• The Journal of the Korea Contents Association
• /
• v.10 no.1
• /
• pp.372-380
• /
• 2010

In this study, we consider a mid-and-long term technological forecasting method based on simulation technique. We, first, gather information about a point of appearance time of new technologies which will be developed in the future and influence relationship among those technologies by Delphi survey. And then we propose a simulation-based heuristic approach searching for the key technology among new technologies which will be developed to attain a normative objective using the Delphi data. We also provide the range of occurrence time for individual technology and define key technologies in this study in contrast that a expert's estimate to occurrence time is only one point in traditional Delphi survey. The information for key technologies which are detected by this procedure gives priorities of R&D planning and aids the R&D planner or project manager in resource allocation.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.251-258
• /
• 2000

인공신경망에 의해 부도예측을 하기 위해서는 여러 개의 재무비율을 입력변수 즉, 입력노드로 이용하는데, 이 가운데 적절한 입력노드를 선정하는 일은 예측력을 결정하는데 있어서 매우 중요하다. 본 연구에서는 새로운 입력노드 선정 휴리스틱을 제안하기 위하여 적절한 훈련이 끝난 인공신경망 모델에서 각 입력노드와 연결되는 가중치들의 합에 대한 절대값인 연결강도가 작은 경우 해당 노드는 출력값에 대한 설명력이 약할 것이다라는 연결강도판별 명제를 제시한다. 즉, 연결강도가 연결강도임계치보다 작은 입력노드는 제거 대상으로 분류할 수 있을 것이고, 이들 노드를 제외한 입력노드는 그렇지 않은 경우보다 더 나은 예측력을 보여 줄 수 있을 것이다. 연결강도판별 명제를 실증적으로 입증하기 위해 본 연구에서는 연결강도판별 선처리 과정에 대한 방법론을 제안하고 제안된 방법론에 의해 부도예측을 실시하여 아무런 선처리를 거치지 않은 모형과 비교하였고, 또 기존의 입력변수 선정방식 중에 하나인 의사결정트리 방식에 의한 입력변수 선정 모형과도 비교하여 더 나은 결과를 얻었다.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.801-811
• /
• 2016

Self-adaptive systems (SASs) can change their goals and behaviors to achieve its ultimate goal in a dynamic execution environment. Existing approaches have designed, at the design time, utility functions to evaluate and predict the goal satisfaction, and set policies that are crucial to achieve each goal. The systems can be adapted to various runtime environments by utilizing the pre-defined utility functions and policies. These approaches, however, may or may not guarantee the proper adaptability, because system designers cannot assume and predict all system environment perfectly at the design time. To cope with this problem, this paper proposes a new method of dynamic decision making, which takes the following steps: firstly we design a Dynamic Decision Network (DDN) with environmental data and goal model that reflect system contexts; secondly, the goal satisfaction is evaluated and predicted with the designed DDN and real-time environmental information. We furthermore propose a dynamic reflection method that changes the model by using newly generated data in real-time. The proposed method was actually applied to ROBOCODE, and verified its effectiveness by comparing to conventional static decision making.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.121-127
• /
• 2013

As the worldwide trade of agricultural products became liberalized with the establishment of WTO and FTA, relatively cheaper agricultural products have influenced the Korean domestic market substantially. Fortunately, foreign countries have soften their restrictions on Korean agricultural exports, providing Korean farmers with more opportunities to advance into the world market. This study aims to propose a multiple-criteria decision-making model for selecting an optimal tomato export farm, as the part of an effort to vitalize exports of domestic agricultural products amid the competitive agricultural market worldwide. For this purpose, we are suggesting a 2-step decision-making model which consists of a simple hierarchy decision model that preliminary selects tomato export farms and a detailed hierarchy decision model that chooses the final and optimal tomato export farm. We applied the analytic hierarchy process (AHP) to determine the relative importance of the used evaluation factors and to choose the tomato export farms with most potential. Eventually, the systematic and efficient decision-making model proposed in this paper can be applied to determine the optimal export farms for crops other than tomato, and thus it can encourage the competitiveness of Korean agricultural exports.

• Korean Journal of Construction Engineering and Management
• /
• v.15 no.3
• /
• pp.113-119
• /
• 2014

Recently, the demand on the practical application of life-cycle cost effectiveness for design and rehabilitation of structure is rapidly growing unprecedently in engineering practice. Accordingly, in the 21st century, it is almost obvious that life-cycle cost together with value engineering will become a new paradigm for all engineering decision problems in practice. However, in spite of impressive progress in the researches on the LCC, the most researches have only focused on the Deterministic or Probabilistic LCC analysis approach (Level-1 LCC Model) at design stage. Thus, the goal of this study is to develop a practical and realistic methodology for the Lifetime risk based Life-Cycle Cost (LCC)-effective optimum decision-making at design stage.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.322-322
• /
• 2019

최근 기후변화로 인한 물관리 어려움이 가중되고 있으며 대비책 마련이 시급한 실정이며, 기후변화를 고려한 댐 안전도 및 재개발에 대한 정량적인 평가방법이 요구되고 있다. 국내에서는 댐 노후화 및 기후변화 영향으로 인한 불확실한 강우패턴으로 인해 댐 붕괴사고가 증가하고 있으나 기후변화를 고려한 댐 설계기준이 반영되지 않고, 미래 불확실한 상황에서 다양한 기후변화를 고려한 수문분석결과에 제공되지 않는 실정이다. 또한, 불안전한 국내 댐들을 다양한 측면에서 진단할 수 있는 방법론이 제시되고 있지 않다. 따라서 본 연구에서는 다양한 기후변화 시나리오를 고려한 수문분석을 통해 불확실한 미래 댐 유입량을 예측하고 사전에 대비해야할 수 있는 연구를 수행하고, 선진화된 댐 평가를 위해 체계적인 절차를 통해 댐 평가방법을 제시할 것이다. 국내 댐의 종합적인(경제, 환경, 정책, 수문학적 안전) 진단을 위해서 댐 평가자료에 대한 빅데이터를 구축하고, 머신러닝을 이용한 국내 댐 안전도 평가 실시하였다. 본 연구성과는 댐 재개발계획 수립을 위한 의사결정 도구로 객관적이고 정량적인 의사결정 판단자료를 제공할 것이며, 댐 붕괴로 발생하는 경제, 사회, 인명 손실을 사전에 예방할 수 있을 것으로 기대된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.5-6
• /
• 2019

본 논문에서는 데이터 기반 정보 고도화를 통해, 사격전술지휘 의사결정체계의 Assisted Decision-Maker인 AI 부전포대장을 구현하는 방법론을 제시한다. 전포대장은 지휘결심의 말단에 있는 지휘관으로서, 최종적인 의사결정자이다. 이들의 지휘결심이 보다 견고하고 신속하게 이루어지도록 하는 것이 전쟁 승패에 매우 중요한 요소이다. 화력체계를 언급하는 경우 JMEM 탄약효과가 자주 언급되고 한국형 구축 사업이 아직 진행 중이기도 하지만, 완료되더라도 임의의 지형과 전술상황 각각에 대한 유용성까지를 입증하는 데에는 또 다른 기간과 노력이 요구된다. 본고에서는 AI 플랫폼 구축의 실제 사례가 전무한 상황에서 AI 부전포대장 구축을 위해 필요한 연구의 범위와 그 대상을 살펴보고, 지능형 사격지휘체계의 구축 방안을 제안한다.

• Journal of the Korea Society for Simulation
• /
• v.29 no.2
• /
• pp.63-72
• /
• 2020

Tank, which is a representative ground weapon system, is one of the most important weapon systems in each country. For the cost-effective acquisition of a tank based on scientific analysis, the operational concept and effectiveness should be studied based on engagement simulation technology. Besides physical capabilities including maneuver and communication, logical models including decision-making of a tank commander should be developed systematically. This paper describes a method to model a tank for engagement simulation based on Base System Model(BSM), which is the standard architecture of the weapon system model in AddSIM, an integrated engagement simulation software. In particular, a method is proposed to develop logical models by hierarchical and modular approach based on human decision-making model. The proposed method applies a mathematical formalism called DEVS(Discrete EVent system Specification) formalism. It is expected that the proposed method is widely used to study the operational concept and analyze the effectiveness of tanks in the Korean military in the future.

• The Journal of Society for e-Business Studies
• /
• v.19 no.1
• /
• pp.95-118
• /
• 2014

The information technologies industry is now experiencing a rebirth of strong stable growth. However, very few studies have examined performance implications of strategic alliance or merger and acquisition from a knowledge-based view. Furthermore, none of these studies have investigated resource complementarities and alliance or merger and acquisition motive as potential sources of firm performance. This paper extends upon current knowledge-based literature to discover and explore linkages between resource complementarities and firm performance of strategic alliances or merger acquisitions. This study finds that strategic alliance and merger and acquisition announcements have provided abnormal positive returns of production alliances and merger and acquisition. This study can be used as a stepping stone for selection of strategic alliance or merger and acquisition.

• Korean Journal of Construction Engineering and Management
• /
• v.17 no.2
• /
• pp.21-30
• /
• 2016

The current PF project is entirely relying on construction company's credibility. As such, it has increased a negative and bad recognition in domestic real estate economy. In addition, PF experts has a perception that a project's safety of future cash flow profitability is more important than the construction company's credibility. So many PF experts make an effort in order to set aside safe project structure of PF and analyse systematically the risks of the project. In common feasibility study of the PF Project, financial specialists and real estate specialists are forecasting and evaluating the suitability of the project through reviewing the development profit from the project of sales. However, cash flow analysis and evaluation from the perspective of mid-sized construction companies are still in the primary level. Therefore, this study has analysed the current feasibility study and go/no go decision making procedures. Then the authors have a new cash flow analysis method from the perspective of mid-sized construction companies, by improving the feasibility study and go/no go decision making procedures.