• Journal of Electrical Engineering and Technology
• /
• v.2 no.4
• /
• pp.461-467
• /
• 2007

The paper describes a way to diagnose machine condition based on the expert system. In this paper, an expert system-decision tree is built and experimented to diagnose and to detect machine defects. The main objective of this study is to provide a simple way to monitor machine status by synthesizing the knowledge and experiences on the diagnostic case histories of the rotating machinery. A traditional decision tree has been constructed using vibration-based inputs. Some case studies are provided to illustrate the application and advantages of the decision tree system for machine fault diagnosis.

• Korean Journal of Construction Engineering and Management
• /
• v.4 no.1 s.13
• /
• pp.81-89
• /
• 2003

This research suggests the FD-AHP decision making model for Construction Projects which is composed of two main method to prevent a ranking invert situation ; First, to make the consensus of the experts consistent, we utilize Fuzzy-Delphi method to adjust the fuzzy rating of every expert to achive the consensus condition with the fuzzy linguistic presentation. Second, to handle vague linguistic presentation caused by expert's experiences and subjective judgement, we propose Fuzzy-AHP which is able to enhance precision of construction projects decision mating situation. Moreover, with the correlation analysis, we show that the validity of the FD-AHP model under a decision making task specially on where highly demanded expert's experiences and intuition.

• Korean Management Science Review
• /
• v.12 no.2
• /
• pp.147-164
• /
• 1995

There have been two dominant paradigms in understanding and modeling an expert's decision-making behavior: output analysis and process-tracing. While the two paradigms are complementary, they have not been used yet in a combined manner. This study extends the previous research work in the two paradigms to inductive modeling research by 1) analyzing individual experts' decision strategies, 2) comparing performance of four popular inductive modeling methods, and 3) matching their performance against the type of decision strategy employed by experts.

• Nuclear Engineering and Technology
• /
• v.35 no.4
• /
• pp.318-335
• /
• 2003

Expert judgment is frequently employed in the search for the solution to various engineering and decision-making problems where relevant data is not sufficient or where there is little consensus as to the correct models to apply. When expert judgments are required to solve the underlying problem, our main concern is how to formally derive their technical expertise and their personal degree of familiarity about the related questions. Formal methods for gathering judgments from experts and assessing the effects of the judgments on the results of the analysis have been developed in a variety of ways. The most important interest of such methods is to establish the robustness of an expert's knowledge upon which the elicitation of judgments is made and an effective trace of the elicitation process as possible as one can. While the resultant expert judgments can remain to a large extent substantiated with formal elicitation methods, their applicability however is often limited due to restriction of available resources (e.g., time, budget, and number of qualified experts, etc) as well as a scope of the analysis. For this reason, many engineering and decision-making problems have not always performed with a formal/structured pattern, but rather relied on a pertinent transition of the formal process to the simplified approach. The purpose of this paper is (a) to address some insights into the balanced use of formally structured and simplified approaches for the explicit use of expert judgments under resource constraints and (b) to discuss related decision-theoretic issues.

• Journal of Intelligence and Information Systems
• /
• v.12 no.4
• /
• pp.127-136
• /
• 2006

This paper describes the result of a case study for developing an expert system framework in order to support Korean Army tactical C4I system. Korean Army had developed an expert system, STAFS(Situation & Threat Assessment Fusion Expert System), for supporting field intelligence analysis activities which has been implemented through traditional manual process inside the division level combat briefing room. STAFS, however, has serious limitations for supporting combat commander's decision making processes because of its limited capabilities, since the system had been developed for supporting only intelligence analysis function rather than for integrated combat decision making processes inside the combat briefing room. Thus, this paper proposed an integrated expert system framework for supporting the commander's decision making by addressing various activities implemented in the briefing room.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.231-240
• /
• 2001

Conventional expert systems has been criticized due to its lack of capability to adapt to the changing decision-making environments. In literature, many methods have been proposed to make expert systems more environment-adaptive by incorporating fuzzy logic and neural networks. The objective of this paper is to propose a new approach to building a self-evolving expert system inference mechanism by integrating fuzzy neural network and fuzzy rule extraction technique. The main recipe of our proposed approach is to fuzzify the training data, train them by a fuzzy neural network, extract a set of fuzzy rules from the trained network, organize a knowledge base, and refine the fuzzy rules by applying a pruning algorithm when the decision-making environments are detected to be changed significantly. To prove the validity, we tested our proposed self-evolving expert systems inference mechanism by using the bankruptcy data, and compared its results with the conventional neural network. Non-parametric statistical analysis of the experimental results showed that our proposed approach is valid significantly.

• Journal of Korean Society for Quality Management
• /
• v.16 no.2
• /
• pp.34-47
• /
• 1988

Decision support system (DSS) has been expected to be a powerful tool for aiding the decision making processes in business organizations. But it's contribution has turned to be somewhat doubtful, In this paper, an intergrated systems design apporach is suggested, which integrates DSS and expert system (ES) for the enhancement of performance of DSS, after carefully reviewing both DSS and ES.

• Korean System Dynamics Review
• /
• v.16 no.2
• /
• pp.5-32
• /
• 2015

Last year, a disastrous accident happened on the sea. Car ferry Se-wol which was on its way from In-cheon to Je-ju sank in the middle of the western sea. 304 passengers were drowned at the sea in the accident. There were no passengers who were waiting on board ship rescued in the accident. This study is to review the pattern of decision making in the middle of saving a life, right after Se-wol was about to sink. The starting point of this study is decision making on the rescue by rescue corps with no expert knowledge at the initial stage. When it comes to saving victims, there was no expert on rescue on the sea. Failure in rescue at Se-wol disaster lets us find a vicious circle of positive feedback loop. Experts with no experience act like well-qualified persons. Unqualified persons(leaders) have no expertise. Those who pretend to be expert occupy the important post in the hierarchy. It means we could not accumulate expertise of know-how in rescue division. That's why a vicious circle of positive feedback is formed in areas of disasters. It is necessary to train experts in Government Organizations to weaken the vicious circle of positive feedback.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.65-93
• /
• 2005

Expert system implementation of human expert's diagnosis in art psychotherapy requires extensive knowledge on: (1) characteristics in a drawing; (2) psychological symptoms in a client; (3) relationships between the characteristics and the symptoms; (4) decision process; (5) knowledge elicitation and aquisition methods. Experts from many different fields provide such knowledge, ranging from art therapists who is on the spot, psychiatrists, psychologists, artists to knowledge engineers who know how to implement the decision system to a computer. The problems that make the implementation difficult are the expert's complex decision process and the ambiguity, the inconsistency and even the contradiction in the huge volume of the knowledge. Modeling the expert's decision process, we develope a framework of the system and then analyze and classify the knowledge. With the proposed classification, we present a suitable method of knowledge elicitation and aquisition. Then, we describe the subsets of knowledge in a unified structure using the ontology concept and Protege 2000 as a tool. Finally, we apply the system to a real case to show its usability and suitability.

• Journal of Digital Convergence
• /
• v.14 no.6
• /
• pp.143-150
• /
• 2016

This paper's aim is to suggest the Expert System for analyzing relative combat power in ground operations. Since relative combat power analysis in terms of comparing combat power of friendly forces with one of the enemy can determine how the commander and staffs operate their unit afterwards, it requires fast and rational decision-making process. However, it has relied on manual method so far though Tactical Information Communications Network(TICN) into which numbers of applications can be loaded has been developed over a decade. 3 methods for analyzing relative combat power were expressed as mathematic rules to be used knowledge in the expert system after reviewing previous studies, and it studied how intangible power as well as tangible were reflected on total combat power. The expert system that will be built using EXSYS Corvid tool is expected to lessen error rate, provide faster decision-making, and reflect both intangible combat power and tangible one by using an appropriate weights in analyzing relative combat power. Next research filed includes how to build expert systems related with military personnel and intelligence areas for fast and rational decision-making processes.