论文部分内容阅读
值约简是Rough集理论研究的一个重要内容,目前已有的算法很难快速处理大数据集.文中通过在属性空间上对论域对象的分解,提出一种基于分治法的快速确定规则获取算法,并给出实例说明.该算法可直接从离散的决策表获取确定决策规则,在数据服从均匀分布的条件下,算法的时间复杂度低于n2,适合大数据集的确定规则获取.实验结果说明算法的高效性.
Value reduction is an important part of Rough set theory research, and it is difficult to deal with big data set quickly with the existing algorithms.Through the decomposition of domain objects in attribute space, this paper proposes a fast decision rule based on divide and conquer The algorithm is given and the example is given. The algorithm can obtain the decision rules directly from the discrete decision table. Under the condition of uniform distribution of the data, the algorithm has the time complexity less than n2, which is suitable for the determination of large data sets. Experimental results show that the algorithm is efficient.