Detecting implicit meta-patterns in relational databases

James P. Buckley, Jennifer M. Seitzer

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Association rule mining identifies patterns in transaction data that are not explicit. In the area of Knowledge Representation, cycle mining algorithms identify metapatterns of these associations depicting inferences forming feedback chains of positive and negative rule dependencies. This paper presents a new algorithm applying the traditional formalism of association rule mining to the new domain of cycle mining. We use this algorithm, along with causal graphs, to detect cycles.

Original languageEnglish
Title of host publicationIMCIC 2010 - International Multi-Conference on Complexity, Informatics and Cybernetics, Proceedings
EditorsJorge Baralt, Michael J. Savoie, Hsing-Wei Chu, C. Dale Zinn, Nagib C. Callaos
PublisherInternational Institute of Informatics and Systemics, IIIS
Pages162-164
Number of pages3
ISBN (Electronic)9781934272916
Publication statusPublished - 2010
Externally publishedYes
EventInternational Multi-Conference on Complexity, Informatics and Cybernetics, IMCIC 2010 - Orlando, United States
Duration: 6 Apr 20109 Apr 2010

Publication series

NameIMCIC 2010 - International Multi-Conference on Complexity, Informatics and Cybernetics, Proceedings
Volume1

Conference

ConferenceInternational Multi-Conference on Complexity, Informatics and Cybernetics, IMCIC 2010
Country/TerritoryUnited States
CityOrlando
Period6/04/109/04/10

Keywords

  • Association rules
  • Casual graphs
  • Cycle mining
  • Data mining
  • Hypergraphs
  • Knowledge base

Fingerprint

Dive into the research topics of 'Detecting implicit meta-patterns in relational databases'. Together they form a unique fingerprint.

Cite this