可调节多粒度粗糙集的细化与粗化

Refining or Coarsening Attribute Values in Adjustable Multigranulation Rough Set

在经典的多粒度粗糙集模型中,属性值细化和粗化后的下近似、上近似变化并不明显,因此在处理实际问题时存在一定局限性。该文首先构造了属性值细化和粗化时的可调节多粒度粗糙集,讨论了可调节多粒度粗糙集下、上近似的一些性质,并设计了相应的增量算法。最后在实验部分中,通过调节数据集、属性集的大小对增量算法和原有的静态算法的计算时间进行比较。实验结果表明提出的可调节多粒度粗糙集在细化和粗化时的增量算法可以更加准确、高效地处理大型数据。

In the classical multigranulation rough set model,the change of upper and lower approximations after attribute values refining and coarsening are not obvious,so there are some limitations in dealing with practical problems.In this paper,the authors first construct the adjustable multigranulation rough set when the attribute values are refined and coarsened,discuss some properties of the upper and lower approximations of the adjustable multigranulation rough set,and design the corresponding incremental algorithm.Finally,in the experimental section,the calculation times of the incremental algorithm and the original static algorithm are compared by adjusting the sizes of the dataset and attribute set.The results demonstrate that the proposed incremental algorithm for adjustable multigranulation rough sets in refining and coarsening are more effective and accurate when handling large data.