Earticle

초록

영어

Tree structures are used extensively in domains such as XML data management, web log analysis, biological computing, and so on. In this paper we introduce the problem of mining frequent sequential trees in a large tree sequence database. We present a framework for mining frequent sequential trees in a so-called tree sequence database. Basically, this framework employs a transformation-based approach which converts the sequential tree mining problem into a traditional sequence mining problem. Our approach firstly mines frequent trees in the tree sequence database. Secondly, we perform a database transformation by means of tree-containment computation to generate a sequence database. Thirdly, after the transformation, frequent sequence patterns can be mined in the newly created sequence database using a conventional sequence mining technique. Finally we perform an inverted transformation process on the output of sequence mining to obtain sequential tree patterns. Experimental results on synthetic datasets show that the proposed framework is both effective and efficient in finding frequent sequential trees in a large tree sequence database.

목차

Abstract
 1. Introduction
 2. Related work
 3. Problem Statement
  3.1. Rooted Ordered Tree
  3.2. Frequent Tree
  3.3. Tree Sequence Database
  3.4. Sequential Tree Mining Problem
 4. Framework of Sequential Tree Mining
  4.1. Tree Mining
  4.2. Database Transforming
  4.3. Sequence Mining
 5. Experimental Results
  5.1. Implementation and Experimental Setup
  5.2. Workload
  5.3. Mining Performance
 6. Conclusions
 Acknowledgements
 References

키워드

저자

• Yijun Bei [ College of Software Technology, Zhejiang University, China ]
• Zhen Lin [ College of Computer Science & Technology, Zhejiang University; Department of Computer Science, University of Illinois at Urbana - Champaign, USA ] Corresponding Author
• Qiyao Wang [ State Key Laboratory of Network and Switching Technology, Beijing University of Posts and Telecommunications, China ]
• Erteng Liu [ College of Software Technology, Zhejiang University, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Database Theory and Application

• 간기

  격월간

• pISSN

  2005-4270

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605