Publication Details

Multi-level Sequence Mining Based on GSP

ŠEBEK, M.; HLOSTA, M.; KUPČÍK, J.; ZENDULKA, J.; HRUŠKA, T. Multi-level Sequence Mining Based on GSP. Acta Electrotechnica et Informatica, 2012, vol. 2012, no. 2, p. 31-38. ISSN: 1335-8243.
Czech title
Dolování víceúrovňových sekvenčních vzorů založené na GSP
Type
journal article
Language
English
Authors
Šebek Michal, Ing., Ph.D.
Hlosta Martin, Ing., Ph.D.
Kupčík Jan, Ing.
Zendulka Jaroslav, doc. Ing., CSc. (UIFS)
Hruška Tomáš, prof. Ing., CSc. (DIFS)
Keywords

multi-level sequence pattern mining, GSP, taxonomy

Abstract

Mining sequential patterns is an important problem in the field of data mining and many algorithms and optimization techniques have been published to deal with that problem. The GSP algorithm, which is one of them, can be used for mining sequential patterns with some additional constraints. In this paper, we propose a new algorithm for mining multi-level sequential patterns based on GSP. The idea is that if a more general item appears in a pattern, the pattern has higher or at least the same support as the one containing the corresponding specific item. However, too generalized sequence patterns are not important for user. In our algorithm generalization uses a selective method based on information content of patterns. This allows us to mine more patterns with the same minimal support threshold and to reveal new potentially useful patterns.

Published
2012
Pages
31–38
Journal
Acta Electrotechnica et Informatica, vol. 2012, no. 2, ISSN 1335-8243
DOI
10.2478/v10198-012-0012-8
BibTeX 
@article{BUT96928,
  author="Michal {Šebek} and Martin {Hlosta} and Jan {Kupčík} and Jaroslav {Zendulka} and Tomáš {Hruška}",
  title="Multi-level Sequence Mining Based on GSP",
  journal="Acta Electrotechnica et Informatica",
  year="2012",
  volume="2012",
  number="2",
  pages="31--38",
  doi="10.2478/v10198-012-0012-8",
  issn="1335-8243",
  url="https://www.fit.vut.cz/research/publication/9874/"
}
Back to top