• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.4
• /
• pp.12-17
• /
• 1995

Fuzzy rules, developed by experts thus far, may be often inconsistent and incomplete. This paper proposes a new methodology for automatic generation of fuzzy rules which are nearly complete and not inconsistent. This is accomplished by simulating a knowledge gathering process of humans from control experiences. This method is simpler and more efficient than existing ones. It is shown through simulation that our method even generates better rules than those generated by experts, under fine tuned parameters.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.2
• /
• pp.430-440
• /
• 1997

The knowledge repressenatation technique by production rule has been popular method to represent to represent the experts'dxpertise in expert systems.In this paper,we propose a method to verify the integrity of rule base.Proposcd method models rule base as a Petri net and utilizes the systematic strucutural properties of the petri net for berifi-cation.We describe the pricesure to check rule base at both local and global level intermal verification.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.613-615
• /
• 2004

수치적인 데이터를 분류하기 위한 대표적인 방법은 퍼지 규칙을 사용하는 것이다. 하지만 퍼지 규칙을 이용하는 방법은 퍼지 소속 함수를 어떻게 정의하느냐에 따라 퍼지 분류의 성능이 크게 영향을 받는다는 문제점이 있다. 따라서 퍼지 규칙을 쉽게 이해하기 위해서는 가능한 퍼지 규칙의 수를 적게 유지하는 것이 필요하다. 본 논문에서는 효과적이며 이해하기 쉬운 퍼지 규칙을 생성하기 위해 기울기 강하법을 기반으로 하는 소속 함수 학습 방법을 제안한다 에러율을 감소하기 위해 Penalty 연산과 Reward 연산을 통해 소속 함수가 반복적으로 조절된다 새로운 소속 함수는 Coverage 연산에 의해 생성된다. 또한 이해하기 쉬운 퍼지 규칙을 최적화하기 위해 학습된 소속 함수골 퍼지 결정 트리에 적용한다. 본 논문에서 제안한 알고리즘의 타당성을 확인하기 위해 벤치 마크 데이터인 Iris, Wisconsin Breast Cancer, Plma, Bupa 데이터를 이용하여 실험 결과를 보인다. 실험 결과를 통해 제안한 알고리즘이 기존의 C4.5와 FID 3.1 알고리즘보다 더 효과적이거나 비슷한 성능을 보임을 알 수 있다.

• Journal of Korean Library and Information Science Society
• /
• v.52 no.4
• /
• pp.153-177
• /
• 2021

The revision of the Korean Cataloging Rules (KCR) is in progress in order to conform IFLA LRM conceptual model and to strengthen its internal stability. Religious works, along with musical works and legal works, have been treated as special and important in cataloging rules. This trend continues in the new cataloging rules that seek a bibliographic model that interconnects related materials. However since KCR2(1966), there are no rules for access points or specific rules on religious works. Under the circumstances, this study analyzed (1) the contents of religious works in the recently revised cataloging rules, (2) the access points and their functions for religious works implemented in online catalogs and authority system, and finally (3) the direction and scope of KCR revision. As a result of the study, this study suggested that it is necessary to prepare detailed rules for preferred title and authorized access points for various religious works in KCR. In conclusion, some issues for further discussion were summarized.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.4
• /
• pp.942-950
• /
• 1998

Extraction of knowledge, especially in the form of rules, from raw data is very important in data mining, the aim of which is to help users who feel the lack of knowledge in spite of the abundance of data. Logic minimization tools are ones which derive optimized knowledge given ON set and DC set. First, the parallel expansion scheme of logic minimization is extracted and used to obtain intial knowledge to get final rules, which are successfully applicable to real world data. The prototype system based on this new approach has been experimented with real world data to show that it is as practical as conventional long studied decision tree methods like C4.5 system.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2002.08a
• /
• pp.141-146
• /
• 2002

KCR4판 초안의 제5장 '악보'부분에 대한 각 조문을 일본목록규칙(NCR, 1996), 영미목록규칙(AACR2R, 1998), ISBD(PM, 1991)와 비교해 그 차이점과 논란이 될 수 있는 부분에 대한 분석을 시도해 보았다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.24 no.2
• /
• pp.185-203
• /
• 2013

This study was to suggest the new rules for revision of KCR4 by comparing between ISBD consolidated edition and KCR4. The study methods was to compare the rules in each element after mapping the description elements in each area of ISBD and KCR4. Resultingly, first, content forms and media types must be included for describing resource types. Second, it is needed for rules about the common title and the dependent title. Third, it is needed for rules about "parallel" such as parallel title, parallel other title information, parallel statement of responsibility relating to title, parallel edition statement, parallel statement of responsibility relating to edition, parallel numbering system, parallel place of publication, production and distribution, et. al. Fourth, the rules about material or type of resource specific area must be regulated in terms of the contents of the resource. Fifth, the home country principle must be not applied in describing the place of publication, production and distribution for the consistency. Sixth, it is needed to regulate the extent, other physical details, dimensions, and accompanying material statement for all materials instead of the material description according to material types. Seventh, rule number of notes must be agreed to number of main rules. Eighth, it is needed for detailed rules about resource identifier. This study might be contributed to revise the KCR4.

• Journal of KIISE:Software and Applications
• /
• v.26 no.4
• /
• pp.462-472
• /
• 1999

능동적 시간지원 데이터베이스 시스템은 시간지원 데이터베이스 시스템에 능동규칙 시스템을 통합하여 구성한 진보된 데이터베이스 시스템이다. 이 시스템은 추세 분석, 상태 관찰을 통한 경보,고장에 대한 예측, 금융 시스템 및 공정 제어 등과같은 고도의 응용에 효과적으로 대응할수 있다. 그러나 능동적 시간지원 데이터베이스 시스템은 시간 차원을 갖는 다차원 데이터공간에 대해 처리해야 하므로 그 처리비용이 매우 높으며, 규칙 처리에 의한 시스템 부하가 매우 증가할 수 있다. 따라서 효과적 규칙 처리방법에 대한 연구가 수행되어야 한다. 한편 규칙의 성능에 대한 문제는 일반적으로 조건 평가 방법의 효율성에 달려있다. 특히 데이터의 시간차원을 고려한 시간지원 능동규칙의 경우 시간 영역에 따라 규칙에 의해 처리되어야 할 데이터 량의 증가하고 이에 다라 성능의 차이가 많이 나므로 더욱 문제가 된다. 따라서 이 논문에서는 능동적 시간지원 데이터베이스 시스템을 위한 시간지원 능동규칙의 성능향상을 위해 조건 평가를 검토하고 시간지원 차분에 의한 시간지원 점진적 평가연산을 제시하였다. 아울러 이 시간지원 점진적 연산자를 적용한 조건 평가 예를 보이고 이 연산자의 효율성을 증명하였다.

• The KIPS Transactions:PartC
• /
• v.16C no.4
• /
• pp.449-460
• /
• 2009

The signature hashing algorithm[9] provides the fast pattern matching speed for network IPS(Intrusion Prevention System) using the hash table. It selects 2 bytes from all signature rules and links to the hash table by the hash value. It has an advantage of performance improvement because it reduces the number of inspecting rules in the pattern matching. However it has a disadvantage of performance drop if the number of rules with the same hash value increases when the number of rules are large and the corelation among rules is strong. In this paper, we propose a method to make all rules distributed evenly to the hash table independent of the number of rules and corelation among rules for overcoming the disadvantage of the signature hashing algorithm. In the proposed method, it checks whether or not there is an already assigned rule linked to the same hash value before a new rule is linked to a hash value in the hash table. If there is no assigned rule, the new rule is linked to the hash value. Otherwise, the proposed method recalculate a hash value to put it in other position. We implemented the proposed method in a PC with a Linux module and performed experiments using Iperf as a network performance measurement tool. The signature hashing method shows performance drop if the number of rules with the same hash value increases when the number of rules are large and the corelation among rules is strong, but the proposed method shows no performance drop independent of the number of rules and corelation among rules.

• Journal of The Korean Association For Science Education
• /
• v.37 no.4
• /
• pp.705-717
• /
• 2017

The purpose of the study is to explore secondary science teachers' emotional display rules, types of emotional labor, science-specific emotional display rules and the episodes of emotional labor. For this purpose, the survey to measure emotional labor of science teachers (The Emotional Labor of Science Teaching Scale: TELSTS) was developed and the participants were 145 secondary science teachers in Korea. Results showed that first, secondary science teachers recognized the emotional display rules defined by their schools, especially, positive display rules. Second, secondary science teachers showed that they were carrying out emotional labor in order to keep their emotional display rules in check. The mean value of responses to deep acting was high. Also, there were statistically significant differences in emotional labor depending on whether they were full-time or part-time teachers and their teaching career. Third, as a result of analyzing the specificity of science teachers, it was mainly related to the objective and logical image of science, and experimental instruction. Seventy-four percent (74%) of responses were negative or neutral emotional display rules. Finally, implications for science education are discussed.