• Journal of Korean Society for Quality Management
• /
• v.42 no.2
• /
• pp.221-234
• /
• 2014

Purpose: The Purpose of this study is to develop a model for predicting agent churn group in the cosmetics industry. We develope two models, pattern model and matrix model, which are compared regarding the prediction accuracy of churn agents. Finally, we try to conclude if there is statistically significant difference between two models by empirical study. Methods: We develop two models using the part of RFM(Recency, Frequency, Monetary) method which is one of customer segmentation method in traditional CRM study. In order to ensure which model can predict churn agents more precisely between two models, we used CRM data of cosmetics company A in China. Results: Pattern model and matrix model have been developed. we find out that there is statistically significant differences between two models regarding the prediction accuracy. Conclusion: Pattern model and matrix model predict churn agents. Although pattern model employed the trend of monetary mount for six months, matrix model that used the amount of sales per month and the duration of the employment is better than pattern model in prediction accuracy.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.32 no.7
• /
• pp.497-503
• /
• 2008

Hydrogen is considered as a fuel of the future for its renewability and environmental compatibility. The reforming of hydrocarbon fuels is currently the most important source of hydrogen, which is expected to continue for next several decades. In this study, extensive CFD simulations on the steam-methane reforming process were conducted to study the performance of four reaction models, i.e. three Arrhenius-type models and a user-defined function (UDF) model. The accuracies of different reaction models for various operating temperatures and steam carbon ratios (SCRs) were evaluated by comparing their CFD results with zero-dimensional intrinsic model of Xu and Froment. It was found that the UDF model generally produced more accurate results than Arrhenius-type models. However, it was also shown that Arrhenius-type models could be made sufficiently accurate by choosing appropriate reaction coefficients, and thus could also be useful for the simulation of the steam-methane reforming process.

• Journal of computational fluids engineering
• /
• v.20 no.1
• /
• pp.47-56
• /
• 2015

In this paper, we study the effect of various turbulence models by comparing the aerodynamic characteristics and the flow patterns computed for aircraft models. An in-house CFD solver, MSAPv, that solves the three dimensional RANS equations with the turbulence model equations is used. The turbulence models used in this study are the Spalart-Allmaras model, Menter's $k-{\omega}$ SST model, Coakley's $q-{\omega}$ model, and Huang and Coakley's $k-{\varepsilon}$ model. DLR-F6 WB and WBNP configurations are selected for the study. We concentrate on the separated flow pattern variations with the turbulence models at the wing-body junction and the wing-pylon junction as well as drag polar curves.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.38 no.3
• /
• pp.386-396
• /
• 2014

This study examined the effects of Korean celebrity advertising models on the advertising effectiveness for Chinese brands by comparing apparel products with electronic products. In addition, this study explored the effects of gender and monthly expenses on the evaluation of Korean celebrity advertising models. This study targeted 388 Chinese university students in China. The results show that Korean advertising models consist of five attributes (familiarity, visibility, credibility, similarity, and attractiveness) and that advertising effectiveness consists of three factors (attitude toward the advertisement, attitude toward the brand, and purchase intention). The impact of these five advertising model attributes on advertising effectiveness differ for apparel and electronic products. The results also indicate gender and expense differences in the evaluation of Korean celebrity models. We discuss the theoretical and managerial implications of the results along with potential limitations and future research directions.

• Korean Journal of Remote Sensing
• /
• v.28 no.6
• /
• pp.597-609
• /
• 2012

Leaf area index (LAI) is important in explaining the ability of the crop to intercept solar energy for biomass production and in understanding the impact of crop management practices. This paper describes a procedure for estimating LAI as a function of image-derived vegetation indices from temporal series of IKONOS, Landsat TM, and MODIS satellite images using empirical models and demonstrates its use with data collected at Missouri field sites. LAI data were obtained several times during the 2002 growing season at monitoring sites established in two central Missouri experimental fields, one planted to soybean (Glycine max L.) and the other planted to corn (Zea mays L.). Satellite images at varying spatial and spectral resolutions were acquired and the data were extracted to calculate normalized difference vegetation index (NDVI) after geometric and atmospheric correction. Linear, exponential, and expolinear models were developed to relate temporal NDVI to measured LAI data. Models using IKONOS NDVI estimated LAI of both soybean and corn better than those using Landsat TM or MODIS NDVI. Expolinear models provided more accurate results than linear or exponential models.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.7 no.2
• /
• pp.115-125
• /
• 2011

An accurate estimation of software development size is an important factor in calculating reasonable cost of project development and determining its success. In this study, we propose estimation models, using function point based on the functional correlation between software, with empirical data. Three models($FP_{est}(I)$, $FP_{est}(II)$, $FP_{est}(III)$) are developed with correlation and regression analysis. The validity of the models is evaluated by the significance test by comparing values of Mean Magnitude of Relative Error (MMRE) and predictions of each model at level n%. Model $FP_{est}(III)$ proved to be superior to other models such as IFPC(Indicative Function Point Count), EFPC(Estimated Function Point Count), EPFS(Early Prediction of Function Size), $FP_{est}(I)$, and $FP_{est}(II)$. As a result, the accuracy of the model appears to be very high to determine the usefulness of the model to finally overcome weakness of other estimation models. The model can be efficiently used to estimate project development size including software size or manpower allocation.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.70-78
• /
• 2020

Under the situation which customer orders are cancelled unless all products in the order are delivered all at once, this paper concentrates on the purchase dependent demands and explores the systematic approach to implant the purchase dependence into the multi-product inventory model. First, by acknowledging that it is a challenging task to formulate a suitable inventory model for the purchase dependence, we derive the optimal solution condition using an EOQ model and extend the optimal solution condition to periodic review models. Then, through the comparison simulation of four inventory policies regarding several degrees of purchase dependence, we demonstrate that the inventory models which consider the purchase dependence generate less total cost than the inventory models which ignore the purchase dependence. In general, the inventory models which consider the purchase dependence reduce the loss of sales by maintaining more inventories, which results in reducing the total cost. Consequently, the simulation result supports the effectiveness of this paper's approach. In addition, this paper uses the individual order period and joint order period obtained from the EOQ model for the multi-product inventory model. Through the in-depth analysis of comparing the two models, we observe that the model of using the joint order period produces less total cost when the degree of purchase dependence is high, but the model of using the individual order period produces less total cost when the degree of purchase dependence is low.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.10
• /
• pp.1393-1401
• /
• 2014

In this paper the operational characteristics of stand-alone microgrid was analyzed using RTDS simulation models. The accuracy of developed simulation models were verified by comparing with the analysis results using the PSCAD/EMTDC simulation models. The proper scenarios and operation algorithms were developed and analyzed in accordance with various situations that can occur in the actual system, so as to establish operation scheme for the stand-alone microgrid system. The developed simulation models can be effectively utilized to design a newly installed stand-alone microgrid and to develop various operation scenarios for stand-alone microgrid. And these models can be applied for analyzing the transient phenomena due to system fault so that system protection can be properly designed.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.95-102
• /
• 2017

Gamma generalized linear models have received less attention than Poisson and binomial generalized linear models. Therefore, many old-established statistical techniques are still used in gamma generalized linear models. In particular, existing literature and textbooks still use approximate estimates for the dispersion parameter. In this paper we study the efficiency of various dispersion parameter estimators in gamma generalized linear models and perform numerical simulations. Numerical studies show that the maximum likelihood estimator and Cox-Reid adjusted maximum likelihood estimator are recommended and that approximate estimates should be avoided in practice.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.115-123
• /
• 2021

Through machine learning-based load prediction, it is possible to prevent excessive power generation or unnecessary economic investment by estimating the appropriate amount of facility investment in consideration of the load that will increase in the future or providing basic data for policy establishment to distribute the maximum load. However, in order to secure the reliability of the developed load prediction model in the field, the performance comparison verification between the distribution line load prediction models must be preceded, but a comparative performance verification system between the distribution line load prediction models has not yet been established. As a result, it is not possible to accurately determine the performance excellence of the load prediction model because it is not possible to easily determine the likelihood between the load prediction models. In this paper, we developed a reliability verification system for load prediction models including a method of comparing and verifying the performance reliability between machine learning-based load prediction models that were not previously considered, verification process, and verification result visualization methods. Through the developed load prediction model reliability verification system, the objectivity of the load prediction model performance verification can be improved, and the field application utilization of an excellent load prediction model can be increased.