• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.225-238
• /
• 2021

The ROC, TOC, and TROC curves, which are visually descriptive methods of exploring the performance of the binary classification model, are implemented with TP, TN, FP, FN which consist of the confusion matrix, as well as their ratios TPR, TNR, FPR, FNR. In this study, we consider two types odds and then propose an odds curve representing these odds. And show the relationship between the odds curve and ROC curve. Based on the odds curve, we propose not only two statistics that measure the discriminant power of the odds curve but also the criteria for validation ratings of the odds curve. According to the shape of the odds curves, two classification distributions can be estimated and a criterion for validation ratings can be determined. The odds curve can be meaningfully used like other visual methods, and two kinds of measures for the discriminant power can be also applied together as an alternative criterion.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2007.12a
• /
• pp.304-306
• /
• 2007

In this paper, we presents a scheme for the parameter estimation and optimal control scheme for apparatus of container crane system. For parameter estimation, first, we construct the open loop of the container crane system and estimate its parameters based on input-output data, a real-coded genetic algorithm(RCGA) and the model adjustment technique. The RCGA plays an important role in parameter estimation as an adaptive mechanism. For controller design, state feedback gain matrix is searched by another RCGA and the estimated model. The performance of the proposed methods are demonstrated through a set of simulation and experiments of the experimental apparatus.

• Journal of Navigation and Port Research
• /
• v.32 no.8
• /
• pp.675-683
• /
• 2008

This paper develops a framework of combining Balanced Scorecard (BSC) and Quality Function Deployment (QFD) using Analytic Hierarchy Process (AHP) and Analytic Network Process (ANP) and evaluates the performance factors of container terminals using the framework. This study designs a BSC of container terminals and then transforms this into QFD in order to determine the priority of performance factors. This paper provides a modified QFD model and shows a causal relationship among perspectives of BSC to find out critical performance factors of container terminals. This modified QFD model is different from traditional models in that a correlation and relation matrix is presented. This combination of BSC and QFD with AHP and ANP helps to create more realistic and accurate representation of QFD models.

• Resources Recycling
• /
• v.27 no.3
• /
• pp.66-77
• /
• 2018

The import amount of rare metal in Korea is about 6,034 million USD, but the self-sufficiency of rare metals is about only 1%. In order to secure the stable supply of rare metals, it is necessary to operate an efficient stockpile system. In this study, we established a system to assess the adequacy of stockpiles by quantifying the risk factors of tangible and intangible risks in order to establish an efficient stockpile strategy. The model developed in this study aims to select the rare metals that need to be stockpiled first and to suggest the direction of the stockpiling policy in accordance with technological change and market change from the mid and long term viewpoint. The evaluation results derived from the model can quantitatively measure the security level of each rare metal and enable relative comparison between the rare metals using criticality matrix. Therefore, it is expected that more efficient stockpile policy will be possible if the proposed model is utilized in the future policy making.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.149-157
• /
• 2011

Undecided inference could be regarded as a missing data problem such as MARand MNAR. Under the assumption of MAR, undecided inference make use of logistic regression model. The probability of default for the undecided group is obtained with regression coefficient vectors for the decided group and compare with the probability of default for the decided group. And under the assumption of MNAR, undecide dinference make use of logistic regression model with additional feature random vector. Simulation results based on two kinds of real data are obtained and compared. It is found that the misclassification rates are not much different from the rate of rawdata under the assumption of MAR. However the misclassification rates under the assumption of MNAR are less than those under the assumption of MAR, and as the ratio of the undecided group is increasing, the misclassification rates is decreasing.

• Nuclear Engineering and Technology
• /
• v.21 no.1
• /
• pp.40-47
• /
• 1989

For the effective design of a beam forming structure of the negative-ion-based neutral beam injector, a computer program based on a particle simulation model is developed for the calculation of charged particle motions in the electrostatic fields. The motions of negative ions inside the acceleration tube of a multiple-aperture triode are computed at finite time steps. The electrostatic potentials are obtained from the Poisson's equation by the finite difference method. The successive overrelaxation method is used to solve the matrix equation. The particle and force weighting methods are used on a cloud-in-cell model. The optimum design of the beam forming structure has been studied by using this computer code for the various conditions of elctrodes. The effects of the acceleration-deceleration gap distance, the thickness of the deceleration electrode and the shape of the acceleration electrode on beam trajectories are exmined to find the minimum beam divergence. Some numerical illustrations are presented for the particle movements at finite time steps in the beam forming tubes. It is found in this particle simulation modelling that the shape of the acceleration electrode is the most significant factor of beam divergence.

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.761-772
• /
• 2021

Simulation results for the comparison of estimators of interest are usually reported in tables or plots. However, if the simulations are conducted under various conditions for many estimators, the comparison can be difficult to be made with tables or plots. Furthermore, for algorithms that take a long time to run, the number of iterations of the simulation is costly to to be increased. The analysis of simulation results using regression models allows us to compare the estimators more systematically and effectively. Since variances in performance measures may vary depending on the simulation conditions and estimators, the heteroscedasticity of the error term should be allowed in the regression model. And multiple comparisons should be made because multiple estimators should be compared simultaneously. We introduce background theories of heteroscedasticity and multiple comparisons in the context of analyzing simulation results. We also present a concrete example.

• International Area Studies Review
• /
• v.13 no.2
• /
• pp.117-144
• /
• 2009

This paper analyzes how Korea's trade intensity with major ASEAN countries changed from 2000 to 2005. For this purpose, we measured the trade intensity index, the trade complementarity index, and the special country bias index between Korea and ASEAN countries by the trade intensity index model developed by Yamazawa (1970). The OECD trade matrix was used as data. We found that Korea's trade intensity with Indonesia increased from 8.91 in 2000 to 10.88 in 2005 due to a considerable increase in Korea's special country bias with Indonesia from 9.58 in 2000 to 10.75 in 2005. Therefore Korea's special country bias with Indonesia should be enhanced further by increasing capital movements and reducing discriminatory tariffs and other import restrictions between Korea and Indonesia. It was also found that trade intensity between Korea and other ASEAN countries (i.e., Malaysia, Philippines, Singapore, and Thailand) shows a similar pattern of the above trade intensity between Korea and Indonesia except the trade complementarity.

• Journal of Korea Water Resources Association
• /
• v.36 no.6
• /
• pp.925-936
• /
• 2003

The objective of this study is to suggest new drawing methods of isochrones using GIS. For this purpose the Unit Hydrograph (UH) of studied watershed for instantaneous rainfall suggested by Clark have been determined by routing the time-area curve through a single linear reservoir. To evaluate constructing methods of isochrones three methods has been examined; Channel Profile and Clark-kict method; Laurenson method; Average velocity method of S.C.S. Also, these methods have been recomposed by GIS in this study. To apply first method, spatial modeling, the vector based on the stream network and Route_System measuring a distance between points has been used. A raster based on the flow direction grid from burn DEM and the slope grid from original DEM has been applied for the second method. The third method has been applied by a raster based on the landuse grid and a velocity function expressed by slope. Results by these three methods have been evaluated with observed hydrograph, and the method using average velocity method of S.C.S shows more reasonable results comparatively.

• Journal of Korean Society of Transportation
• /
• v.20 no.3
• /
• pp.17-30
• /
• 2002

Incident duration prediction is one of the most important steps of the overall incident management process. An accurate and reliable estimate of the incident duration can be the main difference between an effective incident management operation and an unacceptable one since, without the knowledge of such time durations, traffic impact can not be estimated or calculated. This research presents several multiple linear regression models for incident duration prediction using data consisting of 384 incident cases. The main source of various incident cases was the Traffic Incident Reports filled out by the Motorist Assistant Units of the Korea Highway Corporation. The models were proposed separately according to the time of day(daytime vs. nighttime) and the fatality/injury incurred (fatality/injury vs. property damage only). Two models using an integrated dataset, one with an intercept and the other without it, were also calibrated and proposed for the generality of model application. Some findings are as follows ; ?Variables such as vehicle turnover, load spills, the number of heavy vehicles involved and the number of blocked lanes were found to significantly affect incident duration times. ?Models, however, tend to overestimate the duration times when a dummy variable, load spill, is used. It was simply because several of load spill incidents had excessively long clearance times. The precision was improved when load spills were further categorized into "small spills" and "large spills" based on the size of vehicles involved. ?Variables such as the number of vehicles involved and the number of blocked lanes found not significant when a regression model was calibrated with an intercept. whereas excluding the intercept from the model structure signifies those variables in a statistical sense.