Quick Complete Attribute Reduction Algorithm
Chuanjian Yang, Hao Ge, Guangshun Yao, Lisheng Ma · 2009
To improve the efficiency of attribute reduction and obtain the minimal attribute reduction, the notion of consistent simplified decision table is proposed. The concentrated discernibility set is created in the consistent simplified decision table, and an algorithm of completeness attribute reduction based on concentrated discernibility set is put forward. The least information of attribute reduction is withheld in concentrated the discernibility set, so the efficiency of the algorithm is improved. In addition, the heuristic method is used to select the deleted attribute, which better ensure to acquire the minimal reduction. The experimental results show that the algorithm is correct and effective.