Monotonic variable consistency rough set approaches

  • Authors:

  • Jerzy Błaszczyński;Salvatore Greco;Roman Słowiński;Marcin Szeląg

  • Affiliations:

  • Institute of Computing Science, Poznan University of Technology, Poznan, Poland;Faculty of Economics, University of Catania, Catania, Italy;Institute of Computing Science, Poznan University of Technology, Poznan, Poland and Institute for Systems Research, Polish Academy of Sciences, Warsaw, Poland;Institute of Computing Science, Poznan University of Technology, Poznan, Poland

  • Venue:
  • RSKT'07 Proceedings of the 2nd international conference on Rough sets and knowledge technology
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

We consider new definitions of Variable Consistency Rough Set Approaches that employ monotonic measures of membership to the approximated set. The monotonicity is understood with respect to the set of considered attributes. This kind of monotonicity is related to the monotonicity of the quality of approximation, considered among basic properties of rough sets. Measures that were employed by approaches proposed so far lack this property. New monotonic measures are considered in two contexts. In the first context, we define Variable Consistency Indiscernibility-based Rough Set Approach (VC-IRSA). In the second context, new measures are applied to Variable Consistency Dominance-based Rough Set Approaches (VC-DRSA). Properties of new definitions are investigated and compared to previously proposed Variable Precision Rough Set (VPRS) model, Rough Bayesian (RB) model and VC-DRSA.