科研之友
微信
新浪微博
Facebook
分享链接
摘要
As the classification rules based on rough set cannot directly handle a decision table with many types of data attributes, a clustering-based artificial fish's rough set decision rules extraction method is proposed in this paper. By roughly classifying the attribute interval with the decision attributes and discretizing, reducing the classified attribute interval with the clustering behavior of artificial fish-swarm, the complexity of attribute reduction can be greatly diminished. The experimental results have shown that the proposed algorithm can lead to a set of more simplified decision rules.
