Uncertainty Measure of Covering Generated Rough Set

  • Authors:
  • Jun Hu;Guoyin Wang;Qinghua Zhang

  • Affiliations:
  • Xidian University, China/ Chongqing University of Posts and Telecommunications, China;Xidian University, China/ Chongqing University of Posts and Telecommunications, China;Chongqing University of Posts and Telecommunications, China

  • Venue:
  • WI-IATW '06 Proceedings of the 2006 IEEE/WIC/ACM international conference on Web Intelligence and Intelligent Agent Technology
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Uncertainty measure is a key issue of knowledge discovery based on covering approximation space. Information entropy was applied into both classical rough set and extended rough set to measure the uncertainty respectively, but their relationship has not been studied. Based on equal domain relation, a covering approximation space is converted into a partition approximation space in this paper, and uncertainty measures of covering generated rough set are developed. Their properties are analyzed with the generated partition approximation space fined, and these properties are still kept with the original covering approximation spacer fined.