• Journal of the Korean Statistical Society
• /
• v.26 no.4
• /
• pp.477-491
• /
• 1997

A new predictive classification rule for assigning future cases into one of two multivariate normal population (with unknown normal mixture model) is considered. The development involves calculation of posterior probability of each possible normal-mixture model via a default Bayesian test criterion, called intrinsic Bayes factor, and suggests predictive distribution for future cases to be classified that accounts for model uncertainty by weighting the effect of each model by its posterior probabiliy. In this paper, our interest is focused on constructing the classification rule that takes care of uncertainty about the types of covariance matrices (homogeneity/heterogeneity) involved in the model. For the constructed rule, a Monte Carlo simulation study demonstrates routine application and notes benefits over traditional predictive calssification rule by Geisser (1982).

• Membrane Journal
• /
• v.14 no.4
• /
• pp.312-319
• /
• 2004

The porous SiO$_2$-B$_2$O$_3$ membrane was prepared from Si(OC$_2$$H_5$)$_4$-($CH_3$O)$_3$B-C$_2$$H_5$OH-$H_2O$ system by sol-gel method. In order to investigate the characteristics of this membrane, we examined that using BET, IR spectrophotometer, X-ray diffractometer, SEM and TEM. At $700^{\circ}C$, the surface area of SiO$_2$-B$_2$O$_3$ membrane was 354.398 $m^2$/, the median pore diameter was 0.0048 ${\mu}{\textrm}{m}$, and the particle size of SiO$_2$-B$_2$O$_3$ membrane was 7 nm. The separation properties of the gas mixture ($H_2$/$N_2$) through the SiO$_2$-B$_2$O$_3$ membrane was studied as a function of pressure. The real separation factor($\alpha$) of SiO$_2$-B$_2$O$_3$ membrane for $H_2$/$N_2$ gas mixture was 4.68 at 155.15 cmHg and $25^{\circ}C$. The real separation factor($\alpha$), head separation factor($\beta$) and tail separation factor((equation omitted)) were increased as the pressure of permeation cell increased.

• Journal of the Korean Statistical Society
• /
• v.9 no.2
• /
• pp.145-172
• /
• 1980

Draper and Lawrence (1965a) have given mixture designs for three factors when all the mixture components can vary on the entire factor space so that the region of interest is an equilateral triangle in two dimensions. In this paper their work is extended to the cases when the region of interest is an echelon, parallelogram, pentagon or hexagon, because of the restirctions imposed on some or all of the mixture components. The principles used in the choice of appropriate designs are those originally introduced by Box and Draper(1959). It is assumed that a response surface equation of first order is fitted, but there is a possibility of bias error due to presence of second order terms in the true model. Minimum bias designs for several cases of restricted regions of interest are illustrated.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.8
• /
• pp.149-154
• /
• 1999

FRMLs(Fiber Reinforced Metal Laminates) is a new type of hybrid materials. FRMLs consists of high strength metal and fiber which are laminated using a structural adhesive bond(epoxy resin). The effect of resin mixture ratios on the fatigue crack propagation behavior and mechanical property of Aramid fiber reinforced aluminum composites was investigated. The epoxy, diglycidylether of bisphenol A(DGEBA) was cured with methylene dianiline(MDA) with or without accelerator(K-54). Eight kinds of resin mixture ratio were tested for the experiment ; five kinds of FRMLs(1))epoxy & curing agent) and three kinds of FRMLs(2)(epoxy & curing agent & accelerator). FRMLs(2) have a more effective characteristics on the fatigue crack propagation behavior and mechanical property than FRMLs(1)

• Advances in concrete construction
• /
• v.11 no.2
• /
• pp.99-109
• /
• 2021

Slag blended concrete is widely used as a mineral admixture in the modern concrete industry. This study shows an optimization process that determines the optimal mixture of air-entrained slag blended concrete considering carbonation durability, frost durability, CO2 emission, and materials cost. First, the aim of optimization is set as total cost, which equals material cost plus CO2 emission cost. The constraints of optimization consist of strength, workability, carbonation durability with climate change, frost durability, range of components and component ratio, and absolute volume. A genetic algorithm is used to determine optimal mixtures considering aim function and various constraints. Second, mixture design examples are shown considering four different cases, namely, mixtures without considering carbonation (Case 1), mixtures considering carbonation (Case 2), mixtures considering carbonation coupled with climate change (Case 3), and mixtures of high strength concrete (Case 4). The results show that the carbonization is the controlling factor of the mixture design of the concrete with ordinary strength (the designed strength is 30MPa). To meet the challenge of climate change, stronger concrete must be used. For high-strength slag blended concrete (design strength is 55MPa), strength is the control factor of mixture design.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.12 no.8
• /
• pp.717-724
• /
• 2000

It is important to investigate characteristics of flow of refrigerant/oil mixture circulating in a refrigeration system. Therefore the oil concentration in refrigerant/oil mixture should be measured exactly by the adequate measuring instrument. In this paper, the oil concentration was measured by density monitoring system(DMS) in the liquid-line of a inverter-driven heat pump. Experimental result follows ; the main factor that have an effect on oil concentration refrigerant/oil mixture circulating in a refrigeration system is the momentum and kinematic viscosity of refrigerant/oil mixture compressed by scroll compressor.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2002.10a
• /
• pp.265-268
• /
• 2002

This study is focused on the influence of mixture and construction factor on bleeding amount of concrete According to the results, Amount of bleeding with mixture factor increases with increase of water contents and W/C. Amount of bleeding with construction factors is larger in the case of placing height of 1m than in the case of placing height of 0 and 0.5m. Amount of bleeding is larger at the temperature of 20℃ than at the temperature of 35℃ and 5℃, and increases in order of vibration compacting, standard lamping and non tamping. Therefore, to reduce bleeding, it is thought that it is profitable to reduce water content within the range that fluidity and workability don't go bad, to lower the placing height and not to do compacting too much.

• Korean Chemical Engineering Research
• /
• v.43 no.2
• /
• pp.266-271
• /
• 2005

This paper studied succinic acid recovery from organic acid mixture by using mono-polar membrane electrodialysis. Current efficiency, solute recovery efficiency, energy consumption, and separation factor were measured at various pHs and concentration ratios. The separation factor of succinic acid could be interpreted in terms of ionization degree, molecular weight, ionic conductance, average charge, and initial feed composition.

• Membrane Journal
• /
• v.14 no.4
• /
• pp.298-303
• /
• 2004

PTMSP/PDMS-PEI composite membrane was prepared by solution casting method. To investigate the characteristics of this membrane, the analytical methods such as FT-IR, $^1$H-NMR, DSC, TGA, GPC, and SEM have been utilized. The number-average((equation omitted)) and weight-average((equation omitted)) molecular weight of PTMSP/PDMS copolymer were 501,516 and 675,560 respectively. The separation of the gas mixture($H_2$/$N_2$) through the composite membrane was studied as a function of pressure. The separation factor($\alpha$, $\beta$, (equation omitted)) of the composite membrane used in this work increased as the pressure of permeation cell increased. The real separation factor($\alpha$), head separation factor($\beta$), and tail separation factor ((equation omitted)) of PTMSP/PDMS-PEI composite membrane were 21.50, 49.14 and 1.84 respectively at $\Delta$P 345.55 kPa and $25^{\circ}C$.

• Membrane Journal
• /
• v.13 no.4
• /
• pp.291-299
• /
• 2003

Polymer membranes such as poly(1-trimethylsilyl-1-propyne)-polyetherimide (PTMSP-PEI) and poly(dimethylsiloxane)- polyetherimide (PDMS-PEI) composite membrane were prepared by solution casting method. To investigate the characteristics of these membranes, the analytical methods such as FT-IR, $^1H-NMR,$ DSC, TGA, GPC, and SEM have been utilized. The number-average (equation omitted) and weight-average (equation omitted) molecular weight of PTMSP were 477,920 and 673,329 respectively. The glass transition temperature ($T_g$) of PTMSP was $224^{\circ}C.$ The separation of the gas mixture ($H_2/N_2$) through the composite membranes were studied as a function of pressure. The separation factor (${\alpha}, {\beta},$ quation omitted) of the composite membranes used in this work increased as the pressure of permeation cell increased. The real separation factor (${\alpha}$), head separation factor (${\beta}$), and tail separation factor (equation omitted) of PTMSP-PEI composite membrane were 2.28, 1.17, and 1.96 respectively at ${\Delta}P$ 30psi and $25^{\circ}C.$ (${\alpha}, {\beta}$ and equation omitted of PDMS-PEI composite membrane were 3.70, 1.53, and 2.42 respectively at ${\Delta}P$ 30psi and $25^{\circ}C$.