论文信息 - Rule Quality Measures in Creation and Reduction of Data Rule Models

Rule Quality Measures in Creation and Reduction of Data Rule Models

Properties of several rule quality measures are characterized in the paper. Possibilities of their application in algorithms of rules induction and reduction are presented. Influence of replacing rules accuracy with the Bayesian confirmation measure has been tested.

Marek Sikora | M. Sikora

[1] Z. Pawlak. Rough Sets: Theoretical Aspects of Reasoning about Data , 1991 .

[2] Salvatore Greco,et al. Rough Membership and Bayesian Confirmation Measures for Parameterized Rough Sets , 2005, RSFDGrC.

[3] Zdzisław Pawlak,et al. Can Bayesian confirmation measures be useful for rough set decision rules? , 2004, Eng. Appl. Artif. Intell..

[4] Nick Cercone,et al. Rule Quality Measures for Rule Induction Systems: Description and Evaluation , 2001, Comput. Intell..

[5] Andrzej Skowron,et al. A rough set-based knowledge discovery process , 2001 .

[6] Kenneth A. Kaufman,et al. Learning in an Inconsistent World: Rule Selection in AQ18 , 1999 .

[7] Jerzy W. Grzymala-Busse,et al. LERS-A System for Learning from Examples Based on Rough Sets , 1992, Intelligent Decision Support.

[8] Andrzej Skowron,et al. Tolerance Approximation Spaces , 1996, Fundam. Informaticae.

[9] Roberto J. Bayardo,et al. Mining the most interesting rules , 1999, KDD '99.

[10] Jan Komorowski,et al. Taming Large Rule Models in Rough Set Approaches , 1999, PKDD.

[11] Marek Sikora,et al. An algorithm for generalization of decision rules by joining , 2005 .