• Journal of the Korean Statistical Society
• /
• v.20 no.2
• /
• pp.108-117
• /
• 1991

A parametric empirical Bayes procedure is proposed and studied to compare treatments simultaneously with the best. Minimum Bayes risk lower bounds are derived for an additive loss function, and their relationship with Bayesian simultaneous confidence lower bounds is given. For the proposed empirical Bayes procedure, the nominal confidence level both in Bayesian sense and in frequentist's sense is shown to be controlled asymptotically. For practical implementation, a measure of significance similar to f-value is suggested with an illustrative example.

• Phonetics and Speech Sciences
• /
• v.3 no.2
• /
• pp.65-70
• /
• 2011

Recently, audio-visual speech recognition (AVSR) has been studied to cope with noise problems in speech recognition. In this paper we propose a novel method of deciding weighting factors for audio-visual information fusion. We adopt the particle swarm optimization (PSO) to weighting factor determination. The AVSR experiments show that PSO-based normalized confidence measures (NCM) improve the rejection performance of mis-recognized words by 33%.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.163-168
• /
• 2009

Given the specific mean shift outlier model, the standard approaches to obtaining test statistics for outliers are discussed. Accuracy of outlier tests is investigated using subset curvatures. These subset curvatures appear to be reliable indicators of the adequacy of the linearization based test. Also, we consider obtaining graphical summaries of uncertainty in estimating parameters through confidence curves. The results are applied to the problem of assessing the accuracy of outlier tests.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.1
• /
• pp.97-106
• /
• 2014

The development of big data technology was to more accurately predict diversified contemporary society and to more efficiently operate it, and to enable impossible technique in the past. This technology can be utilized in various fields such as the social science, economics, politics, cultural sector, and science technology at the national level. It is a prerequisite to find valuable information by data mining techniques in order to analyze big data. Data mining techniques associated with big data involve text mining, opinion mining, cluster analysis, association rule mining, and so on. The most widely used data mining technique is to explore association rules. This technique has been used to find the relationship between each set of items based on the association thresholds such as support, confidence, lift, similarity measures, etc.This paper proposed cosine net confidence as association thresholds, and checked the conditions of interestingness measure proposed by Piatetsky-Shapiro, and examined various characteristics. The comparative studies with basic confidence and cosine similarity, and cosine net confidence were shown by numerical example. The results showed that cosine net confidence are better than basic confidence and cosine similarity because of the relevant direction.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.2
• /
• pp.51-62
• /
• 2020

The study was conducted to verify the causality of the ability of high school and college dance majors to influence the successful goal orientation and how the change in goal affects the sense of dance performance self-confidence. In this regard, 172 dance majors were collected to collect data on their belief in dance ability, the direction of mastery goal of approach and avoidance, and the measure of confidence in dance performance, and the results of their studies were derived through correlation and structural equation analysis and path analysis. The analysis results showed reasonable factor structure and reliability based on the preceding study of feasibility analysis results between variables. Thus, the structural equation for the study variables confirmed that the theoretical hypothesis was suitable, and the path of each variable was verified through the path analysis. The analysis showed that the increased belief that ability can be improved by effort has been found to improve the effort and consequently the confidence in dancing. Also, the fixed belief that ability is not changing in a fixed sense has been found to affect the avoidance goal and reduce confidence. It can be interpreted that the more one believes that one can change one's ability by effort, the more one strengthens one's actions to achieve one's goal, thereby improving one's dance confidence. Therefore, it is deemed necessary for subsequent studies to explore whether the paths of these models differ by their major or dance careers, and to apply variables that can measure the success or failure of actual performances to enhance the explanatory power of these research variables.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.293-301
• /
• 2001

This paper reviews three methods to compute a pointwise confidence interval of neuro-fuzzy models and compares their estimation perfonnanee through simulations. The eOITl.putation methods under consideration include stacked generalization using cross-validation, predictive error bar in regressive models, and local reliability measure for the networks employing a local representation scheme. These methods implemented on the neuro-fuzzy models are applied to the problems of simple function approximation and chaotic time series prediction. The results of reliability estimation are compared both quantitatively and qualitatively.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.3
• /
• pp.495-503
• /
• 2011

The most widely used data mining technique is to find association rules. Association rule mining is the method to quantify the relationship between each set of items in very huge database based on the association thresholds. There are some basic association thresholds to explore meaningful association rules ; support, confidence, lift, etc. Among them, confidence is the most frequently used, but it has the drawback that it can not determine the direction of the association. The net confidence and the attributably pure confidence were developed to compensate for this drawback, but they have other drawbacks.In this paper we consider some predictive similarity measures for binary data in cluster analysis and multi-dimensional analysis as association threshold to compensate for these drawbacks. The comparative studies with net confidence, attributably pure confidence, and some predictive similarity measures are shown by numerical example.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.126-132
• /
• 2023

Object recognition is a technology that detects and identifies various objects in images and videos. LBP is a descriptor that operates robustly to illumination variations and is actively used in object recognition. LBP considers the range of neighboring pixels, the order of combining the neighbors after the comparison operation, and the starting position of combining. In particular, the starting position of the LBP becomes the "most significant bit"; it dramatically affects the performance of object recognition. In this paper, based on the N starting positions, the data most similar to the input data are searched in each of the N feature spaces. Object recognition is performed by the confidence measure that can compare different results of each feature space under the same criterion and select the most reliable result. In the experimental results, it was confirmed that there is a difference in performance depending on the starting position of LBP. The proposed method showed a high performance of up to 12.66% compared to the recognition performance of the existing LBP.

• Communications for Statistical Applications and Methods
• /
• v.15 no.2
• /
• pp.147-159
• /
• 2008

We consider using ranked set sampling methods to draw inference about the three well-known measures of overlap, namely Matusita's measure $\rho$, Morisita's measure $\lambda$ and Weitzman's measure $\Delta$. Two exponential populations with different means are considered. Due to the difficulties of calculating the precision or the bias of the resulting estimators of overlap measures, because there are no closed-form exact formulas for their variances and their exact sampling distributions, Monte Carlo evaluations are used. Confidence intervals for those measures are also constructed via the bootstrap method and Taylor series approximation.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.20 no.1
• /
• pp.37-46
• /
• 2014

Purpose: This study was to measure and identify the differences of perceived confidence in practice of core basic nursing skills performed by new graduate nurses in Korea. Methods: The tool used in this study was a questionnaire for measuring the confidence in 20 items of core basic nursing skills which was structured based on Korean Accreditation Board of Nursing Education tool. 231 new graduate nurses participated in this study. The reliability of this questionnaire had Cronbach's ${\alpha}$ .918. Results: Subjects who experienced simulation education and standard patient education were 86.6% and 35.9%, respectively. Item enema intervention, tracheostomy care, and blood transfusion showed low practice confidence level. These items showed significant differences on whether the subjects experienced simulation and clinical practicum or not. Conclusion: Developing and managing clinical education program under deep cooperation between practicum agency and clinical instructor are needed. Simulation practicum will complement insufficient core basic nursing skills between newly graduated nurses before they allocate at the clinical department.