• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.317-328
• /
• 2002

We first derive group ordering reference priors in a two-way mixed-effects analysis of variance (ANOVA) model. We show that posterior distributions are proper and provide marginal posterior distributions under reference priors. We also examine whether the reference priors satisfy the probability matching criterion. Finally, the reference prior satisfying the probability matching criterion is shown to be good in the sense of frequentist coverage probability of the posterior quantile.

• Journal of the Korean Data and Information Science Society
• /
• 제22권4호
• /
• pp.819-826
• /
• 2011

In this paper, we develop the reference priors for the scale and shape parameters in the nonregular Pareto distribution. We derive the reference priors as noninformative priors and prove the propriety of joint posterior distribution under the general priors including reference priors in the order of inferential importance. Through the simulation study, we compare the reference priors with respect to coverage probabilities of parameter of interest in a frequentist sense.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1409-1418
• /
• 2008

In this paper, we develop the reference priors for the common location parameter in two parameter exponential distributions. We derive the reference priors and prove the propriety of joint posterior distribution under the general prior including the reference priors. Through the simulation study, we show that the proposed reference prior matches the target coverage probabilities in a frequentist sense.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2006년도 학술발표회 논문집
• /
• pp.115-119
• /
• 2006

The goal of this research is to develop and apply the generalized regression neural networks model (GRNNM) embedding genetic algorithm (GA) for pan evaporation, which is missed or ungaged and for the alfalfa reference evapotranspiration, which is not measured in South Korea. The GRNNM-GA is evaluated using the training, the testing, and reproduction performance respectively for the estimation of the PE and the alfalfa reference evapotranspiration. Since the observed data of the alfalfa reference evapotranspiration using lysimeter have not been measured for a long time in South Korea, the PM method is used to assume and estimate the observed alfalfa reference evapotranspiration. From this research, we evaluate the impact of the limited climatical variables on the accuracy of the GRNNM-GA. We should, furthermore, construct the credible data of the PE and the alfalfa reference evapotranspiration and suggest the reference data for irrigation and drainage networks system in South Korea.

• 한국도서관정보학회지
• /
• 제36권2호
• /
• pp.141-163
• /
• 2005

최근에 들어와서 참고문헌이 정보원으로서의 가치가 높아짐에 따라 참고문헌 데이터베이스 구축이 증가하고 있다. 그러나 각 학술지에서 제시하는 참고문헌의 기술규정이 서로 다르고 연구자들마다 참고문헌의 기술규정을 올바르게 인지하지 못한 채로 참고문헌을 다양한 형식으로 기재하고 있다. 이러한 요인들은 참고문헌 데이터베이스의 효과적인 구축을 어렵게 하는 요인이 되고 여다. 따라서 본 연구는 참고문헌 기술규정의 상이성을 면밀히 분석하여 서지기술상의 문제점을 밝히고, 이를 토대로 참고문헌 기술규정 통일화를 위한 방안을 제시하고자 한다.

• 한국멀티미디어학회논문지
• /
• 제9권6호
• /
• pp.750-761
• /
• 2006

As CBD technologies and researches have been matured, component framework as a larger reuse unit than component is being introduced. Especially issues related with adaptation and integration of components in CBD are being raised as a new research topic. The component framework is given as a solution to resolve these issues. However, current approaches don't suggest a sound and comprehensive reference model and development process applying reference model. In order to develop practical and stable component framework, reference model and concrete guidelines are essential elements. In this paper, we propose a generic reference model integrating existing reference models and a design technique of component framework based on it. Especially, we propose concrete and pragmatic guidelines such as how to design component framework architecture's view and style, how to design commonality and variability of component framework, how to design macro workflows among components, and so on. We believe that the proposed reference model becomes basis for component framework development, and the proposed design technique will support reliable and effective development of the component framework.

• 한국의류학회지
• /
• 제28권3_4호
• /
• pp.452-459
• /
• 2004

The purpose of this study was to evaluate the effect of reference fabric for the tactile sensation of worsted fabrics. As specimens, 32 worsted fabrics for spring/fall suits were selected. A series of subjective evaluation for roughness, harshness, coarseness, smoothness, warmth, bulkiness and softness were performed with 20 trained panels. The panels were selected by the test of consistency and trained for 3 weeks to enhance the reproducibility and consistency. Subjective evaluation was performed using 9 points Semantic Differential Scales with and without reference fabric. Results showed that the sensations were very similar between the results for the test of with or without reference. However the standard deviations of ratings for the with-reference were much less than that of without-reference which means the use of reference fabric can reduce the subjective error or can reduce the number of panels to test.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.947-948
• /
• 2006

This paper proposes a robust posture stabilization control method for wheeled mobile robots. To solve the robust posture stabilization, we introduce reference generation mode, reference tracking mode, and reference regulation mode. In reference generation mode, a kinematic time-invariant controller is used to generate the reference trajectory which starts from the initial posture of the actual robot to the desired posture. In reference tracking mode, a sliding mode position controller is employed in such a way that the actual robot can follow the reference trajectory in the desired forward or backward moving direction, even in the presence of the disturbances in the dynamics. In reference regulation mode, a sliding mode heading direction controller is used such that the actual robot can maintain the desired posture against the disturbances. In this way, robust posture stabilization can be achieved at almost all global regions.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.705-708
• /
• 2003

In this paper, we have evaluated the methods to generate the reference signal for the diagnosis of multi-channel signals. The channel signal integrity can be known by the difference between the reference signal and each channel value. The generation method of reference signal is important in the diagnosis of multi-channel measurement system. The continuous weighting average method rejects the abnormal signal using weighting method and makes the reference signal using sumation of all channel values. This gives the simple and reasonable reference signal. The principle component analysis, one of the multivariate analysis methods, and the neural network method give the reliable reference signal by using signal models, and learning algorithm. Two methods can make the reliable reference if all signals are normal, but any signal having the drift have an effect on the reference.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.653-669
• /
• 2024

Dynamic scene deblurring is a complex computer vision problem owing to its difficulty to model mathematically. In this paper, we present a novel approach for image deblurring with the help of the sharp reference image, which utilizes the reference image for high-quality and high-frequency detail results. To better utilize the clear reference image, we develop an encoder-decoder network and two novel modules are designed to guide the network for better image restoration. The proposed Reference Extraction and Aggregation Module can effectively establish the correspondence between blurry image and reference image and explore the most relevant features for better blur removal and the proposed Spatial Feature Fusion Module enables the encoder to perceive blur information at different spatial scales. In the final, the multi-scale feature maps from the encoder and cascaded Reference Extraction and Aggregation Modules are integrated into the decoder for a global fusion and representation. Extensive quantitative and qualitative experimental results from the different benchmarks show the effectiveness of our proposed method.