• Journal of Integrative Natural Science
• /
• v.10 no.1
• /
• pp.33-39
• /
• 2017

Consider the problem of estimating a $p{\times}1$ mean vector ${\theta}(p-q{\geq}3)$, $q=rank(P_V)$ with a projection matrix $P_v$ under the quadratic loss, based on a sample $X_1$, $X_2$, ${\cdots}$, $X_n$. We find a James-Stein type decision rule which shrinks towards projection vector when the underlying distribution is that of a variance mixture of normals and when the norm ${\parallel}{\theta}-P_V{\theta}{\parallel}$ is restricted to a known interval, where $P_V$ is an idempotent and projection matrix and rank $(P_V)=q$. In this case, we characterize a minimal complete class within the class of James-Stein type decision rules. We also characterize the subclass of James-Stein type decision rules that dominate the sample mean.

• Journal of Integrative Natural Science
• /
• v.6 no.4
• /
• pp.251-255
• /
• 2013

For the mean vector of a p-variate normal distribution ($p{\geq}4$), the optimal estimation within the class of modified James-Stein type decision rules under the quadratic loss is given when the underlying distribution is that of a variance mixture of normals and when the norm ${\parallel}{\theta}-\bar{\theta}1{\parallel}$ it known.

• Journal of Mechanical Science and Technology
• /
• v.17 no.6
• /
• pp.935-944
• /
• 2003

Forced convective boiling heat transfer coefficients were predicted for an annular flow inside a horizontal tube for pure refrigerants and nonazeotropic binary refrigerant mixtures. The heat transfer coefficients were calculated based on the turbulent temperature profile in liquid film and vapor core considering the composition difference in vapor and liquid phases, and the nonlinearity in mixing rules for the calculation of mixture properties. The heat transfer coefficients of pure refrigerants were estimated within a standard deviation of 14% compared with available experimental data. For nonazeotropic binary refrigerant mixtures, prediction of the heat transfer coefficients was made with a standard deviation of 18%. The heat transfer coefficients of refrigerant mixtures were lower than linearly interpolated values calculated from the heat transfer coefficients of pure refrigerants. This degradation was represented by several factors such as the difference between the liquid and the overall compositions, the conductivity ratio and the viscosity ratio of both components in refrigerant mixtures. The temperature change due to the concentration gradient was a major factor for the heat transfer degradation and the mass flux itself at the interface had a minor effect.

• Korean Journal of Remote Sensing
• /
• v.31 no.4
• /
• pp.303-319
• /
• 2015

The objectives of this paper are to measure surface imperviousness using three different classification methods: per-pixel, sub-pixel, and object-oriented classification. They are tested on high-spatial resolution QuickBird data at 2.4 meters (four spectral bands and three principal component bands) as well as a medium-spatial resolution Landsat TM image at 30 meters. To measure impervious surfaces, we selected 30 sample sites with different land uses and residential densities across image representing the city of Phoenix, Arizona, USA. For per-pixel an unsupervised classification is first conducted to provide prior knowledge on the possible candidate spectral classes, and then a supervised classification is performed using the maximum-likelihood rule. For sub-pixel classification, a Linear Spectral Mixture Analysis (LSMA) is used to disentangle land cover information from mixed pixels. For object-oriented classification several different sets of scale parameters and expert decision rules are implemented, including a nearest neighbor classifier. The results from these three methods show that the object-oriented approach (accuracy of 91%) provides more accurate results than those achieved by per-pixel algorithm (accuracy of 67% and 83% using Landsat TM and QuickBird, respectively). It is also clear that sub-pixel algorithm gives more accurate results (accuracy of 87%) in case of intensive and dense urban areas using medium-resolution imagery.

• Journal of Industrial Technology
• /
• v.10
• /
• pp.9-13
• /
• 1990

The approximation of the radial distribution functions(RDF) of mixture plays an important role in deriving the mixing rules for the corresponding states principle(CSP). The mean density approximation(MDA), one of the most successful approximations, fails to predict the radial distribution functions when the size ratio in terms of the Lennard-Jones size parameters is greater than 1.5. To get a better prediction of important structural integrals over the radial distribution functions that arise in the asymmetrical attraction contribution of the perturbaton theory, the new type of mean density approximation(NTMDA) is proposed. With this NTMDA, quite reliable results for those integrals for systems with comparatively large ratio of the size parameters are obtained.

• ETRI Journal
• /
• v.39 no.1
• /
• pp.21-29
• /
• 2017

This paper addresses the problem of unsupervised speech separation based on robust non-negative matrix factorization (RNMF) with ${\beta}$-divergence, when neither speech nor noise training data is available beforehand. We propose a robust version of non-negative matrix factorization, inspired by the recently developed sparse and low-rank decomposition, in which the data matrix is decomposed into the sum of a low-rank matrix and a sparse matrix. Efficient multiplicative update rules to minimize the ${\beta}$-divergence-based cost function are derived. A convolutional extension of the proposed algorithm is also proposed, which considers the time dependency of the non-negative noise bases. Experimental speech separation results show that the proposed convolutional RNMF successfully separates the repeating time-varying spectral structures from the magnitude spectrum of the mixture, and does so without any prior training.

• Journal of Korean Elementary Science Education
• /
• v.37 no.2
• /
• pp.188-205
• /
• 2018

For STEM education science teachers usually choose topics which are related to both science and other disciplinary contents. Nevertheless it is not clear for the teachers to adopt what kind of criteria for their choices. Interdisciplinary teaching is not a mixture of science content with another one from different disciplines as resources for the content teaching. Instead the criteria and perspectives for the integration need to be clearly defined. In this study we investigated how to integrate science and other disciplines in terms of interdisciplinary teaching. Family resemblance approach by Wittgenstein, recently revised by Erduran and Dagher, was applied to comparative analysis of science, math, and physical education curriculum documents in Korea. Aim and value, methodological rules and methods, knowledge, and activities in each discipline were compared and analyzed with the view of FRA. Results of the study described alternative criteria of how to find appropriate topics for interdisciplinary teaching.

• Journal of the Korean Data and Information Science Society
• /
• v.11 no.1
• /
• pp.37-45
• /
• 2000

Consider the problem of estimating a $p{\times}1$ mean vector ${\underline{\theta}}(p{\geq}4)$ under the quadratic loss, based on a sample ${\underline{x}_{1}},\;{\cdots}{\underline{x}_{n}}$. We find an optimal decision rule within the class of Lindley type decision rules which shrink the usual one toward the mean of observations when the underlying distribution is that of a variance mixture of normals and when the norm ${\parallel}\;{\underline{\theta}}\;-\;{\bar{\theta}}{\underline{1}}\;{\parallel}$ is known, where ${\bar{\theta}}=(1/p){\sum_{i=1}^p}{\theta}_i$ and $\underline{1}$ is the column vector of ones.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2003.04a
• /
• pp.220-223
• /
• 2003

The methodology of micromechanical finite element method (MFEM) is proposed to calculate the micromechanical strains on fiber and matrix under mechanical and thermal loadings. For micromechanical analysis, composite structure is idealized the square and hexagonal unit cells. Boundary conditions are determined to calculate the effective material properties of composites and the strain magnification matrix. And they are verified by comparing with the results from multi cells, and the strain distributions of the unit cells are in accordance with those of the multi cells. Finally, the effective material properties of composite structure are obtained with respect to its fiber volume fraction and compared with results from rules-of-mixture.

• Journal of Mechanical Science and Technology
• /
• v.18 no.8
• /
• pp.1338-1348
• /
• 2004

A simplified method that models the deflagration process occurring in closed or vented vessels is described. When combustion occurs within the spherical or cylindrical vessels, the flame moves spherically or segmentally to the vessel periphery. The volume and area of each element along the propagating flame front are calculated by using simple geometrical rules. For instabilities and turbulence resulting in enhanced burning rates, a simple analysis results in reasonable agreement with the experimental pressure transients when two burning rates (a laminar burning rate prior to the onset of instability and an enhanced burning rate) were used. Pressure reduction caused by a vent opening at predetermined pressure was modeled. Parameters examined in the modeling include ignition location, mixture concentration, vented area, and vent opening pressure. It was found that venting was effective in reducing the peak pressure experienced in vessels. The model can be expected to estimate reasonable peak pressures and flame front distances by modeling the enhanced burning rates, that is, turbulent enhancement factor.