• 한국국방경영분석학회지
• /
• 제36권3호
• /
• pp.83-93
• /
• 2010

본 논문에서는 훈련용 워게임모델의 근접전투 피해평가를 위한 새로운 근접전투전문가시스템을 제안하였다. 군에서 사용하고 있는 워게임모델에서 피해평가 모의논리는 아주 중요한 모의가능이다. 현재, 육군의 군사단급 워게임모델인 창조21 모델에서는 근접전투 피해평가의 핵심기능이 창조21 모델에서 계산되지 않고, 공개소스와 내부논리를 알 수 없는 미군에서 제작한 근접전투전문가시스템(일명 COBRA)에서 별도로 계산되고, 이 결과가 네트워크를 통해 창조21 모델로 전송되어 근접전투에 대한 피해평가가 이루어진다. 본 논문에서는 COBRA를 대체할 수 있는 근접전투전문가시스템을 의사결정나무를 이용해서 제안하였다. 제안하는 시스템은 실험결과 COBRA와 유사한 성능을 보였고, 시스템의 계산량이 적었고 군사작전 상황에 적합하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1069-1072
• /
• 1996

In modern control engineering, the model following system is a typical method. The model following system's performance is due to algorithm of control law, accuracy of modeling to the plant, and dynamics of the reference model. But the determination of the reference model depends on knowledge of an expert. Using an expert system, the determination method of the reference model was proposed in this paper. So, the reference model can be selected by user who has no Knowledge of dynamics and parameters.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2627-2647
• /
• 2016

With the rapid growth of microblog, expert identification on microblog has been playing a crucial role in many applications. While most previous expert identification studies only assess global authoritativeness of a user, there is no way to differentiate the authoritativeness in a particular aspect of topics. In this paper, we propose a novel model, which jointly models text and following relationship in the same generative process. Furthermore, we integrate a similarity-based weight scheme into the model to address the popular bias problem, and use followee topic distribution as prior information to make user's topic distribution more precisely. Our empirical study on two large real-world datasets shows that our proposed model produces significantly higher quality results than the prior arts.

• 소성∙가공
• /
• 제7권1호
• /
• pp.12-22
• /
• 1998

An expert drawbead model is developed for the finite element analysis of stamping processes. The expert model calculates drawbead restraining forces and bead-exit thinnings with the forming condi-tions and drawbead size. The drawbead restraining forces and bead-exit thinnings of a circular draw-bead and stepped drawbead are computed by mathematical models and corrected by the multiple lin-ear regression method based on experimental measurements. The squared drawbead preventing the sheet from drawing-in inside die cavity is assumed to have a very huge drawbead restraining force and no pre-strain just after drawbead. The combined beads are considered as a combination of basic draw-beads such as circular a drawbead stepped drawbead and squared drawbead so that the drawbead restraining forces and bead-exit thinnigs are basically sum of those of basic drawbeads.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2005년도 춘계학술대회 논문집
• /
• pp.457-463
• /
• 2005

The use of the internet to facilitate commerce among companies promises vast benefits. Lots of e-marketplaces are building for several industries such as chemistry, airplane, and automobile industries. This study proposed new B2B EC business model for the shipping industry which concerns relatively massive fixed assets to be fully utilized. To be successful the proposed model gives participants to support useful information. To do this the expert system is constructed as the hybrid prediction system of neural network (NN) and memory based reasoning (MBR) with self-organizing map (SOM) and knowledge augmentaton technique using qualitative reasoning (QR). The expert system supports participants useful information coping with dynamic market environment. with this transportation companies are induced to participate in the proposed e-marketplace and helped for exchanges easily. Also participants would utilize their assets fully through B2B exchanges.

• 한국항해항만학회지
• /
• 제29권4호
• /
• pp.349-355
• /
• 2005

The use of the internet to facilitate commerce among companies promises vast benefits. Lots of e-marketplaces are building for several industries such as chemistry, airplane, and automobile industries. This study provides the new B2B EC business model for the shipping industry which concerns relatively massive fixed assets to be fully utilized. To be successful the proposed model gives participants useful information. To do this the expert system is constructed with the hybrid prediction system of neural network (NN) and memory based reasoning (MBR) with self-organizing map (SOM) and knowledge augmentation technique using qualitative reasoning (QR). The expert system supports participants useful information coping with dynamic market environment. with this shipping companies are induced to participate in the proposed e-marketplace and helped for exchanges easily. Also participants would utilize their assets fully through B2B exchanges.

• 경영과학
• /
• 제12권1호
• /
• pp.35-50
• /
• 1995

The material handling equipment selection, that is a key task in the material handling system design, is a complex, difficult task, and requires a massive technical knowledge and systematic analysis. It is also invaluable to justify the selected equipment model by the performance evaluation before its actual implementation. This paper presents an intelligent knowledge-based expert system called "IMESE" created by author, for the selection and evaluation of material handling equipment model suitable for movement and storage of materials in a manufacturing facility. The IMESE was constructed by using the tools of VP-Expert expert system shell, DBASEIII plus, FORTRAN 77, and SLAMII simulation language. The whole process of IMESE is executed under VP-Expert expert system environment.vironment.

• 대한전기학회논문지
• /
• 제41권4호
• /
• pp.331-338
• /
• 1992

The application of Connectionist expert system using neural network to fault diagnosis of power system is presented and compared with rule-based expert system. Also, the merits of Connectionist model using neural network is presented. In this paper, the neural network for fault diagnosis is hierarchically composed by 3 neural network classes. The whole power system is divided into subsystems, the neural networks (Class II) which take charge of each subsystem and the neural network (Class III) which connects subsystems are composed. Every section of power system is classified into one of the typical sections which can be applied with same diagnosis rules, as line-section, bus-section, transformer-section. For each typical section, only one neural network (Class I) is composed. As the proposed model has hierarchical structure, the great reduction of learning structure is achieved. With parallel distributed processing, we show the possibility of on-line fault diagnosis.

• 한국정밀공학회지
• /
• 제15권5호
• /
• pp.50-58
• /
• 1998

A proper model of expert system for the very thin sheet metal press die design has been suggested. Using the suggested model, an expert system of the very thin sheet metal press die has been developed. This study contains that the results from the developed system for three kinds of specimens have the adaptability in the actual site. In addition, the possibility for expansion of this system has been discussed. The developed system, which is based on the knowledge base, has been included in a lot of expert's technology in the practice field. C-language under the HP-UNIX system and CIS customer language of the EXCESS CAD/CAM system have been used as the overall CAD environment. Results from this system will provide effective aids to the designer in this field.

• 한국시뮬레이션학회논문지
• /
• 제9권3호
• /
• pp.27-41
• /
• 2000

As the application domains of rule-based systems become larger and more complicated, the integration of rule-based systems within the database systems has become the topic of many research works. This paper suggests a simulation modeling using expert system and database. The integration methods employed in this research are as follows. First, we defined new states and state transition functions to interrelate simulation model and expert system. Second, we designed and implemented FCL(Fact Class Library) as a interface of expert system and database. FCL has facilities of filtering data from database, and assigning a meaning to the filtered data. Also, FCL detects the violation of the integrity rules in database, as the result of inference is reflected. Some implementation problems are pointed out and the methods to solve these problems are discussed in this paper, We developed a simulation model of the grating production line and executed it to validate the functions of the proposed method.