A Rough-Apriori Technique in Mining Linguistic Association Rules

  • Authors:

  • Yun-Huoy Choo;Azuraliza Abu Bakar;Abdul Razak Hamdan

  • Affiliations:

  • Department of Science and System Management, Faculty of Information Science and Technology, National University of Malaysia, Bangi, Malaysia 43600;Department of Science and System Management, Faculty of Information Science and Technology, National University of Malaysia, Bangi, Malaysia 43600;Department of Science and System Management, Faculty of Information Science and Technology, National University of Malaysia, Bangi, Malaysia 43600

  • Venue:
  • ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper has proposed a rough-Apriori based mining technique in mining linguistic association rules focusing on the problem of capturing the numerical interval with linguistic terms in quantitative association rules mining. It uses the rough membership function to capture the linguistic interval before implementing the Apriori algorithm to mine interesting association rules. The performance of conventional quantitative association rules mining algorithm with Boolean reasoning as the discretization method was compared to the proposed technique and the fuzzy-based technique. Five UCI datasets were tested in the 10-fold cross validation experiment settings. The frequent itemsets discovery in the Apriori algorithm was constrained to five iterations comparing to maximum iterations. Results show that the proposed technique has performed comparatively well by generating more specific rules as compared to the other techniques.