• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2001.11a
• /
• pp.85-87
• /
• 2001

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1996.06a
• /
• pp.331-334
• /
• 1996

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.183-189
• /
• 2024

In order to effectively predict time series data, this study proposed a hybrid prediction model that decomposes the data into trend, seasonality, and residual components using Seasonal-Trend Decomposition on Loess, and then applies ARIMA to the trend component, Fourier Series Regression to the seasonality component, and XGBoost to the remaining components. In addition, performance comparison experiments including ARIMA, XGBoost, LSTM, EMD-ARIMA, and CEEMDAN-LSTM models were conducted to evaluate the prediction performance of each model. The experimental results show that the proposed hybrid model outperforms the existing single models with the best performance indicator values in MAPE(3.8%), MAAPE(3.5%), and RMSE(0.35) metrics.

• Journal of the Korean Society for Railway
• /
• v.15 no.4
• /
• pp.413-421
• /
• 2012

The purpose of this study is to evaluate the structural dynamic behavior under hybrid control system. The hybrid test is to consider the interaction between the numerical and physical models. In this paper, single degree of freedom hybrid test was performed with one-bay, two-story steel frame structure. One column at the first floor was selected as a physical substructure and one actuator was used for applying the displacement load in horizontal direction. El Centro as earthquake waves was inputted and OpenSees was employed as the numerical analysis program for the hybrid real-time simulation. As a result, the total time of the hybrid test was about 9.6% of actual measured seismic period. The experimental results agreed well with the numerical one in terms of the maximum displacement. In nonlinear analysis, however, material nonlinearity made a difference of residual strain. Therefore, this hybrid dynamic test can be used to predict the structural dynamic performance more effectively than shaking table test, because of the spatial and economic limitations.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.14 no.6
• /
• pp.33-43
• /
• 2010

This paper deals with the hybrid structural test technique which has been introduced and studied currently in Korea. In this study, a Mini-MOST system which was developed as a part of NEES research was modified and improved to reduce the total simulation time to half of the original system. Using the proposed system together with the 2 dimensional small steel frame specimen, the validity and efficiency of the hybrid test technique is investigated. Even though the hybrid test has been developed as an alternative to the shaking table test and has been studied and applied for a long time in several countries, no attempt has been made to compare it directly with the shaking table test. Therefore, in this study, the hybrid test results are compared with those of the shaking table test as well as with a numerical simulation for the verification of hybrid test. From the comparison and analysis of the test results, it is concluded that the hybrid test can simulate the actual seismic behavior of structural systems very accurately and it can be a good alternative to the shaking table test.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.27-43
• /
• 2024

The market share of online platform services in the used car market continues to expand. And The used car online platform service provides service users with specifications of vehicles, accident history, inspection details, detailed options, and prices of used cars. SUV vehicle type's share in the domestic automobile market will be more than 50% in 2023, Sales of Hybrid vehicle type are doubled compared to last year. And these vehicle types are also gaining popularity in the used car market. Prior research has proposed a used car price prediction model by executing a Machine Learning model for all vehicles or vehicles by brand. On the other hand, the popularity of SUV and Hybrid vehicles in the domestic market continues to rise, but It was difficult to find a study that proposed a used car price prediction model for these vehicle type. This study selects a used car price prediction model by vehicle type using vehicle specifications and options for Sedans, SUV, and Hybrid vehicles produced by domestic brands. Accordingly, after selecting feature through the Lasso regression model, which is a feature selection, the ensemble model was sequentially executed with the same sampling, and the best model by vehicle type was selected. As a result, the best model for all models was selected as the CBR model, and the contribution and direction of the features were confirmed by visualizing Tree SHAP Value for the best model for each model. The implications of this study are expected to propose a used car price prediction model by vehicle type to sales officials using online platform services, confirm the attribution and direction of features, and help solve problems caused by asymmetry fo information between them.

• Management & Information Systems Review
• /
• v.28 no.4
• /
• pp.27-44
• /
• 2009

Economic value of a certain technology is of great interest and importance in a wide variety of investment circumstances. These vary from companies considering investing in R&D projects, to venture capitalists funding start-up companies. However, such valuation is extremely difficult in any case, and the cost of failure can be very high. Many techniques have been proposed to assist managers facing this issue, from traditional discounted cash flow analysis to more recent methods based on real options. In the meantime, the discounted cash flow method has limitations in applying the valuation of technology. At the same time, there have been various solutions to overcome theoretical problems of the method. Real options have been thought as a solution. However, there are another problems in using them in real world. This paper reviews the previous studies on the valuation of technology in several aspects, discusses the practicability of the various methods available, and explore the application of a hybrid model, which aims to make these rather aore the ideas more accessible to practicing managers.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.17 no.6
• /
• pp.1-10
• /
• 2013

In this paper, the main cause on excitation of the combustion instability which may occur in the hybrid rocket motor with a diaphragm was studied. Hybrid rocket motor propulsion tests considering various experimental conditions such as with a diaphragm or not, a diameter of diaphragm, oxidizer mass flow rate, fuel length, etc were performed, and the combustion visualization for the inside of a hybrid rocket motor with a diaphragm was performed. With these experimental results, it was confirmed that the main cause of a large excitation was the hole-tone, and it was shown that the hole-tone model can be predicted experimental primary pressure oscillation frequency quite well.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.823-833
• /
• 2015

Hybrid system is a dynamic system that is composed of both a continuous and discrete system, suitable for automobile, avionic and defense systems. Various modeling languages and their supporting tools have been proposed and used in the hybrid system. The languages and tools have specific characteristics for their purpose. Electronics and Telecommunications Research Institute (ETRI) proposed a hybrid system modeling language, ECML (ETRI CPS Modeling Language). ECML extends DEV&DESS (Differential Event and Differential Equation Specified System) formalism with consideration of CPS (Cyber-Physical System), which supports modeling and simulation. In this paper, we introduce ECML and suggest a formal definition. The case study specifies a simple vehicle model using the suggested formal definition.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.753-758
• /
• 2006

We present the development of the digital fuzzy controller for maximum power regulation. A hybrid system that comprises wind and photovoltaic generation subsystems, and battery bank is developed in this paper. We use Takaki-Sugeno (T-S) fuzzy model to deal with the power regulation problem, since each power generator has complex nonlinear terms. The problem for regulation control can be simplified into a stabilization one. Also, in order to utilize the advanced digital device, we perform the intelligent digital redesign method. Finally, the performance of the proposed controller is extensively assessed through computer simulation.