• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.91-94
• /
• 2001

In the frequency response analysis using a modal method, it is very important to determine the number of modes involved with the formulation of a frequency response function. Most engineers are inclined to determine mode truncation with their experience. But it is difficult for non-experts to decide the mode truncation reasonably in many problems of dynamic analyses. In this study, fuzzy theory is used to standardize the empirical determination of mode truncation so that not only the experts but also non-experts can decide a proper mode truncation easily. Fuzzy rule base is based on the simulation results using finite element method. Numerical simulations show that the developed mode truncation method is a very effective method to choose the number of the considered modes.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.127-129
• /
• 2006

The distributed control system is used in wide control fields. Factory automation, home network and building automation are good examples. Lonworks that Echelon company has been developing and providing since 1991 is one of popular distributed control systems. Lonwork system is support various communication media, especially it has a feature that supports communication through the power line. When Constructing Lonworks network in a construction field, the experts, who can treat Lonworks bring laptops that LNS and Lonmaker installed, install the network. However this way takes long time to construct the network and needs the experts. To resolve this problem, this paper suggests that a design of Lonworks network installation machine that is easy to use for everyone and portable. Non-experts can install Lonworks network by using this machine so they can reduce fare for installation of network and time to install.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.65-68
• /
• 2004

복잡한 문제 학습을 위해 여러 가지 형태의 모듈라 네트워크의 구조가 제시되어 왔다. 그 중 엑스퍼트 네트워크와 게이팅 네트워크로 구성된 Mixtures of Experts network은 복잡한 문제를 단순한 문제들로 분해하고, 각각의 엑스퍼트 네트워크가 분해된 단순한 문제를 학습하여 결과를 도출함으로써, 국소적 지역해의 위험을 방지하고 보다 정확한 학습을 가능하게 한다. 그러나 엑스퍼트 네트워크의 수렴은 게이팅 네트워크의 수렴에 많은 영향을 받게 되고, 모든 복잡한 데이터에 대한 엑스퍼트 네트워크의 기여도를 학습하는 게이팅 네트워크는 역전파 알고리즘에 의한 학습 방법으로는 수렴 속도가 떨어진다. 본 논문에서는 게이팅 네트워크를 칼만필터로 학습하여 복잡한 문제에 대한 강건성은 유지하고 보다 빠른 수렴이 가능한 방법을 제시하고자한다.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.05a
• /
• pp.774-779
• /
• 2001

If rotating machinery have a fault, we can detect it using vibration or noise signals. However some maintenance engineers who doesn't have expert knowledge, needs the help of vibration experts for diagnosing rotating machinery. But qualified experts are rare, therefore we have been developed the case based reasoning (CBR) system which is able to manipulate the past experiences of vibration diagnosis experts. In the CBR system, the maintenance engineers can retrieve too information from previous cases which are most similar to new problem and they can solve new problem using solutions from the previous cases. In this paper, we propose a new method which is the case retrieval of CBR system using Petri net and we also applied it to diagnosis for electric motors as a practical problem.

• Proceedings of the KSR Conference
• /
• 2005.05a
• /
• pp.1-13
• /
• 2005

Recently, The business environment is very rapidly changed and complicated. Therefore, the companies are confront with the biggest difficulty. To overcome this difficulty, the management should be able to accomplish the human resources management and the efficient business management. KR(Korea Railroad) has a close association with national life as it carries out public works based on its public nature as well as purses the corporate spirit. For that reason, KR has a great spin-off on national economy and exerts a tremendous impact on the improvement of productivity around the industries and the international competitiveness at aspect of efficiency resulting from business rationalization. Railroad system can be described as organic. Railroad Experts take a great role in this system. According the psychology and the Organization Behavior, the decision maker's personality and employee' work satisfaction have influence on performance. The purpose of this study is to examine the Railroad Experts' Personality and Work satisfaction which influence on the efficient business management.

• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.73-79
• /
• 2003

In managing organizational tacit knowledge, recent researches have shown that it is more applicable in many ways to provide expert search mechanisms in KMS to pinpoint experts in the organizations with searched expertise. In this paper, we propose an intelligent expert search framework to provide search capabilities for experts in similar or related fields according to the user's information needs. In enabling intelligent expert searches, Fuzzy Abstraction Hierarchy (FAH) framework has been adopted, through which finding experts with similar or related expertise is possible according to the subject field hierarchy defined in the system. To improve FAH, a text categorization approach called Vector Space Model is utilized. To test applicability and practicality of the proposed framework, the prototype system, "Knowledge Portal for Researchers in Science and Technology" sponsored by the Ministry of Science and Technology (MOST) of Korea, was developed.

• Proceedings of the Korea Contents Association Conference
• /
• 2014.06a
• /
• pp.123-124
• /
• 2014

• Proceedings of the Korea Technology Innovation Society Conference
• /
• 2003.11a
• /
• pp.275-286
• /
• 2003

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2000.11a
• /
• pp.8-22
• /
• 2000

• Proceedings of the Korean Magnestics Society Conference
• /
• 2016.11a
• /
• pp.129-129
• /
• 2016