• KIISE Transactions on Computing Practices
• /
• v.21 no.12
• /
• pp.774-779
• /
• 2015

In this paper, we present the design and implementation of a large-scale qualitative spatial reasoner using Apache Spark, an in-memory high speed cluster computing environment, which is effective for sequencing and iterating component reasoning jobs. The proposed reasoner can not only check the integrity of a large-scale spatial knowledge base representing topological and directional relationships between spatial objects, but also expand the given knowledge base by deriving new facts in highly efficient ways. In general, qualitative reasoning on topological and directional relationships between spatial objects includes a number of composition operations on every possible pair of disjunctive relations. The proposed reasoner enhances computational efficiency by determining the minimal set of disjunctive relations for spatial reasoning and then reducing the size of the composition table to include only that set. Additionally, in order to improve performance, the proposed reasoner is designed to minimize disk I/Os during distributed reasoning jobs, which are performed on a Hadoop cluster system. In experiments with both artificial and real spatial knowledge bases, the proposed Spark-based spatial reasoner showed higher performance than the existing MapReduce-based one.

• The Journal of Society for e-Business Studies
• /
• v.13 no.3
• /
• pp.85-101
• /
• 2008

The semantic web is taken as next generation standards of information exchange on the internet to overcome the limitations of the current web. To utilize the information on the semantic web, tools are required the functionality of query search and reasoning for the ontology. However, most of semantic web management tools cannot efficiently support the search for the complex query because they apply Triple-based storage structure about RDF metadata. We design the storage structure of the ontology in corresponding with the structure of ontology data and develop the search system(SMART-DLTriple) to support complex query search efficiently in this research. The performance of the system using new storage structure is evaluated to compare with the popular semantic web management systems. The proposed method and system make a contribution to enhancement of a practical ontology reasoning systems due to improved performance of the ontology search.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.247-251
• /
• 1989

본 논문은 한국어를 대상으로 하는 자연언어 처리 시스템을 개발하는데 있어서 기초가 되는 지식베이스의 구축에 대하여 논한다. 한국어의 일반문에서 단문을 분리해 내기 위하여 형태소 해석의 결과로부터 도출한 구 단위를 한-일 기계번역 시스템의 구문, 의미 해석기(VCPN) 을 적용하여 절단위로 결합한다. 그리고 이들 단위절에 대하여 대명사의 조응관계, 생략에의 재생을 위한 추론, 부정어, 시제일치 등을 처리하여 논리적 지식베이스를 구성하는 방법을 제안한다. 본 논문은 입력문장에 제한을 두지 않고 단문으로부터 장문에 이르기까지 광범위한 일반문을 대상으로 하여 Horn Clause 이론을 확장한다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.34 no.7
• /
• pp.282-287
• /
• 2007

Information society is dramatically developing in the various areas of finance, trade, medical service, energy, and education using information system. Evaluation for risk analysis should be done before security management for information system and security risk analysis is the best method to safely prevent it from occurrence, solving weaknesses of information security service. In this paper, Modeling it did the evaluation-base CBD function it will be able to establish the evaluation plan of optimum. Evaluation-based CBD(case-based reasoning) functions manages a security risk analysis evaluation at project unit. it evaluate the evaluation instance for beginning of history degree of existing. It seeks the evaluation instance which is similar and Result security risk analysis evaluation of optimum about under using planning.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.05a
• /
• pp.51-54
• /
• 2002

본 논문은 글자 문서를 배경으로 사용자의 손가락 이동에 의하여 일정한 영역을 그린 후, 영역내의 한글영상을 편집 가능한 에디터에 출력하는 시스템을 구현하였다. 영상의 전처리 단계에서는 문서 배경과 손영역을 분리하고 최대 원형 이동법을 이용하여 손의 무게 중심점을 추출한다. 원형 패턴 벡터 알고리즘을 사용하여 손을 인식한 후, 거리 스펙트럼으로 손가락 위치를 찾는다. 손가락의 움직임에 의해 선택되어진 문자 영역을 추출한 후, 한글 자소 간 히스토그램을 이용하여 추출된 문자 이미지 영역에서 문자단위로 분할하고 다양한 크기의 문자를 표준화한다. 퍼지 추론을 적용한 원형 패턴 벡터 알고리즘을 이용하여 표준 패턴문자와 입력문자의 특징벡터를 비교하여 문자를 인식하게 함으로써 사용자가 원하는 영역의 문자들을 수정 가능한 문서로 변환하였다

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.163-166
• /
• 2017

본 논문에서는 학생들에게 자신의 진로결정에 도움이 될 수 있는 비교과 및 교과 정보 제공 시스템을 제안한다. 이는 교수들의 학생 수강지도에 활용되어 정확한 진로 지도에 도움을 줄 수 있다. 이러한 시스템을 구현하기 위하여, 온톨로지 기반 지식베이스를 구축한다. 온톨로지 지식베이스는 강의, 역량, 능력단위, 직무, 기업 정보로 구성이 되어있으며 유지보수가 쉬운 구조로 설계하였다. 또한 온톨로지 지식베이스가 가진 정보로 새로운 지식들을 추론한다. 이 추론 결과를 웹 인터페이스를 활용해, 사용자가 개념들 간의 관계를 파악하고 자신에게 맞는 과목 및 직무를 추천받을 수 있도록 한다.

• The Korean Journal of Applied Statistics
• /
• v.22 no.1
• /
• pp.181-188
• /
• 2009

This paper discusses the covariance structures of data collected from an experiment with a nested design structure, where a smaller experimental unit is nested within a larger one. Due to the nonrandomization of repeated measures factors to the nested experimental units, compound symmetry covariance structure is assumed for the analysis of data. Treatments are given as the combinations of the levels of random factors and fixed factors. So, a mixed-effects model is suggested under compound symmetry structure. An example is presented to illustrate the nesting in the experimental units and to show how to get the parameter estimates in the fitted model.

• School Mathematics
• /
• v.18 no.4
• /
• pp.819-838
• /
• 2016

This research analyzed proportional reasoning abilities of the 5th grade students who learned only the basis of ratio and rate and 6th grade students who also learned proportion and cross product strategy. Data were collected through the proportional reasoning tests and the interviews, and then the achievement of the students and their proportional reasoning strategies were analyzed. In the light of such analytical results, the conclusions are as follows. Firstly, there is not much difference between 5th and 6th grade students in the achievement scores. Secondly, both 5th and 6th graders are less familiar with the geometric, qualitative and comparisons tasks than the other tasks. Thirdly, not only 5th graders but also 6th graders used informal strategies much more than the formal strategy. Fourthly, some students can't come up with other strategies than the cross product strategy. Finally, many students have difficulties in discerning proportional situation and non-proportional situations. This study provided suggestions for improving teaching proportional reasoning in elementary schools in Korea as follows: focusing on letting students use their informal strategies fluently in geometric, qualitative, and comparisons tasks as well as algebraic, quantitative, and missing value tasks focusing on the concept of ratio and proportion instead of enforcing the formal strategy.

• The Journal of Society for e-Business Studies
• /
• v.18 no.4
• /
• pp.195-214
• /
• 2013

Case-based reasoning is a methodology for solving problems more quickly and efficiently by bringing the most similar case of a given problem from past cases and transforming it to fit the current situation. The most important performance indicator of case-based reasoning is the number of cases, so it is difficult to apply the methodology for the area which has not enough cases. In this paper, we proposed a method to exchange cases based on the Semantic Web in order to overcome the problems. Inparticular, we separated cases into sub-cases to make it possible creating new cases by combining the appropriate sub-cases even if there was no proper full case. In order to achieve that, we designed an ontology that connects a case and its sub-cases, represents detailed similarity rules that compare sub-cases, and represents the rules for the combination of sub-cases. Moreover, we designed and implemented a semantic distributed case-based reasoning framework where a case requester can request sub-cases via the Web from case providers and integrates sub-cases into a new case by using the ontology.

• The Korean Journal of Applied Statistics
• /
• v.1 no.2
• /
• pp.61-65
• /
• 1987

Randomization is one of the principles that should be adopted in comparative experiments. Randomization is well known as a useful tool for averaging out the effects of external factors. It also validates statistical inference based on mathematical model. This teaching meterial is designed for the purpose of illustrating the role of randomization.