A new attribute reduction algorithm in inconsistent decision information systems

This paper mainly deals with attribute reductions of inconsistent decision information system. In inconsistent decision system, improper selection of rules may lead to lose useful information. A new attribute reduction algorithm is proposed in this paper. By using this method, inconsistent rules are eliminated without affecting the useful information. It is a useful method to deal with small sample problem. The performance of the proposed method is compared with the conventional methods. The results indicate our method can include the result of the conventional methods. And the experiment results show the validity of the method.