• Journal of KIISE:Databases
• /
• v.31 no.1
• /
• pp.1-12
• /
• 2004

As network systems are developed rapidly and network architectures are more complex than before, it needs to use PBNM(Policy-Based Network Management) in network system. Generally, architecture of the PBNM consists of two hierarchical layers: management layer and enforcement layer. A security policy server in the management layer should be able to generate new policy, delete, update the existing policy and decide the policy when security policy is requested. And the security policy server should be able to analyze and manage the alert messages received from Policy enforcement system in the enforcement layer for the available information. In this paper, we propose an alert analyzer using data mining. First, in the framework of the policy-based network security management, we design and implement an alert analyzes that analyzes alert data stored in DBMS. The alert analyzer is a helpful system to manage the fault users or hosts. Second, we implement a data mining system for analyzing alert data. The implemented mining system can support alert analyzer and the high level analyzer efficiently for the security policy management. Finally, the proposed system is evaluated with performance parameter, and is able to find out new alert sequences and similar alert patterns.

• Proceedings of the Korea Database Society Conference
• /
• 2000.11a
• /
• pp.210-215
• /
• 2000

최근 대량의 텍스트 문서로부터 의미 있는 패턴이나 연관 규칙을 발견하기 위한 텍스트마이닝 기법에 대한 연구가 활발히 전개되고 있다. 하지만 비정형 텍스트 문서로부터 추출된 용어의 수는 불규칙적이고 일반적인 용어가 많이 추출되는 관계로 일반적인 연관 규칙 탐사 방법을 사용하게 되면 무의미한 연관 규칙이 대량으로 생성되어 지식 정보를 효과적으로 검색하기 어렵다. 본 논문에서는 연관 규칙 탐사 기법을 이용하여 대량의 문서로부터 유용한 지식 정보를 찾기 위하여 의미적으로 연관된 전문 용어들끼리 클러스터링 하기 위한 방법을 제안하였다. 학술 논문을 대상으로 전문 용어를 추출하여 관련된 용어들끼리 클러스터를 구성하는 실험을 통하여 제안된 방법의 효율성을 보였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.485-489
• /
• 2003

Several clustering methods for spatial data mining have been devised in the literature, but have the following drawback: increase cost due to calculating distance among objects. To solve this problem, we propose a spatial clustering method using regular cells. In this paper, we design and implement file structures, data structures and algorithms to realize the proposed method, also, show experimental results after applying test data to the implemented method.

• Proceedings of the Korea Database Society Conference
• /
• 2000.11a
• /
• pp.101-108
• /
• 2000

기업에서 보유한 전문 지식 정보가 급속도로 증가함에 따라 대량의 문서에 저장된 지식 정보를 효과적으로 탐색하여 기업 경영에 활용하기 위한 지식경영시스템 도입이 확산되고 있다. 이러한 지식경영시스템에서 핵심적인 구성 요소는 전문 분야의 지식 정보를 체계적으로 분류하고 효율적으로 검색하기 위한 지식 탐사 기법이다. 본 논문에서는 데이타마이닝 기법을 이용하여 문서를 자동적으로 분류하기 위한 새로운 모델을 제안하였다. 연관 규칙 탐사 알고리즘을 이용하여 학습용 문서 집합으로부터 세부 분야를 대표하는 색인어 집합을 구성하였다. 세부 분야별 색인어 집합에 대하여 전체 문서에 대한 비중에 따라 가중치 배열을 구성하여 문서를 자동으로 분류하기 위한 기준으로 삼았다. 임의의 문서를 자동적으로 분류하는 실험을 통하여 제안된 방법의 효율성을 검정하였다.

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.40-51
• /
• 2007

To improve academic achievement, the most students not only participate in regular classes but also take various extra programs such as private lessons, private institutes, and educational TV programs. In this paper, we propose a data mining approach to identify which studying methods or usual life patterns during a school vacation affect changes in the academic achievement. First, we derive various studying methods and life patterns that are thought to be affecting changes in the academic achievement during a school vacation. Second, we propose the method of transforming and analyzing data to apply them to decision trees and association rules, which are representative data mining techniques. Third, we construct decision trees and find association rules from the real survey data of middle school students. We have discovered four representative results from the decision trees. First, for students in the higher rank, there is a tendency that private institutes give a positive effect on the academic achievement. Second, for the most students, the Internet teaming sites nay give a negative effect on the achievement. Third, private lessons that have thought to be making a large impact to the achievement, however, do not make a positive effect on the achievement. Fourth, taking several studying methods in parallel nay give a negative effect on the achievement. In association rules, however, we cannot find any meaningful relationships between academic achievement and usual life patterns during a school vacation. We believe that our approach will be very helpful for teachers and parents to give a good direction both in preparing a studying plan and in selecting studying methods during a school vacation.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1314-1323
• /
• 1999

컴퓨터의 사용이 일반화됨에 따라 데이타를 생성하고 수집하는 것이 용이해졌다. 이에 따라 데이타로부터 자동적으로 유용한 지식을 얻는 기술이 필요하게 되었다. 데이타 마이닝에서 얻어진 지식은 정확성과 이해성을 충족해야 한다. 본 논문에서는 데이타 마이닝을 위하여 퍼지 결정트리에 기반한 효율적인 퍼지 규칙을 생성하는 알고리즘을 제안한다. 퍼지 결정트리는 ID3와 C4.5의 이해성과 퍼지이론의 추론과 표현력을 결합한 방법이다. 특히, 퍼지 규칙은 속성 축에 평행하게 판단 경계선을 결정하는 방법으로는 어려운 속성 축에 평행하지 않는 경계선을 갖는 패턴을 효율적으로 분류한다. 제안된 알고리즘은 첫째, 각 속성 데이타의 히스토그램 분석을 통해 적절한 소속함수를 생성한다. 둘째, 주어진 소속함수를 바탕으로 ID3와 C4.5와 유사한 방법으로 퍼지 결정트리를 생성한다. 또한, 유전자 알고리즘을 이용하여 소속함수를 조율한다. IRIS 데이타, Wisconsin breast cancer 데이타, credit screening 데이타 등 벤치마크 데이타들에 대한 실험 결과 제안된 방법이 C4.5 방법을 포함한 다른 방법보다 성능과 규칙의 이해성에서 보다 효율적임을 보인다.Abstract With an extended use of computers, we can easily generate and collect data. There is a need to acquire useful knowledge from data automatically. In data mining the acquired knowledge needs to be both accurate and comprehensible. In this paper, we propose an efficient fuzzy rule generation algorithm based on fuzzy decision tree for data mining. We combine the comprehensibility of rules generated based on decision tree such as ID3 and C4.5 and the expressive power of fuzzy sets. Particularly, fuzzy rules allow us to effectively classify patterns of non-axis-parallel decision boundaries, which are difficult to do using attribute-based classification methods.In our algorithm we first determine an appropriate set of membership functions for each attribute of data using histogram analysis. Given a set of membership functions then we construct a fuzzy decision tree in a similar way to that of ID3 and C4.5. We also apply genetic algorithm to tune the initial set of membership functions. We have experimented our algorithm with several benchmark data sets including the IRIS data, the Wisconsin breast cancer data, and the credit screening data. The experiment results show that our method is more efficient in performance and comprehensibility of rules compared with other methods including C4.5.

• Journal of KIISE:Databases
• /
• v.33 no.5
• /
• pp.453-462
• /
• 2006

Discovering sequential patterns is an important problem for many applications. Existing algorithms find sequential patterns in the sense that only items are included in the patterns. However, for many applications, such as business and scientific applications, quantitative attributes are often recorded in the data, which are ignored by existing algorithms but can provide useful insight to the users. In this paper, we consider the problem of mining sequential patterns with quantities. We demonstrate that naive extensions to existing algorithms for sequential patterns are inefficient, as they may enumerate the search space blindly. Thus, we propose hash filtering and quantity sampling techniques that significantly improve the performance of the naive extensions. Experimental results confirm that compared with the naive extensions, these schemes not only improve the execution time substantially but also show better scalability for sequential patterns with quantities.

• Journal of KIISE:Databases
• /
• v.29 no.5
• /
• pp.335-346
• /
• 2002

LBS(Location Based Services) provide the location-based information to its mobile users. The primary functionality of these services is to provide useful information to its users at a minimum cost of resources. The functionality can be implemented through data mining techniques. However, conventional data mining researches have not been considered spatial and temporal aspects of data simultaneously. Therefore, these techniques are inappropriate to apply on the objects of LBS, which change spatial attributes over time. In this paper, we propose a new data mining technique for identifying the temporal patterns from the series of the locations of moving objects that have both temporal and spatial dimension. We use a spatial operation of contains to generalize the location of moving point and apply time constraints between the locations of a moving object to make a valid moving sequence. Finally, the spatio-temporal technique proposed in this paper is very practical approach in not only providing more useful knowledge to LBS, but also improving the quality of the services.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.730-740
• /
• 2006

In recent years, bullied students and rogue groups in teenagers make many serious social problems. In this paper we propose a novel approach that more objectively analyzes peer relationships among students. As the data for objective analysis, we use communication history records that are collected from various communication tools such as telephones, e-mails, and messengers. We use the simple intuition that communication history records implicitly contain peer relationship information. And, we adopt data mining techniques for the more systematic analysis. The proposed peer relationship analysis consists of the following steps. First, we formally define the notion of degree of familiarity between friends, and present mathematical equations that compute the degree based on communication history records. In the proposed method, we use the intuition that the degree of familiarity from student x to student y becomes higher as x makes the more communications with y. Second, by using the degree of familiarity between students, we find out the students who are potentially bullied. This procedure is based on the assumption that a bullied student may have a very small number of history records from other students to him. Third, we adopt the clustering technique, one of the most representative data mining techniques, to find out meaningful student groups by using the degree of familiarity. To use the clustering technique, we formally define the notion of similarity between friends based on the degree of familiarity, and perform clustering using the notion. Last, to show the practicality of the proposed method, we have implemented the method and interpreted the meaning of the experimental results. Overall, we believe that our research result provides an effective framework that analyzes peer relationships more objectively and more systematically.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.233-235
• /
• 2021

본 논문에서는 물 공급량 예측을 위한 다양한 알고리즘 적용에 있어서 데이터 마이닝의 효용성을 검토하고자 하였다. 물 공급분야에 있어서, 물 이용 지역의 특성에 따라 공급량과 이용 시간이 매우 상이한 특성을 나타낸다. 물 이용 지역은 주택지역, 상업지역, 산업단지지역 등 다양한 형태로 분류할 수 있고, 이에 따라 물 이용 시간의 상이함에 따른 물 공급패턴이 일정하지 않게 된다. 특히, 주택지역과 상업지역이 복합적으로 이루어진 경우, 물 이용 단위인 블록 단위에서의 물 특성이 불규칙적인 패턴을 나타낸다. 따라서, 각 블록 단위 특성에 적합한 물 이용량을 예측하여 효율적 물 공급 방안을 마련할 필요가 있다. 또한, 물 이용량 데이터 중 이상 데이타 감지와 이상 데이터 보정을 통하여 물 이용량 예측의 정확도가 향상된다. 따라서, 블록 단위의 물 이용량에 대한 원시데이타의 효율적인 데이터 마이닝 방안이 요구된다. 본 연구에서는 물 공급지역의 특성에 따른 물 공급 패턴을 분석하고, 이에 적합한 데이터 마이닝 기법을 제시하고 비교 분석하였다. 제안된 데이터 마이닝 기법은 딥러닝 예측모델을 적용하여 적합성을 검증하고, 이를 물 공급량 예측알고리즘에 폭넓게 활용될 수 있음을 확인하였다.