Skip to the main content

Original scientific paper

https://doi.org/10.20532/cit.2016.1002745

Penguins Search Optimisation Algorithm for Association Rules Mining

Youcef Gheraibia ; Faculty of Science, Department of Computer Science and Mathematics, University of Mohammed Cherif Messaadia
Abdelouahab Moussaoui ; Department of Computer Science, University of Feraht Abaas
Youcef Djenouri orcid id orcid.org/0000-0003-0135-7450 ; Computer Science Department, Saad Dahlab University
Sohag Kabir ; 4 Department of Computer Science, University of Hull, Hull, UK
Peng Yeng Yin ; Department of Information Management, National Chi Nan University, Puli, Taiwan


Full text: english pdf 805 Kb

page 165-179

downloads: 801

cite


Abstract

Association Rules Mining (ARM) is one of the most popular and well-known approaches for the decision-making process. All existing ARM algorithms are time consuming and generate a very large number of association rules with high overlapping. To deal with this issue, we propose a new ARM approach based on penguins search optimisation algorithm (Pe-ARM for short). Moreover, an efficient measure is incorporated into the main process to evaluate the amount of overlapping among the generated rules. The proposed approach also ensures a good diversification over the whole solutions space. To demonstrate the effectiveness of the proposed approach, several experiments have been carried out on different datasets and specifically on the biological ones. The results reveal that the proposed approach outperforms the well-known ARM algorithms in both execution time and solution quality.

Keywords

association rules mining; penguins search optimisation algorithm; overlap measure; biological data-set; ARM

Hrčak ID:

161745

URI

https://hrcak.srce.hr/161745

Publication date:

30.6.2016.

Visits: 1.799 *