• Journal of Korea Port Economic Association
• /
• v.28 no.2
• /
• pp.179-194
• /
• 2012

In this study, we compared the efficiency of container terminals using DEA. To do this, we designed an AHP/DEA hybrid model using AHP and DEA, and evaluated the efficiency by comparing the container terminal operation company in Gwangyang(KEC, KIT, GICT) and Busan(HBCT, DPCT, KBCT, UPT, Gamman, PNC, PNIT, HJNC, HPNT). The proposed model can control the number of selected promising container terminal by applying DEA-AR model. This model can also improve the credibility of analysis by using objective weights through the AHP application to efficiency evaluation data and normalizing the evaluation data to apply AHP and DEA. The model assumes inputs to be container crane, transfer crane, yard tractor, and reach stacker and output as container traffic. The result shows that DPCT was an efficient DMU.

• Journal of Korea Water Resources Association
• /
• v.34 no.4
• /
• pp.303-316
• /
• 2001

In this study, Radial Basis Function(RBF) Neural Networks Model, a kind of Hybrid Neural Networks was applied to hydrological forecasting in a small watershed. RBF Neural Networks Model has four kinds of parameters in it and consists of unsupervised and supervised training patterns. And Gaussian Kernel Function(GKF) was used among many kinds of Radial Basis Functions(RBFs). K-Means clustering algorithm was applied to optimize centers and widths which ate the parameters of GKF. The parameters of RBF Neural Networks Model such as centers, widths weights and biases were determined by the training procedures of RBF Neural Networks Model. And, with these parameters the validation procedures of RBF Neural Networks Model were carried out. RBF Neural Networks Model was applied to Wi-Stream basin which is one of the IHP Representative basins in South Korea. 10 rainfall events were selected for training and validation of RBF Neural Networks Model. The results of RBF Neural Networks Model were compared with those of Elman Neural Networks(ENN) Model. ENN Model is composed of One Step Secant BackPropagation(OSSBP) and Resilient BackPropagation(RBP) algorithms. RBF Neural Networks shows better results than ENN Model. RBF Neural Networks Model spent less time for the training of model and can be easily used by the hydrologists with little background knowledge of RBF Neural Networks Model.

• Water for future
• /
• v.26 no.3
• /
• pp.137-148
• /
• 1993

A hybrid finite difference method for the longitudinal dispersion equation was developed. The method is based on combining the Holly-Preissmann scheme with the fifth-degree Hermite interpolating polynomial and the generalized Crank-Nicholson scheme. Longitudinal dispersion of an instantaneously-loaded pollutant source was simulated by the model and other characteristics-based numerical methods. Computational results were compared with the exact solution. The present method was free from wiggles regardless of the Courant number, and exactly reproduced the location of the peak concentration. Overall accuracy of the computation increased for smaller value of the weighting factor, $\theta$ of the model. Larger values of $\theta$ overestimated the peak concentration. Smaller Courant number gave better accuracy, in general, but the sensitivity was very low, especially when the value of $\theta$ was small. From comparisons with the hybrid method using the third-degree interpolating polynomial and with split-operator methods, the present method showed the best performance in reproducing the exact solution as the advection becomes more dominant.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.9 no.2 s.42
• /
• pp.7-15
• /
• 2005

Numerical analysis model is proposed to predict the dynamic behavior of a single-degree-of-freedom structure that is equipped with hybrid base isolation system. Hybrid base isolation system is composed of friction pendulum systems (FPS) and a magnetorheological (MR) damper. A neuro-fuzzy model is used to represent dynamic behavior of the MR damper. Fuzzy model of the MR damper is trained by ANFIS (Adaptive Neuro-Fuzzy Inference System) using various displacement, velocity, and voltage combinations that are obtained from a series of performance tests. Modelling of the FPS is carried out with a nonlinear analytical equation that is derived in this study and neuro-fuzzy training. Fuzzy logic controller is employed to control the command voltage that is sent to MR damper. The dynamic responses of experimental structure subjected to various earthquake excitations are compared with numerically simulated results using neuro-fuzzy modeling method. Numerical simulation using neuro-fuzzy models of the MR damper and FPS predict response of the hybrid base isolation system very well.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2007.12a
• /
• pp.259-260
• /
• 2007

The forecast of a container traffic has been very important for port plan and development Generally, statistic methods, such as regression analysis, ARIMA, have been much used for traffic forecasting. Recent research activities in forecasting with artificial neural networks(ANNs) suggest tint ANNs am be a promising alternative to the traditional linear methods. In this paper, a hybrid methodology that combines both ARIMA and ANN models is proposed to take advantage of the unique strength of ARIMA and ANN models in linear and nonlinear modeling. The results with port traffic data indicate tint effectiveness can differ according to the ch1racteristics of ports.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.3
• /
• pp.467-476
• /
• 2011

We developed the hybrid model coupled with predictive model and business rule model for administration of injury by utilizing medical data of the National Health Insurance in Korea. We performed decision tree analysis using data mining methodology and used SAS Enterprise Miner 4.1. We also investigated under several business rule for benefits (expense paid by insurer) and claims of injury in National Health Insurance Corporation. We can see that the proposed hybrid model provides a quite efficient plausible results.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.6 no.1
• /
• pp.35-41
• /
• 1986

A hybrid modelling technique of a soil-structure system on viscoelastic soil medium is studied in this paper. The hybrid model consists of a near-field and a far-field with their common interface passing through the soil region at some distance from the base of the structure. It makes use of frequency-dependent impedances so as to represent the semi-infinite far-field. The far-field impedances are formulate including the radiation damping characteristics as well as the viscoelastic properties of the soil medium. The verification of the method has been carried out using a rigid circular plate on a viscoelastic half-space. The impedances obtained by the method are compared with the theoretical values. Example analyses have been performed for a tall chimney and the results have been compared with those obtained by other methods which are frequently used.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.329-345
• /
• 2021

Recommender systems use data from customers to suggest personalized products. The recommender systems can be categorized into three cases; collaborative filtering, contents-based filtering, and hybrid recommender system that combines the first two filtering methods. In this work, we introduce and compare deep learning-based recommender system using autoencoder. Autoencoder is an unsupervised deep learning that can effective solve the problem of sparsity in the data matrix. Five versions of autoencoder-based deep learning models are compared via three real data sets. The first three methods are collaborative filtering and the others are hybrid methods. The data sets are composed of customers' ratings having integer values from one to five. The three data sets are sparse data matrix with many zeroes due to non-responses.

• The Journal of the Korea Contents Association
• /
• v.16 no.2
• /
• pp.513-524
• /
• 2016

The purpose of this study was to open two classes with the name of $21^{st}$ Leadership, run with two different hybrid teaching styles which are hybrid LZ type and hybrid lz type, and compare them with each other in order to analyze their effectiveness of hybrid model of the subject. The subjects of this study were 64 students who took these classes, and statistical analysis were analyzed through SPSS 21.0 program. As a result of the analysis, first, there were significant development in terms of the knowledge of leadership in both LZ and lz model. but the result of final exam in the group lz was shown only significant development. Second, in the case of unconditional self-acceptance there was significant development only in the group lz. Third, the development of leadership skills was shown only in the group lz. Implications of these results were concluded that the lz is more suitable for the subject of $21^{st}$ Leadership because this model can provide much more opportunities to develope interpersonal relationship skill than LZ model. In addition, suggestions for future research were discussed.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1037-1051
• /
• 2021

Biochemical oxygen demand (BOD) concentration, one of important water quality indicators, is treated as the measuring item for the ecological chapter in lakes and rivers. This investigation employed novel two-stage hybrid paradigm (i.e., wavelet-based gated recurrent unit, wavelet-based generalized regression neural networks, and wavelet-based random forests) to predict BOD concentration in the Dosan and Hwangji stations, South Korea. These models were assessed with the corresponding independent models (i.e., gated recurrent unit, generalized regression neural networks, and random forests). Diverse water quality and quantity indicators were implemented for developing independent and two-stage hybrid models based on several input combinations (i.e., Divisions 1-5). The addressed models were evaluated using three statistical indices including the root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), and correlation coefficient (CC). It can be found from results that the two-stage hybrid models cannot always enhance the predictive precision of independent models confidently. Results showed that the DWT-RF5 (RMSE = 0.108 mg/L) model provided more accurate prediction of BOD concentration compared to other optimal models in Dosan station, and the DWT-GRNN4 (RMSE = 0.132 mg/L) model was the best for predicting BOD concentration in Hwangji station, South Korea.