysis disease is a highly dangerous and murderous disease. Shin et al. (1978) constructed the diagnosis expert system which identify a type of the paralysis disease from symptoms of a paralysis disease patients by using the canonical discriminant analysis. The decision tree-based analysis, however, has advantages over the method used in Shin et al. (1998), such as it does not need assumptions - linearity and normality, and suggest appropriate diagnosis procedure which is easily explained. In this paper, we applied the decision tree to construct the model which Identify a type of the paralysis disease.

• Journal of Korean Institute of Industrial Engineers
• /
• v.15 no.2
• /
• pp.33-44
• /
• 1989

This paper presents stochastic-statistical dominance rules which eliminate dominated alternatives thereby reduce the number of satisficing alternatives to a manageable size so that the decision maker can choose the best alternative among them when neither the utility function nor the probability distribution of outcomes is exactly known. Specifically, it is assumed that only the characteristics of the utility function and the value function are known. Also, it is assumed that prior probabilities of the mutually exclusive states of nature are not known, but their relative bounds are known. First, the notion of relative risk aversion is used to describe the decision maker's attitude toward risk, which is defined with the acknowledgement that the utility function of the decision maker is a composite function of a cardinal value function and a utility function with-respect to the value function. Then, stochastic-statistical dominance rules are developed to screen out dominated alternatives according to the decision maker's attitude toward risk represented in the form of the measure of relative risk aversion.

• Communications for Statistical Applications and Methods
• /
• v.24 no.6
• /
• pp.543-559
• /
• 2017

Tree-based regression and classification ensembles form a standard part of the data-science toolkit. Many commonly used methods take an algorithmic view, proposing greedy methods for constructing decision trees; examples include the classification and regression trees algorithm, boosted decision trees, and random forests. Recent history has seen a surge of interest in Bayesian techniques for constructing decision tree ensembles, with these methods frequently outperforming their algorithmic counterparts. The goal of this article is to survey the landscape surrounding Bayesian decision tree methods, and to discuss recent modeling and computational developments. We provide connections between Bayesian tree-based methods and existing machine learning techniques, and outline several recent theoretical developments establishing frequentist consistency and rates of convergence for the posterior distribution. The methodology we present is applicable for a wide variety of statistical tasks including regression, classification, modeling of count data, and many others. We illustrate the methodology on both simulated and real datasets.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.414-422
• /
• 2022

Presented in this paper is a methodology for combining a Bayesian statistical approach with Data Quality Objectives (a structured decision-making method) to provide increased levels of confidence in analytical data when approaching a waste boundary. Development of sampling and analysis plans for the characterisation of radioactive waste often use a simple, one pass statistical approach as underpinning for the sampling schedule. Using a Bayesian statistical approach introduces the concept of Prior information giving an adaptive sample strategy based on previous knowledge. This aligns more closely with the iterative approach demanded of the most commonly used structured decision-making tool in this area (Data Quality Objectives) and the potential to provide a more fully underpinned justification than the more traditional statistical approach. The approach described has been developed in a UK regulatory context but is translated to a waste stream from the Fukushima Daiichi Nuclear Power Station to demonstrate how the methodology can be applied in this context to support decision making regarding the ultimate disposal option for radioactive waste in a more global context.

• Journal of the Korean Statistical Society
• /
• v.8 no.1
• /
• pp.15-21
• /
• 1979

A zone of sensitivity is developed to investigate the effect of nonnormality on the Bayes decision function for testing mean of a normal population when either parent or prior belongs to Edgeworthian family of moderately nonnormal probability density functions.