• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.837-842
• /
• 2008

Students taking linear model courses have difficulty in determining which parametric functions are estimable when the design matrix of a linear model is rank deficient. In this note a special form of estimable functions is presented with a linear combination of some orthogonal estimable functions. Here, the orthogonality means the least squares estimators of the estimable functions are uncorrelated and have the same variance. The number of the orthogonal estimable functions composing the special form is equal to the rank of the design matrix. The orthogonal estimable functions can be easily obtained through the singular value decomposition of the design matrix.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.372-376
• /
• 1989

One of the major difficulties with modular approach model of separation process simulation is initial guess problem. Only accurate initial guess make the problem converge and large computer memory and calculating time are required. In this study, we use the initial bottom guess value same as given feed condition and update the value the .theta.method. So we examine;(1)the problem converges using initial guess with large range, (2)computer memory and calculating time are reduced considerably.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1995.06a
• /
• pp.64-73
• /
• 1995

The forging limit curves of sintered porous metals have been calculated, in terms of the two principal strains, by the Lee-Kuhn initial imperfection model. The various yield functions for porous metal have been applied to the initial imperfection model. When the value of initial imperfection ratio equals the value of initial relative density of the sintered porous metals, the calculation values are in good agreement with the measured data. The slopes of the forging limit curves are about 0.5 as in the case of non-porous metals.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.2
• /
• pp.331-337
• /
• 2004

In the analysis of massive volume data, a neural network model is a useful tool. To implement the Neural network model, it is important to select initial value. Since the initial values are generally used as random value in the neural network, the convergent performance and the prediction rate of model are not stable. To overcome the drawback a possible method use samples randomly selected from the whole data set. That is, coefficients estimated by logistic regression based on the samples are the initial values.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1176-1178
• /
• 1998

This paper presents a model reduction procedure of the high order MIMO (multi input multi output) controller designed for the steam turbine in the generating plant. The application limit to reduction of the order is reviewed by variation in Hankel singular value as well as by variation in singular value Bode diagrams of transfer function matrices. Dynamic performances in the time domain are also compared for each reduced order model.

• Journal of the military operations research society of Korea
• /
• v.16 no.2
• /
• pp.43-55
• /
• 1990

When people choose one way of action from various alternatives, they make value judgement. Due to limited capacity of human information processing, however, a decision maker cannot reflect his true subjective utility in evaluating alternatives especially for a problem which has multiattribute. The analytic hierachy model is a tool which converts scores derived from pairwise comparison with respect to each attribute to overall scores of the alternatives. Then the overall scores are utilized to choose an alternative. Therefore this model can be used to support people's value judgement.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.469-472
• /
• 2003

A life cycle cost analysis model for public water supply systems should be different from the ones for other civil and architectural facilities as the operation and the maintenance cost of the water supply systems mainly come from the various mechanical systems and the pipeline systems of the collecting/treating/distributing facilities. This paper presents a cost classification scheme and a life cycle cost analysis model for public water supply systems. A value analysis (VA) procedure that is well suited for practical purposes is also presented. The presented life cycle model and the value analysis procedure were applied to a real world project, and this case study is discussed in the paper. The model and the procedure presented in this study can greatly contribute to the value-oriented design alternative selection, the estimation of the maintenance cost, and the allocation of budget for water supply system construction projects.

• Knowledge Management Research
• /
• v.11 no.1
• /
• pp.83-96
• /
• 2010

In this study, the effect of firm's patent competency on the their management performance was analysed. The number of patents granted to Korean firms, patent grade score as of the firm's patent competence were considered in the perspectives of patent volume and patent value respectively. Specially the analysis were implemented focusing on the high performance venture ranked 200th in Korea. The patent source data were from the Korean Intellectual Property Office, Korean Credit Evaluation Information Company, and the Patent Evaluation System of KIPO and KIPA. And the year sales and net profit volume as of the firm's management performance data from the KIS. Management performance data are consisted of the mean sales, net profit and ROI during the 4 years from FY2005 to FY2008. Major results are as follows. The regression model were proved significantly that the year sales volume and net profit are effected by the number of patents and patent grade score. But the model including the ROI were shown not significantly. So it can be concluded that patent volume and patent value are the important factors on firm's financial performance as of the year sales volume and net profit. Also the regression model including the control variables, firm's number of employee and business year, the number of patents and patent grade score are the significant factors on firms performance. And regression coefficients of patent value model were higher than these of patent volume model. So it can be recognized that patent value of firms' patent competency are more important factor than the patent volume.

• Korean Journal of Human Ecology
• /
• v.21 no.6
• /
• pp.1185-1198
• /
• 2012

The purposes of this study were to investigate the relationships between e-loyalty formation process and satisfaction for apparel products by testing the research model developing upon prior researches, and to analyze the differences of the structural model between two groups (high satisfaction group and low satisfaction group). A total of 356 respondents participated through a convenience sampling at universities in Busan. Data were analyzed by a structural equation model analysis. The results were as followings: First, for the structural model, the attributes of shopping malls (e.g., e-store attributes and product attributes) affected consumer satisfaction which influenced the e-loyalty of shopping malls, mediated by value perception. Second, high-satisfaction group evaluated more importantly the attributes of shopping malls, higher perceived the value of products and web sites, more satisfied the mall, and had greater loyalty of online shopping malls than low-satisfaction group. Third, there were significant differences between high-satisfaction group and low-satisfaction group in the e-loyalty model for apparels. Specifically, for high-satisfaction group, the e-store attributes were more likely to influence the value perception of products and web sites than low-satisfaction group, while low-satisfaction group was the higher perceived the value of products, the more they satisfied and then the greater e-loyalty respectively. According to the findings, the implications and future suggestions related to e-loyalty of shopping malls for apparels are provided.

• Journal of Korean Society on Water Environment
• /
• v.32 no.6
• /
• pp.552-561
• /
• 2016

For the prediction of hydrologic phenomenon, predicting future land use change is a very important task. This study aimed to compare and analyze the two land use change models, CLUE-S and SLEUTH3-R. The analysis of two models were performed based on the MSR value such that the model with more reliable MSR value can be recommended as an appropriate land use change prediction model. The model performance was examined by applying to the Gapcheon A watershed. Land use map of the study area of 2007 obtained from the Ministry of Environment was compared with the predicted land use map obtained from each of the two models. The result from both models showed somewhat similar results. The MSR value obtained from CLUE-S was 0.564, while that from SLEUTH3-R was 0.586. However, when land use map of 2010 was compared with predicted land use map obtained from the two models in same manner, the MSR value obtained from CLUE-S' was 0.500 while that from SLEUTH3-R was decreased to 0.397, an approximately 32.3% decrease from previous value of 2007. Moreover, SLEUTH3-R showed more sensitivity in conversion of urban areas, as compared to other land use types. Therefore, for the prediction of future land use change, CLUE-S model is more reliable than SLEUTH3-R.