• 지능정보연구
• /
• 제14권1호
• /
• pp.1-17
• /
• 2008

데이터 마이닝은 대용량의 데이터에 숨겨진 의미있고 유용한 패턴과 상관관계를 추출하여 의사결정에 활용하는 작업이다. 그 중에서도 고객 트랜잭션의 데이터베이스에서 아이템(item) 사이에 존재하는 연관규칙을 찾는 것은 중요한 일이 되었다. Apriori 알고리즘 이후 연관규칙을 찾기 위해 대용량의 데이터베이스로부터 압축된 의미있는 정보를 저장하기 위한 데이터 구조와 알고리즘들이 많이 제안되어 왔다. 연관규칙을 발견하기 위한 기존의 연구들은 모든 규칙을 찾아내지만, 사람이 분석하기에 너무 많은 규칙이 생성되기 때문에 규칙을 분석하기 위한 일 또한 많은 과정을 거쳐야 한다. 본 논문에서는 빈발 패턴 네트워크(Frequent Pattern Network)라 부르는 자료 구조를 제안하고 이를 활용하였다. 네트워크는 정점과 간선으로 구성되며 정점은 아이템을 표현하고, 간선은 두 아이템 집합을 표현한다. 아이템의 빈도수를 이용하여 빈발 패턴 네트워크를 구성하고, 아이템 사이의 유사도를 측정한다. 그리고 클러스터 내의 아이템과는 유사도가 높고, 다른 클러스터의 아이템과는 유사도가 낮도록 클러스터를 생성한다. 클러스터를 이용해 연관규칙을 생성하고 실험을 통해 Apriori와 FP Growth 알고리즘과의 성능을 비교를 하였다. 그 결과 빈발 패턴 네트워크에서 신뢰도 유사도를 이용하는 것이 클러스터의 정확성을 높여줌을 볼 수 있었다. 그리고 전통적인 방법과 비교를 통해 빈발 패턴 네트워크를 이용하는 것이 최소지지도에 유연성을 가짐을 알 수 있었다.

• 한국산업정보학회논문지
• /
• 제20권5호
• /
• pp.61-69
• /
• 2015

매일 각종 모바일 디바이스와 온라인, 소셜네트워크서비스 등에서 쏟아지는 데이터로 인해 정보의 홍수를 넘어 과부하 상태에 있다. 이미 생성되어 있는 기존 정보들도 있지만 시시각각 새롭게 생겨나고 있는 정보들이 헤아릴 수 없을 정도이다. 연관분석은 이러한 정보들 속에서 나타나는 항목의 발생 빈도수가 최소 지지도보다 큰 빈발항목집합(Frequent Item set)을 찾는 방법이다. 항목의 수가 많아짐에 따라 규칙의 수도 기하급수적으로 늘어나므로 원하는 정보를 찾기가 어려운 단점이 있다. 따라서 본 논문에서는 트랜잭션데이터 집합을 Boolean 변수 아이템으로 나타내었다. 논리함수를 간소화하는데 사용되는 Quine-McKluskey의 방법으로 알고리즘화하여 각 항목에 가중치를 부여한 WT-알고리즘을 제안한다. 제안한 알고리즘은 항목의 개수와 관계없이 간략화가 가능한 장점으로 인하여 불필요한 규칙을 감소시켜 데이터마이닝 효율을 향상시킬 수 있다.

• 산업경영시스템학회지
• /
• 제38권3호
• /
• pp.78-86
• /
• 2015

Up-to-date business environment for manufacturers is very complex and rapidly changing. In other words, companies are facing a variety of changes, such as diversifying customer requirements, shortening product life cycles, and switching to small quantity batch production. In this situation, the companies are introducing the concept of JIT (just-in-time) to solve the problem of on-time production and on-time delivery for survival. Though many companies have introduced ERP (enterprise resource planning) systems and MRP (material requirement planning) systems, the performance of these systems seems to fall short of expectations. In this paper, the case study on introducing an APS (advanced planning and scheduling) system based on dispatching rules to a machining company and on finding a method to establish an efficient production schedule is presented. The case company has trouble creating an effective production plan and schedule, even though it is equipped with an MRP-based ERP system. The APS system is applied to CNC (computer numerical control) machines, which are key machines of the case company. The overall progress of this research is as follows. First, we collect and analyze the master data on individual products and processes of the case company in order to build a production scheduling model. Second, we perform a pre-allocation simulation based on dispatching rules in order to calculate the priority of each order. Third, we perform a set of production simulations applying the priority value in order to evaluate production lead time and tardiness of pre-defined dispatching rules. Finally, we select the optimal dispatching rule suitable for work situation of the case company. As a result, an improved production schedule leads to an increase in production and reduced production lead time.

• 무역상무연구
• /
• 제25권
• /
• pp.75-98
• /
• 2005

With the advent of new customs and practice of electronic records, the eUCP provides some useful guidance to accommodate the presentation of the paper documents electronically and also provides necessary rules to allow the UCP and eUCP to work together. There is no denying the fact that many of the UCP articles are not impacted by the presentation of electronic equivalent of paper documents, so the integrated application of the UCP and eUCP will be broad enough to allow for developing practice in this area. This study discusses some theoretical implication for efficient utilization of the global usages of letter of credit through the finding of optimal solution in the state of uncertainty caused by the electronic presentation of documents. This study suggest that the decision rules be developed to show how individuals choose optimal portfolio between the eUCP and the UCP that maximize their expected utility in letter of credit transaction, and also suggest that the optimal portfolio be determined at the point of tangency between the efficient trading line and the highest indifference curve in the mean-variance plane. This study finally recommends three rebuttable doctrines with regard to the relationship between the eUCP and UCP such as linkage characteristics, generation lap propensity, and homothetic application rule, which may be the critical standards for understanding of the integrated usages of the eUCP and UCP.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제5권2호
• /
• pp.107-118
• /
• 2001

Mathematics subject of the seventh national curriculum in Korea, which has been effective since 2000, strongly encourages the use of calculators and computers to help children gain a better understanding of basic mathematical concepts and develop creative thinking and problem-solving skills without spending too much time and effort on making mechanical computations. Despite the recommendation by the national curriculum, however, only a small segment of elementary school teachers have been using calculators because of the fear that children\\`s dependence on calculators might bring about negative consequences. As a result, little research has been conducted in this area as well. This study has been conducted on the assumption that calculators have the potential for being a useful instructional tool in certain areas of elementary school mathematics education. To investigate the usefulness of calculators, a review was made of the scanty literature in the area. The literature review indicated that calculators are effective when they are used for the following purposes: understanding concepts and properties in numbers and operations, deducing mathematical rules, and solving problems. In view of the available research finding, we will give some concrete learning and teaching models of such uses of calculators. The teaching-learning models are organized around three categories: concept formation, discovery of principles and rules, and problem solving. Such organization is intended to help teachers use the models with ease.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권3호
• /
• pp.204-209
• /
• 2002

The interest of data mining in artificial intelligence with fuzzy logic has been increased. Data mining is a process of extracting desirable knowledge and interesting pattern ken large data set. Because of expansion of WWW, web data is more and more huge. Besides mining web contents and web structures, another important task for web mining is web usage mining which mines web log data to discover user access pattern. The goal of web usage mining in this paper is to find interesting user pattern in the web with user feedback. It is very important to find user's characteristic fer e-business environment. In Customer Relationship Management, recommending product and sending e-mail to user by extracted users characteristics are needed. Using our method, we extract user profile from the result of web usage mining. In this research, we concentrate on finding association rules and verify validity of them. The proposed procedure can integrate fuzzy set concept and association rule. Fuzzy association rule uses given server log file and performs several preprocessing tasks. Extracted transaction files are used to find rules by fuzzy web usage mining. To verify the validity of user's feedback, the web log data from our laboratory web server.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.123-126
• /
• 1998

The theoretical foundations of GA are the Schema Theorem and the Building Block Hypothesis. In the Meaning of these foundational concepts, simple genetic algorithm(SGA) allocate more trials to the schemata whose average fitness remains above average. Although SGA does well in many applications as an optimization method, still it does not guarantee the convergence of a global optimum. Therefore as an alternative scheme, there is a growing interest in a co-evolutionary system, where two populations constantly interact and co-evolve in contrast with traditional single population evolutionary algorithms. In this paper, we propose a new design method of an optimal fuzzy logic controller using co-evolutionary concept. In general, it is very difficult to find optimal fuzzy rules by experience when the input and/or output variables are going to increase. So we propose a co-evolutionary method finding optimal fuzzy rules. Our algorithm is that after constructing two population groups m de up of rule vase and its schema, by co-evolving these two populations, we find optimal fuzzy logic controller. By applying the proposed method to a path planning problem of autonomous mobile robots when moving objects exist, we show the validity of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• 제21권2호
• /
• pp.263-270
• /
• 2010

데이터마이닝은 방대한 양의 데이터 속에서 쉽게 드러나지 않는 유용한 정보를 체계적이고도 자동적으로 찾아내는 기법이다. 데이터마이닝의 중요한 목표 중의 하나는 여러 변수들 간의 관계를 발견하고 결정하는 것이다. 연관성 규칙은 항목 집합으로 표현된 트랜잭션에서 각 항목간의 연관성을 반영하는 규칙으로서, 항목 집합간의 관계를 지지도, 신뢰도, 순수 신뢰도 등과 같은 흥미도 측도에 의해 명확히 수치화함으로써 두 개 이상의 항목집합간의 관련성을 표시해주기 때문에 현업에서 많이 활용되고 있다. 본 논문에서는 기존에 많이 활용되고 있는 흥미도 측도인 신뢰도와 순수 신뢰도의 문제점을 보완하여 연관성 규칙을 올바르게 생성하기 위한 새로운 의사결정과정을 제안하고자 한다. 본 논문에서 제안하는 의사결정과정은 특히 스트리밍 데이터베이스에서의 연관성 규칙을 탐색하는 데 효율적이다.

• Journal of Information Processing Systems
• /
• 제9권4호
• /
• pp.575-591
• /
• 2013

Most of the edge detection methods available in literature are gradient based, which further apply thresholding, to find the final edge map in an image. In this paper, we propose a novel method that is based on fuzzy logic for edge detection in gray images without using the gradient and thresholding. Fuzzy logic is a mathematical logic that attempts to solve problems by assigning values to an imprecise spectrum of data in order to arrive at the most accurate conclusion possible. Here, the fuzzy logic is used to conclude whether a pixel is an edge pixel or not. The proposed technique begins by fuzzifying the gray values of a pixel into two fuzzy variables, namely the black and the white. Fuzzy rules are defined to find the edge pixels in the fuzzified image. The resultant edge map may contain some extraneous edges, which are further removed from the edge map by separately examining the intermediate intensity range pixels. Finally, the edge map is improved by finding some left out edge pixels by defining a new membership function for the pixels that have their entire 8-neighbourhood pixels classified as white. We have compared our proposed method with some of the existing standard edge detector operators that are available in the literature on image processing. The quantitative analysis of the proposed method is given in terms of entropy value.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.361-367
• /
• 1998

The main two applications of the Genetic Algorithms(GA) are the optimization and the machine learning. Machine Learning has two objectives that make the complex system learn its environment and produce the proper output of a system. The machine learning using the Genetic Algorithms is called GA machine learning or genetic-based machine learning (GBML). The machine learning is different from the optimization problems in finding the rule set. In optimization problems, the population of GA should converge into the best individual because optimization problems, the population of GA should converge into the best individual because their objective is the production of the individual near the optimal solution. On the contrary, the machine learning systems need to find the set of cooperative rules. There are two methods in GBML, Michigan method and Pittsburgh method. The former is that each rule is expressed with a string, the latter is that the set of rules is coded into a string. Th classifier system of Holland is the representative model of the Michigan method. The classifier systems arrange the strength of classifiers of classifier list using the message list. In this method, the real time process and on-line learning is possible because a set of rule is adjusted on-line. A classifier system has three major components: Performance system, apportionment of credit system, rule discovery system. In this paper, we solve the food search problem with the learning and evolution of an artificial ant using the learning classifier system.