• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1138-1146
• /
• 1996

Fuzzy logic ignores some informations in the reasoning process. Neural networks are powerful tools for the pattern processing. However, to model human knowledges, besides pattern processing capability, the logical reasoning capability is equally important. Another new neural network called neural logic network is able to do the logical reasoning. Because the fuzzy logical reasoning, we construct fuzzy inference net-work based on the neural logic network, extending the existing rule-inferencing network. And the traditional propagation rule is modified. For the search strategies to find out the belief value of a conclusion in the fuzzy inference network, we conduct a simulation to evaluate the search cost for searching sequentially and searching by means of priorities.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.115-119
• /
• 1997

본 논문은 색료의 삼원색인 빨강, 노랑 및 파랑을 적절히 혼합하는 경우에 나타나는 색채를 추론하는 문제에 대하여, 퍼지이론을 적용하여 결과를 추론하는 문제를 다루고 있다. 즉, 인간이 색료의 혼합에 있어서 행하는 과정을 모사한 퍼지규칙을 바탕으로 삼원색의 색료가 일정 분량씩 혼합된 경우, 결과적으로 나타나는 색을 직접 실험을 통하지 않고 추론할 수 있는 시스템을 구축하고 있다. 또한, 구축된 시스템에 대하여 여러 가지 예를 통한 모의 실험을 수행하여 본 연구에서 구축된 색채혼합 시스템의 타당성을 검증하였다.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.281-286
• /
• 2007

This paper proposes an intelligent context awareness middleware(ICAM) for Ubiquitous Computing Environment. In this paper we have researched about the context awareness middleware. The ICAM model is based on ontology that efficiently manages analyses and learns about various context information and can provide intelligent services that satisfy the human requirements. Therefore, various intelligent services will improve user's life environment. We also describe the current implementation of the ICAM for service adaptation based on fuzzy inference that help applications to adapt their ubiquitous computing environments according to rapidly changing. For this, after defining the requirements specifications of ICAM, we have researched the inferred processes for the higher level of context awareness. The Fuzzy Theory has been used in process of inferences, and showed constructing the model through the service process. Also, the proposed fuzzy inferences has been applied to smart Jacky, and after inferring the fuzzy values according to the change of temperature, showed the adaptability of Smart Jacky according to the change of surroundings like temperature as showing the optimal value of status.

• The KIPS Transactions:PartB
• /
• v.17B no.2
• /
• pp.163-168
• /
• 2010

A linguistic case-based fuzzy reasoning (LCBFR) based on standardized parametric membership functions (SPMF) is proposed. It provides an efficient mechanism for a fuzzy reasoning within linear time complexity. Thus, it can be used to improve the speed of fuzzy reasoning. In the process of LCBFR, linguistic case indexing and retrieval based on SPMF is suggested. It can be processed relatively fast compared to the previous linguistic approximation methods. From the engineering viewpoint, it may be a valuable advantage.

• Journal of Intelligence and Information Systems
• /
• v.2 no.2
• /
• pp.1-15
• /
• 1996

전문가의 지식을 지식베이스화하여 의사결정지원시스템으로 사용하려는 노력이 증대하고 있다. 특히 투자의사결정과 같은 원인결과의 관계를 명확히 규정할 수 없는 복작한 영역에서 전문가의 지식베이스는 비전문가의 의사결정에 중요한 조언을 제공할 수 있다. 불확실한 지식을 지식베이스화하는 한 방법으로 퍼지프러덕션시스템이 널리 사용되고 있다. 주식시장과 같은 동태적인 시스템에서 어떤 정보의 중요성은 상황에 따라 변화하는데 이를 정태적인 프로덕션시스템의 규칙으로 지식베이스화하는 것은 불가능하다. 그러나 추론을 수행하는 과정에서 수행당시 각 정보의 중요도에 부응하는 가중치를 부여하여 평가함으로써 정태적인 지식베이스에 동태적인 실제시스템의 특성을 반영할 수 있다. 이는 가중치가 높은 정보에 해당하는 조건명제의 충족정도가 해당규칙의 전체평가결과에 더욱 중요하게 반영되게 하여 좀더 현실성 있는 추론 결과를 얻게 한다. AHP(Analytic Hierachy Process) 방법에 의하여 얻어진 정보의 상대적 중요도에 따른 가중치 (w)를 해당 정보와 조건명제의 합치정도(Degree of Match : DM)에 (DM)w 의 형식으로 적용함으로써 퍼지프러덕션시스템에서 정보의 중요도를 반영하여 프러덕션규칙을 평가하는 방법을 제시한다.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.5 no.4
• /
• pp.75-81
• /
• 2001

Fuzzy supervisory control method is studied for the active control of earthquake excited structures. The proposed algorithm supervises and tunes previously designed control gains by evaluating the state of a structure through the fuzzy inference mechanism, which uses the information of relative displacements and velocities. Example designs and numerical simulations of earthquake exited three degrees of freedom structures are performed to prove the validity of the proposed control algorithm. Comparative results with conventional LQR method show that the proposed method is effective for the vibration suppression of earthquake excited structures.

• International Journal of Highway Engineering
• /
• v.13 no.1
• /
• pp.69-77
• /
• 2011

This study is to suggest a methodology to overcome the uncertainty and lack of reliability of data. The fuzzy reasoning model and the neural network model were developed in order to overcome the potential lack of reliability which may occur during the process of data collection. According to the result of comparison with the Poisson regression model, the suggested models showed better performance in the accuracy of the accident frequency prediction. It means that the more accurate accident frequency prediction model can be developed by the process of the uncertainty of raw data and the adjustment of errors in data by learning. Among the suggested models, the performance of the neural network model was better than that of the fuzzy reasoning model. The suggested models can evaluate the safety of signalized intersections in operation and/or planning, and ultimately contribute the reduction of accidents.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.742-746
• /
• 2006

Evaluation of learning ability of students is classified a step of diagnostic, formative and summative evaluation. This step-by-step evaluation is the standard of synthesis judgement, from a student's prior learning of preparation state to devotion of learning process and even learning result. In this paper, we propose the method of synthesis learning evaluation which is considered evaluation of each step in using fuzzy inference. In order to get objective evaluation of learning ability, we applied to the weights by evaluation steps. And we reflected defuzzification values of final evaluation membership function interval obtained by fuzzy inference about diagnostic, formative and summative evaluation. As a result, it processes definite inference ensures objectivity and shows validity of the synthesis evaluation method.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.543-563
• /
• 1996

In this paper, we propose a Timed Fuzzy Petri Net(TFPN) model as a new model of real-time fuzzy control. The TFPN model, which is useful for fuzzy inference and fuzzy control is an integrated model of Timed PetriNet and Fuzzy Petri Net. Additionally, a Timed Fuzzy Control Language is defined as a textual specification model of fuzzy control rues, and proposed a TFPN modeling method. The TFPN model is a Petri Net formalism of fuzzy control systems. Execution rule is consisted of marking(i.e,fuzzyfication) and firing(i.e,inference and defuzzyfication) procedures. A simple case work by using TFPN model shows us computing time of inference and defuzzyfication is low and uncertainty and visibility of fuzzy control rule are modeled effectively.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.5
• /
• pp.1-12
• /
• 2000

In this paper we propose a design method of the adaptive fuzzy controller for autonomous navigation of mobile robots based on the fuzzy theory. We present two improvements. First, unnecessary rules in the fuzzy inference process make data processing time increase. We reduce this data processing time by generating suitable fuzzy inference rules and membership functions according to the current state of a mobile robot. It is implemented with the clustering method using input and output data pairs, and then it is possible for a mobile robot to navigate in shorter processing time with less fuzzy inference rules. Second, existing algorithms used fixed membership functions of input and output variables, hence converged slowly. We improve convergence time via scaling membership functions generated by the clustering method. To evaluate and compare the performance of the proposed method with the existing fuzzy navigation controller, computer simulations and navigation experiments of a mobile robot are Presented.