• 정보과학회 논문지
• /
• 제43권5호
• /
• pp.553-561
• /
• 2016

웹으로부터 얻어진 데이터를 통해 자동적으로 온톨로지를 확장하는 많은 기계학습 방법들이 존재한다. 또한 대용량 온톨로지 추론에 대한 관심이 증가하고 있다. 하지만 웹으로부터 얻어진 다양한 데이터의 신뢰성 문제를 고려하지 않으면, 불확실성을 내포하는 추론결과를 초래하는 문제점이 있다. 현재 대용량 온톨로지의 신뢰도를 반영하는 추론에 대한 연구가 부족하기 때문에 신뢰 값 기반의 대용량 온톨로지 추론 방법론이 요구되고 있다. 본 논문에서는 인메모리 기반의 분산 클러스터 프레임워크인 스파크 환경에서 신뢰 값 기반의 대용량 OWL Horst 추론 방법에 대해서 설명한다. 기존의 연구들의 문제점인 중복 추론된 데이터의 신뢰 값을 통합하는 방법을 제안한다. 또한 추론의 성능을 저하시키는 문제를 해결할 수 있는 분산 병렬 추론 알고리즘을 설명한다. 본 논문에서 제안하는 신뢰 값 기반의 추론 방법의 성능을 평가하기 위해 LUBM3000을 대상으로 실험을 진행했고, 기존의 추론엔진인 WebPIE에 비해 약 2배 이상의 성능을 얻었다.

• 정보과학회 논문지
• /
• 제43권9호
• /
• pp.963-973
• /
• 2016

대용량 미디어 온톨로지를 이용하여 의미 있는 지능형 서비스를 제공하기 위해 기존의 Axiom 추론뿐만 아니라 다양한 추론을 활용하는 지식 확장이 요구되고 있다. 특히 시공간 정보는 인공지능 응용분야에서 중요하게 활용될 수 있고, 시공간 정보의 표현과 추론에 대한 중요도는 지속적으로 증가하고 있다. 따라서 본 논문에서는 공간 정보를 추론에 활용하기 위해서 공공 주소체계에 대한 LOD를 대용량 미디어 온톨로지에 추가하고, 이러한 대용량 데이터 처리를 위해 인메모리 기반의 분산 처리 프레임워크를 활용하는 공간 추론을 포함하는 RDFS 추론 시스템을 제안한다. 또한 추론을 통해 확장된 데이터를 포함하는 대용량 온톨로지 데이터를 대상으로 하는 분산 병렬 시공간 SPARQL 질의 처리 방법에 대해서 설명한다. 제안하는 시스템의 성능을 측정하기 온톨로지 추론과 질의 처리 벤치 마킹을 위한 LUBM과 BSBM 데이터셋을 대상으로 실험을 진행했다.

• Journal of Ship and Ocean Technology
• /
• 제5권3호
• /
• pp.27-35
• /
• 2001

In this research, hybrid method with case-based reasoning and rule-based reasoning is applied. Using case-based reasoning, design experts'experience and know-how are effectively represented in order to obtain a proper configuration of midship section in the initial ship design stage. Since there is not sufficient domain knowledge available to us, traditional case-adaptation algorithms cannot be applied to our problem, i.e., creating the configuration of midship section. Thus, new case-adaptation algorithms not requiring any domain knowledge are developed antral applied to our problem. Using the knowledge representation of DnV rules, rule-based reasoning can perform deductive inference in order to obtain the scantling of midship section efficiently. The results from the case-based reasoning and the rule-based reasoning are examined by comparing the results with various conventional methods. And the reasonability of our results is verified by comparing the results wish actual values from parent ship.

• 한국경영과학회지
• /
• 제28권3호
• /
• pp.135-148
• /
• 2003

In this paper we introduce the Internet-based purchase support systems using data mining and case-based reasoning (CBR). Internet Business activity that involves the end user is undergoing a significant revolution. The ability to track users browsing behavior has brought the vendor and end customer's closer than ever before. It is now possible for a vendor to personalize his product message for individual customers at massive scale. Most of former researchers, in this research arena, used data mining techniques to pursue the customer's future behavior and to improve the frequency of repurchase. The area of data mining can be defined as efficiently discovering association rules from large collections of data. However, the basic association rule-based data mining technique was not flexible. If there were no inference rules to track the customer's future behavior, association rule-based data mining systems may not present more information. To resolve this problem, we combined association rule-based data mining with CBR mechanism. CBR is used in reasoning for customer's preference searching and training through the cases. Data mining and CBR-based hybrid purchase support mechanism can reflect both association rule-based logical inference and case-based information reuse. A Web-log data gathered in the real-world Internet shopping mall is given to illustrate the quality of the proposed systems.

• 정보관리학회지
• /
• 제7권1호
• /
• pp.68-78
• /
• 1990

본 연구는 전문가 대체 시스템에서 모호하거나 절대적인 정의가 없는 개념들을 퍼 지 논리를 이용하여 추론해 나가는 과정을 제시하고 있다. 호가실한 정보가 주어졌을 때 전 체적인 퍼지 추론에 어떻게 영향을 미치는가를 검토하였으며, 구체적으로 확률적 추론에 이 용되는 퍼지 추론의 예를 제시하였다.

• 한국정보과학회논문지:데이타베이스
• /
• 제27권2호
• /
• pp.141-150
• /
• 2000

기존의 퍼지 규칙 기반 전문가 시스템 언어에는 크게 세 가지 단점들이 있다. 첫째, 복합 객체 추론 기능이 없으며, 둘째, 의미적으로 이해하기 쉽고 개념적으로 사용하기 용이한 퍼지 추론을 지원하지 못할 뿐 아니라, 세째, 지식 표현과 추론 방식이 기존의 데이터베이스 모텔과 구문이나 의미에서 현격 한 차이를 보이고 있기 때문에 서로 통합되기 어렵다. 본 논문에서는 이 세가지 단점들을 해결하기 위한 퍼지 객체 추론 모델의 정형화를 보이고, GIS 응용을 예로 들어 제시하는 모델이 데이타베이스내 GIS 복합 객체들을 자연스럽게 모델링하고, 이들 사이의 퍼지 추론을 성공적으로 수행함을 보인다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권1호
• /
• pp.7-12
• /
• 2005

This paper deals with the fuzzy modeling for the complex and uncertain nonlinear systems, in which conventional and mathematical models may fail to give satisfactory results. Finally, we provide numerical examples to evaluate the feasibility and generality of the proposed method in this paper. The expert system which introduces fuzzy logic in order to process uncertainties is called fuzzy expert system. The fuzzy expert system, however, has a potential problem which may lead to inappropriate results due to the ignorance of some information by applying fuzzy logic in reasoning process in addition to the knowledge acquisition problem. In order to overcome these problems, We construct fuzzy inference network by extending the concept of reasoning network in this paper. In the fuzzy inference network, the propositions which form fuzzy rules are represented by nodes. And these nodes have the truth values representing the belief values of each proposition. The logical operators between propositions of rules are represented by links. And the traditional propagation rule is modified.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.532-538
• /
• 1998

In this paper, a new adaptive fuzzy inference method using neural network based fuzzy reasoning is proposed to make a fuzzy logic control system more adaptive and more effective. In most cases, the design of a fuzzy inference system rely on the method in which an expert or a skilled human operator would operate in that special domain. However, if he has not expert knowledge for any nonlinear environment, it is difficult to control in order to optimize. Thus, using the proposed adaptive structure for the fuzzy reasoning system can controled more adaptive and more effective in nonlinear environment for changing input membership functions and output membership functions. The proposed fuzzy inference algorithm is called adaptive neuro-fuzzy control(ANFC). ANFC can adapt a proper membership function for nonlinear plant, based upon a minimum number of rules and an initial approximate membership function. Nonlinear function approximation and rotary inverted pendulum control system ar employed to demonstrate the viability of the proposed ANFC.

• 한국안전학회지
• /
• 제18권1호
• /
• pp.50-55
• /
• 2003

This paper presents an intelligent computer system, which can easily diagnose electrical fire causes, without the help of human experts of electrical fires diagnosis. For this system, a database is built with facts and rules driven from real electrical fires, and an intellectual database system which even a beginner can diagnose fire causes has been developed, named as an Electrical Fire Causes Diagnosis System : EFCDS. The database system has adopted, as an inference engine, a mixed reasoning approach which is constituted with the rule-based reasoning and the case-based reasoning. The system for a reasoning model was implemented using Delphi 3, one of program development tools, and Paradox is used as a database building tool. To verify effectiveness and performance of this newly developed diagnosis system, several simulated fire examples were tested and the causes of fire examples were detected effectively by this system. Additional researches will be needed to decide the minimal significant level of the solution and the weighting level of important factors.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권4호
• /
• pp.254-259
• /
• 2008

Uncertainty of result of context awareness always exists in any context-awareness computing. This falling-off in accuracy of context awareness result is mostly caused by the imperfectness and incompleteness of sensed data, because of this reasons, we must improve the accuracy of context awareness. In this article, we propose a novel approach to model the uncertain context by using ontology and context reasoning method based on Bayesian Network. Our context aware processing is divided into two parts; context modeling and context reasoning. The context modeling is based on ontology for facilitating knowledge reuse and sharing. The ontology facilitates the share and reuse of information over similar domains of not only the logical knowledge but also the uncertain knowledge. Also the ontology can be used to structure learning for Bayesian network. The context reasoning is based on Bayesian Networks for probabilistic inference to solve the uncertain reasoning in context-aware processing problem in a flexible and adaptive situation.