New Variable Precision Reduction Algorithm for Decision Tables

Variable precision reduction (VPR) and positive region (PRR) are common definitions in attribute reduction. The compacted decision table is an extension of a table. In this paper, we propose another extension, called the weighted both types tables, VPR defined, corresponding discernibility matrices for PRR proposed. Then, algorithms obtaining from presented. relationship between established by comparing matrices. If meets given conditions, then can be used to obtain results after modifying some values tables. An analysis modification process compression tables new algorithm that ensures credibility. effectiveness proposed was evaluated experimental comparison with existing algorithms.