Skip to main navigation Skip to search Skip to main content

Mining and updating association rules based on fuzzy concept lattice

  • Caifeng Zou
  • , Huifang Deng
  • , Jiafu Wan*
  • , Zhongren Wang
  • , Pan Deng
  • *Corresponding author for this work
  • South China University of Technology
  • Guangdong Mechanical and Electrical College
  • Hubei University of Arts and Science
  • Peking University
  • Beijing Institute of Big Data Research

Research output: Contribution to journalArticlepeer-review

Abstract

An algorithm for mining and updating association rules based on fuzzy concept lattice is proposed. When a new attribute is added into the fuzzy concept lattice, it is not necessary to calculate all the frequent nodes and association rules. According to the incremental construction algorithm of fuzzy concept lattice, it is only necessary to deal with the new nodes that have changed. Therefore, the amount of calculation is reduced. The existing incremental construction algorithm of precise concept lattices based on attributes is extended so that it can be applied to fuzzy concept lattices. The pruning technology is used to improve the construction algorithm. The steps for generating and updating association rules are added. According to the extended algorithm, the fuzzy concept lattice can be constructed, and the corresponding association rules can be generated and updated at the same time. The experimental results show that the algorithm proposed in this paper greatly reduces the computational workload, and shortens the running time.

Original languageEnglish
Pages (from-to)698-706
Number of pages9
JournalFuture Generation Computer Systems
Volume82
DOIs
StatePublished - May 2018
Externally publishedYes

Keywords

  • Association rule
  • Construction algorithm
  • Data mining
  • Fuzzy concept lattice

Fingerprint

Dive into the research topics of 'Mining and updating association rules based on fuzzy concept lattice'. Together they form a unique fingerprint.

Cite this