• 한국경영과학회지
• /
• 제23권3호
• /
• pp.185-207
• /
• 1998

This research investigates computer generated hybrid second-order model of two numerically based approaches to risk classification : discriminant analysis and neural networks. The hybrid second-order models are derived by rule induction using the ID3 and tested in the several different kinds of data. This new hybrid approach is designed to combine the high prediction accuracy and robustness of DA or NN with perspicuity of ID3. The hybrid model also eliminates the problem of contradictory inputs of ID3. After doing empirical test for the validity of hybrid model using small and medium companies' bankrupt data, hybrid model shows high perspicuity, high prediction accuracy for bankrupt, and simplicity for rules. The hybrid model also shows high performance regardless the type of data such as numeric data, non-numeric data, and combined data.

• 한국경영과학회지
• /
• 제24권4호
• /
• pp.1-12
• /
• 1999

This paper presents a DEA-AHP hybrid model to evaluate and select R&D projects. AHP collects and processes information on the weights of evaluation criteria. The processed information is used as an input for DEA/AR model. Only desirable number of projects are selected by the hybrid model. The model is examined by an example generated from a real data set.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.203-206
• /
• 1996

Prediction of firm bankruptcy have been extensively studied in accounting, as all stockholders in a firm have a vested interest in monitoring its financial performance. The objective of this paper is to develop the hybrid models for bankruptcy prediction. The proposed hybrid models are two phase. Phase one are (a) DA-assisted neural network, (b) Logit-assisted neural network, and (c) Genetic-assisted neural network. And, phase two are (a) DA-assisted Case based reasoning, and (b) Genetic-assisted Case based reasoning. In the variables selection, We are focusing on three alternative methods - linear discriminant analysis, logit analysis and genetic algorithms - that can be used empirically select predictors for hybrid model in bankruptcy prediction. Empirical results using Korean medium-sized firms data show that hybrid models are very promising neural network models and case based reasoning for bankruptcy prediction in terms of predictive accuracy and adaptability.

• 한국수소및신에너지학회논문집
• /
• 제30권2호
• /
• pp.155-162
• /
• 2019

The energy management technology for an independent fuel cell-battery hybrid system is developed for a household usage. To develop an efficient energy management technology, a simulation model is first developed. After the model is verified with experimental results, three energy management schemes are developed. Three control techniques are a fuzzy logic control (FLC), a state machine control (SMC), and a hybrid method of FLC and SMC. As the fuel cell-battery hybrid system is used for a house, battery state of charge (SOC) regulation is the most important factor for an energy management because SOC should be kept constant every day for continuous usage. Three management schemes are compared to see SOC, power split, and fuel cell power variations effects. Experimental results are also presented and the most favorable strategy is the state machine combined fuzzy control method.

• 경영과학
• /
• 제28권3호
• /
• pp.1-13
• /
• 2011

Hub-and-spoke transportation network is a powerful and useful network structure that takes full advantage of economies of scale on routes between hubs. In recent studies, the network structure is extended to hybrid hub-andspoke that allows direct transportation between spokes. In this study, we considered more extended network structure which is called hybrid multiple hub-and-spoke that has multiple hubs and allows direct transportation between spokes. We developed a mathematical optimization model for automotive service parts transportation planning under hybrid multiple hub-and-spoke network structure. The model suggests a long-term transportation route planning and a short-term vehicle assignment planning. The model is verified by simulation and validated in real world application to Hyundai Mobis automotive service parts transportation planning. From the simulation result, the model reduced the transportation cost about 24.7%, the total distance about 6.8% and the CO2 emissions about 8.8%. In real world application for 6 months from July to December 2010, the model reduced the transportation cost about 9.1% by changing the long-term transportation route without daily vehicle assignment planning.

• 경영과학
• /
• 제30권1호
• /
• pp.25-41
• /
• 2013

This paper presents a supply chain framework with the ODM (Original Design Manufacturing)-OEM (Original Equipment Manufacturing) hybrid production of textile industry in FTA (Free Trade Agreements) environments between Korea and other countries. The proposed supply chain framework with ODM-OEM hybrid production is a unique supply chain that has both domestic production with non-tariff advantages in FTA environment and oversea production with low labor costs. To investigate the validity of the proposed supply chain, we first construct its strategic profit model and supply chain planning and then show that each member of supply chain network-yarn manufacturer, fabric manufacturer, and apparel manufacturer-can maximize their own profits without conflicts among the members. The efficiency of the ODM-OEM hybrid production system is analytically verified in comparison with the general OEM and ODM production model using profit models. Comprehensive numerical examples are provided to illustrate the advantages of the proposed system.

• 한국컴퓨터정보학회논문지
• /
• 제4권1호
• /
• pp.54-61
• /
• 1999

실제 생산환경에서는 MRP JIT 그리고 OPT 생산시스템을 상호 보완적으로 사용할 필요가 있으므로 3가지 생산시스템의 역할을 분석하고, 이를 기초로 동적생산체계에 적합한 Hybrid생산시스템을 설계하는 것은 충분한 의의를 갖는다고 할 수 있다. 그러므로 본 연구에서는 개별시스템이 가지는 제조방식의 유용성과 한계성을 분석하고 생산시스템을 전략적 차원. 전술적 차원 그리고 운영적 차원으로 구분하여 Hybrid화를 시도하였다. 그리고 Hybrid시스템의 유용성을 증명하기 위하여 MRP, JIT 그리고 OPT시스템의 개념이 포함된 Hybrid시스템에 대한 Simulation을 실시하였으며, 그 결과 독립적인 개별시스템 보다 Hybrid시스템이 더욱 효과적임을 입증하였다.

• 한국경영과학회지
• /
• 제30권4호
• /
• pp.27-43
• /
• 2005

This paper presents a new hybrid data mining technique using error pattern modeling to improve classification accuracy when the data type of a target variable is binary. The proposed method increases prediction accuracy by combining two different supervised learning methods. That is, the algorithm extracts a subset of training cases that are predicted inconsistently by both methods, and models error patterns from the cases. Based on the error pattern model, the Predictions of two different methods are merged to generate final prediction. The proposed method has been tested using practical 10 data sets. The analysis results show that the performance of proposed method is superior to the existing methods such as artificial neural networks and decision tree induction.

• 보건행정학회지
• /
• 제20권4호
• /
• pp.74-96
• /
• 2010

The purpose of this empirical study is to evaluate efficiency of the regional public hospitals, using DEA(Data Envelopment Analysis). to do this, we design a DEA-AR/AHP Hybrid model to evaluate efficiency of 34 Regional Public Hospitals. the proposed model is developed by adding Acceptance Region(AR). using analytical hierarchy process(AHP). this model is compared with those of typical DEA models. Financial data used in this study were obtained from Database of the Korea Association Regional Public Hospital and analyzed using DEA model. As a result of analysis, This study found that the DEA-AR/AHP Hybrid model was superior to those typical DEA models in determining the priority among efficient hospitals. the result of this study can provide helpful information to evaluate the efficiency of public hospitals for efficient operational management, to develop more precise measurement for the priority of the efficient hospitals.

• 드라이브 ㆍ 컨트롤
• /
• 제16권2호
• /
• pp.80-90
• /
• 2019

Fuel cell hybrid electric vehicle is an attractive solution to reduce pollutants, such as noise and carbon dioxide emission. This study presents an approach for energy management and control algorithm based on energetic macroscopic representation for a fuel cell hybrid electric vehicle that is powered by proton exchange membrane fuel cell, battery and supercapacitor. First, the detailed model of the fuel cell hybrid electric vehicle, including fuel cell, battery, supercapacitor, DC-DC converters and powertrain system, are built on the energetic macroscopic representation. Next, the power management strategy was applied to manage the energy among the three power sources. Moreover, the control scheme that was based on back-stepping sliding mode control and inversed-model control techniques were deduced. Simulation tests that used a worldwide harmonized light vehicle test procedure standard driving cycle showed the effectiveness of the proposed control method.