Evolutionary Approach to Automated Discovery of Censored Production Rules with Fuzzy Hierarchy.

The most predominant representation of the discovered knowledge is the standard Production Rules (PRs), in the form If P Then D. The PRs, however, are unable to handle exceptions and do not exhibit variable precision. The Censored Production Rules (CPRs), an extension of PRs, exhibit variable precision and supports an efficient mechanism for handling exceptions. As an extension of CPR, the Hierarchical Censored Production Rules (HCPRs) system of knowledge representation exhibits both variable certainty as well as variable specificity and offers mechanisms for handling the trade-off between two. This paper focuses on the issue of mining Censored Production Rules with Fuzzy Hierarchy (CPRFH) using evolutionary approach to knowledge discovery. A fuzzy subsumption relation and suitable fitness function are suggested for the proposed scheme. Appropriate genetic operators are proposed for the suggested encoding. Finally, CPRFH are generated from the discovered hierarchy in the form of HCPR: D_k If[P] Unless [C_Dk1v…v_Dk1v…] Generality [general class] Specificity [D_k1(d1),…,D_ki(di),…,D_kj(dj)], where P is the set of preconditions, the Unless element C_Dki is the i-th censor (exception condition) to the class D_k and the Specificity element D_ki(di) means that D_ki is a specific class of D_k with degree of subsumption di. Experimental results are presented to demonstrate the performance of the proposed scheme. [ABSTRACT FROM AUTHOR]