• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.447-450
• /
• 2003

In this research, we propose an automatic knowledge acquisition and composite knowledge expression mechanism based on machine learning and relational database. Most of traditional approaches to develop a knowledge base and inference engine of expert systems were based on IF-THEN rules, AND-OR graph, Semantic networks, and Frame separately. However, there are some limitations such as automatic knowledge acquisition, complicate knowledge expression, expansibility of knowledge base, speed of inference, and hierarchies among rules. To overcome these limitations, many of researchers tried to develop an automatic knowledge acquisition, composite knowledge expression, and fast inference method. As a result, the adaptability of the expert systems was improved rapidly. Nonetheless, they didn't suggest a hybrid and generalized solution to support the entire process of development of expert systems. Our proposed mechanism has five advantages empirically. First, it could extract the specific domain knowledge from incomplete database based on machine learning algorithm. Second, this mechanism could reduce the number of rules efficiently according to the rule extraction mechanism used in machine learning. Third, our proposed mechanism could expand the knowledge base unlimitedly by using relational database. Fourth, the backward inference engine developed in this study, could manipulate the knowledge base stored in relational database rapidly. Therefore, the speed of inference is faster than traditional text -oriented inference mechanism. Fifth, our composite knowledge expression mechanism could reflect the traditional knowledge expression method such as IF-THEN rules, AND-OR graph, and Relationship matrix simultaneously. To validate the inference ability of our system, a real data set was adopted from a clinical diagnosis classifying the dermatology disease.

• 제어로봇시스템학회논문지
• /
• 제5권1호
• /
• pp.54-61
• /
• 1999

Objective of the research is to put the vast and complex fault tracking knowledge of human experts in semiconductor production line into the knowledge base of computer system. We mined the fault tracking knowledge of domain experts(engineers of production line) for the construction of knowledge base of the expert system. Object oriented fact models which increase the extensibility and reusability have been built. The rules are designed to perform the fault diagnosis of the items in production device. We have exploited the evidence accumulation method to assign check priority in rules. The major contribution is in the overall design and implementation of the nile base and related facts of the expert system in object oriented paradigm for the application of the system in fault diagnosis in semiconductor production line.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2005년도 춘계학술대회 학술발표 논문집 제15권 제1호
• /
• pp.153-156
• /
• 2005

In this paper, a framework for implementing UFIS (Unified Fuzzy rule-based knowledge Inference System) is presented. First, fuzzy clustering and fuzzy rules deal with the presence of the knowledge in DB (DataBase) and its value is presented with a value between 0 and 1. Second, RDB (Relational DB) and SQL queries provide more flexible functionality fur knowledge management than the conventional non-fuzzy knowledge management systems. Therefore, the obtained fuzzy rules offer the user additional information to be added to the query with the purpose of guiding the search and improving the retrieval in knowledge base and/ or rule base. The framework can be used as DM (Data Mining) and ES (Expert Systems) development and easily integrated with conventional KMS (Knowledge Management Systems) and ES.

• 한국지능시스템학회논문지
• /
• 제14권6호
• /
• pp.764-770
• /
• 2004

This paper presents a hybrid data mining mechanism to extract expert knowledge from historical data and extend expert systems' reasoning capabilities by using fuzzy neural network (FNN)-based learning & rule extraction algorithm. Our hybrid data mining mechanism is based on association rule extraction mechanism, FNN learning and fuzzy rule extraction algorithm. Most of traditional data mining mechanisms are depended ()n association rule extraction algorithm. However, the basic association rule-based data mining systems has not the learning ability. Therefore, there is a problem to extend the knowledge base adaptively. In addition, sequential patterns of association rules can`t represent the complicate fuzzy logic in real-world. To resolve these problems, we suggest the hybrid data mining mechanism based on association rule-based data mining, FNN learning and fuzzy rule extraction algorithm. Our hybrid data mining mechanism is consisted of four phases. First, we use general association rule mining mechanism to develop an initial rule base. Then, in the second phase, we adopt the FNN learning algorithm to extract the hidden relationships or patterns embedded in the historical data. Third, after the learning of FNN, the fuzzy rule extraction algorithm will be used to extract the implicit knowledge from the FNN. Fourth, we will combine the association rules (initial rule base) and fuzzy rules. Implementation results show that the hybrid data mining mechanism can reflect both association rule-based knowledge extraction and FNN-based knowledge extension.

• 한국해양공학회지
• /
• 제21권6호
• /
• pp.115-119
• /
• 2007

Inference rules of the knowledge base, generated by experts or optimization, may be often inconsistent and incomplete. This paper suggests a systematic and automatic method which extracts inference rules not from experts' subject but from data. First, input/output linguistic variables are partitioned into several properties by the fuzzy equalization algorithm and each combination of their properties comes to premise of inference rule. Then, the conclusion which is the mast suitable for the premise is selected by evaluating consistent measure. This method, automatically from data, derives inference rules from experience. It is shown through application that extracts new inference rules between hull dimensions and hull performance.

• 한국영어학회지:영어학
• /
• 제2권2호
• /
• pp.185-205
• /
• 2002

Within the framework of Generalized Sympathy (GS) (Jun 1999), this paper investigates the reasons why phonological rules such as Cluster Simplification, Closed Syllable ${\ae}$-Tensing, and Belfast Dentalization overapply or underapply in Class 2 affixed words in English. According to GS, a morphologically independent word can be treated as a derived word in that it is assumed to have any possible outputs as bases to resemble. As a result, a correspondence relation is triggered between a morphologically independent word being represented as Derived (D) and any possible outputs represented as Base (B), i.e., BD-Faith. In analyses of affixed words, BA-Faith is evoked, instead of BD-Faith. Furthermore, as Benua (1997) suggests, BA-Faith is classified into two correspondence relations; $BA_1$-Faith between Base and Class 1 affixed words, and $BA_2$-Faith between Base and Class 2 affixed words. When the $BA_1$-Faith takes precedence over phonological constraints three rules misapply in Class 2 affixed words. In other words, the misapplications are driven by base-identity effects.

• 대한전기학회논문지
• /
• 제39권7호
• /
• pp.720-728
• /
• 1990

A learning control method is proposed in this paper, using a knowledge base which contains control rules, data, and patterns of the past experience of a plant. The knowledge for plant control is retrieved from measurement data during operation and continually modified after control performance evaluation. A control method is proposed using tinually modified after control performance evaluation. A control method is proposed using fuzzy model of the plant and a recursive statistic decision method of fuzzy subset for control rule generation. Also, the resulting knowledge-based control algorithm has been applied to aprocess and its performance improvement and proper generation of appropriate control rules have been verified.

• 대한산업공학회지
• /
• 제29권1호
• /
• pp.32-40
• /
• 2003

In this study, we develop the Genetic Fuzzy System(GFS) to estimate the link traveling speed. Based on the genetic algorithm, we can get the fuzzy rules and membership functions that reflect more accurate correlation between traffic data and speed. From the fact that there exist missing links that lack traffic data, we added a Case Base Reasoning(CBR) to GFS to support estimating the speed of missing links. The case base stores the fuzzy rules and membership functions as its instances. As cases are accumulated, the case base comes to offer appropriate cases to missing links. Experiments show that the proposed GFS provides the more accurate estimation of link traveling speed than existing methods.

• 산업공학
• /
• 제3권1호
• /
• pp.31-38
• /
• 1990

This paper deals with two topics which are vital in fuzzy expert systems; one is how to build fuzzy knowledge base by fuzzy expertise modeling for representing knowledge with imprecise characteristic and the other is how to draw an inference from fuzzy knowledge base using translating rules. The result of this study provides the basic principle for constructing the fuzzy knowledge base and the fuzzy inference system.

• Steel and Composite Structures
• /
• 제12권4호
• /
• pp.353-379
• /
• 2012

The accuracy of the 30% and SRSS rules, commonly used to estimate the combined response of structures, and some related issues, are studied. For complex systems and earthquake loading, the principal components give the maximum seismic response. Both rules underestimate the axial load by about 10% and the COV of the underestimation is about 20%. Both rules overestimate the base shear by about 10%. The uncertainty in the estimation is much larger for axial load than for base shear, and, for axial load, it is much larger for inelastic than for elastic behavior. The effect of individual components may be highly correlated, not only for normal components, but also for totally uncorrelated components. The rules are not always inaccurate for large values of correlation coefficients of the individual effects, and small values of such coefficients are not always related to an accurate estimation of the response. Only for perfectly uncorrelated harmonic excitations and elastic analysis of SDOF systems, the individual effects of the components are uncorrelated and the rules accurately estimate the combined response. In the general case, the level of underestimation or overestimation depends on the degree of correlation of the components, the type of structural system, the response parameter, the location of the structural member and the level of structural deformation. The codes should be more specific regarding the application of these rules. If the percentage rule is used for MDOF systems and earthquake loading, at least a value of 45% should be used for the combination factor.