• The Journal of the Korea Contents Association
• /
• v.11 no.1
• /
• pp.56-64
• /
• 2011

It is difficult to discover frequent itemsets based on whole data from data stream since data stream has the characteristics of infinity and continuity. Therefore, a specialized data mining method, which reflects the properties of data and the requirement of users, is required. In this paper, we propose the method of FIMWB discovering the frequent itemsets which are reflecting the property that the recent events are more important than old events. Data stream is splitted into batches according to the given time interval. Our method gives a weighted value to each batch. It reflects user's interestedness for recent events. FP-Digraph discovers the frequent itemsets by using the result of FIMWB. Experimental result shows that FIMWB can reduce the generation of useless items and FP-Digraph method shows that it is suitable for real-time environment in comparison to a method based on a tree(FP-Tree).

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.100-102
• /
• 2002

데이터 마이닝의 대표적인 기법인 연관규칙 마이닝을 위한 다양만 알고리즘들이 제안되었고, 각 알고리즘에 따른 대용량 데이터에 대한 신속한 탐색을 위한 독특한 자료구조가 제안되었다 각 자료구조의 특성에 따른 알고리즘 성능은 데이터의 패턴에 크게 의존한다. 본 논문에서는 Concept을 형성하는 세가지 대표적인 자료구조인 Hash Tree, Lattice. FP-Tree에 대해 비교 분석해보고, 데이터 패턴에 적합한 효율적인 알고리즘의 설계 위한 framework을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.727-728
• /
• 2009

최근 컴퓨터와 인터넷의 발달로 과거 창구거래를 이용하던 방법에서 HTS(Home Trading System)을 이용하여 거래하게 됨으로써 개인투자자들도 쉽게 주식투자를 할 수 있게 되었다. 그러나 개인들이 방대한 양의 과거 데이터를 분석하기에는 상당한 어려움이 있다. 본 논문에서는 주식 데이터베이스로부터 과거 특정 종목들 간 연관성을 추출하여 투자자들로 하여금 주식 선별에 참고가 될 수 있는 방안에 관하여 논의한다. 기존의 논문에서 제안된 과거 패턴을 이용하여 미래의 주가변화를 예측하는 것과 달리, 종목들 간에 연관성을 통하여 하나의 테마가 형성 되었을 때 주도주의 변화로 관련주의 변화를 파악하여 투자에 유익한 정보를 제공하는데 목적이 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.233-236
• /
• 2008

최근 컴퓨터와 통신의 기술이 빠르게 발달함에 따라 사회 각 부분은 그동안 경험하지 못했던 정보화라는 새로운 변화를 겪었다. 그 결과 정보화 수준이 점점 고도화 될수록 더욱 다양하고 방대한 데이터가 생성되어 데이터베이스를 이루게 되었다. 방대한 데이터에서 유용한 정보를 얻는 데이터마이닝 기법이 중요한 문제로 대두되었다. 데이터마이닝 기법은 점점 더 많은 분야에서 합리적인 선택을 위해 필수적으로 사용된다. 본 논문은 마이닝 기법을 적용하여 방대한 데이터베이스가 최적의 여행 경로 선택을 제공한다. 본 논문은 빈발 패턴 증가 기법에 가중치를 두어 여행자가 여행지를 선별하기 좋은 환경을 제공한다. 미래 산업 중 가장 중요한 산업 중 하나인 관광 산업은 계속적으로 성장하고 있으며 논문에서 제시하는 데이터 마이닝 기법으로 더 큰 발전을 기대한다.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.1
• /
• pp.105-115
• /
• 2007

Data mining extracts interesting knowledge from a large database. Among numerous data mining techniques, research work is primarily concentrated on clustering and association rules. The clustering technique of the active research topics mainly deals with analyzing spatial and attribute data. And, the technique of association rules deals with identifying frequent patterns. There was an advanced apriori algorithm using an existing bit-clustering algorithm. In an effort to identify an alternative algorithm to improve apriori, we investigated FP-Growth and discussed the possibility of adopting bit-clustering as the alternative method to solve the problems with FP-Growth. FP-Growth using bit-clustering demonstrated better performance than the existing method. We used chess data in our experiments. Chess data were used in the pattern mining evaluation. We made a creation of FP-Tree with different minimum support values. In the case of high minimum support values, similar results that the existing techniques demonstrated were obtained. In other cases, however, the performance of the technique proposed in this paper showed better results in comparison with the existing technique. As a result, the technique proposed in this paper was considered to lead to higher performance. In addition, the method to apply bit-clustering to GML data was proposed.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.451-464
• /
• 2016

Nowadays, entity search such as Google Product Search and Yahoo Pipes has been in the spotlight. The entity search engines have been used to retrieve web pages relevant with a particular entity. However, if an entity (e.g., Chinatown movie) has various meanings (e.g., Chinatown movies, Chinatown restaurants, and Incheon Chinatown), then the accuracy of the search result will be decreased significantly. To address this problem, in this article, we propose a novel method that quantifies the importance of search queries and then offers the best query for the entity search, based on Frequent Pattern (FP)-Tree, considering the correlation between the entity relevance and the frequency of web pages. According to the experimental results presented in this paper, the proposed method (59% in the average precision) improved the accuracy five times, compared to the traditional query terms (less than 10% in the average precision).

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.19-25
• /
• 2020

In frequent pattern mining, the uncertainty of each item is accompanied by a loss of information. AAlso, in real environment, the importance of patterns changes with time, so fuzzy logic must be applied to meet these requirements and the dynamic characteristics of the importance of patterns should be considered. In this paper, we propose a fuzzy utility mining technique for extracting frequent web page sets from web log databases through fuzzy utility-based web page set mining. Here, the downward closure characteristic of the fuzzy set is applied to remove a large space by the minimum fuzzy utility threshold (MFUT)and the user-defined percentile(UDP). Extensive performance analyses show that our algorithm is very efficient and scalable for Fuzzy Utility Mining using dynamic weights.

• Korean Journal of Computational Design and Engineering
• /
• v.18 no.4
• /
• pp.250-257
• /
• 2013

This paper introduces a failure analysis procedure that underpins real-time fault prognosis. In the previous study, we developed a systematic eventization procedure which makes it possible to reduce the original data size into a manageable one in the form of event logs and eventually to extract failure patterns efficiently from the reduced data. Failure patterns are then extracted in the form of event sequences by sequence-mining algorithms, (e.g. FP-Tree algorithm). Extracted patterns are stored in a failure pattern library, and eventually, we use the stored failure pattern information to predict potential failures. The two practical case studies (marine diesel engine and SIRIUS-II car engine) provide empirical support for the performance of the proposed failure analysis procedure. This procedure can be easily extended for wide application fields of failure analysis such as vehicle and machine diagnostics. Furthermore, it can be applied to human health monitoring & prognosis, so that human body signals could be efficiently analyzed.