An Improved Heuristic Algorithm Used in Attribute Reduction of Rough Set

The paper discusses the problem for attribute reduction based on rough set theory, and an improved heuristic algorithm for attribute reduction is presented based on generalized characteristic table. In the algorithm, generalized characteristic table is first simplified and the attribute core is obtained; the heuristic information is constructed subsequently according to the significance of condition attributes to make recursive calculation; the reduction results are obtained at last. The algorithm can be used in consistent and inconsistent decision table. The improved algorithm is proved to be more effective by analyzing the experimental results.