Abstract: Attribute reduction is the most important technique of rough set. Once it gets whole reductions, the reasoning capability under multi attribute absent can behave well. How to get whole reductions based on reduction’s concept is discussed. After getting rough reduction by pruning, and whole really reductions with back elimination, reduction pruning and discernibility matrix based heuristic reduction algorithm are compared. The experimental results show reduction-pruning algorithm is effective.

Key words: rough set, reduction pruning, back elimination

摘要： 属性约简是粗糙集中重要的技术，只有求出知识系统的所有约简，才能更好地适应在多属性缺失下的推理。该文从属性约简出发，对候选约简进行剪枝，得到了粗约简，并进行反向消除，得到一个知识系统的所有约简，并比较了约简剪枝算法与启发式约简算法。实验证明，约简剪枝算法是有效的。

关键词: 粗糙集, 约简剪枝, 反向消除

CLC Number: 

• TP181