【摘要】 差别矩阵属性约简是粗糙集重要约简方法之一,但在处理不一致大数据集时存在不足。为此,首先提出决策差别集的概念,并给出基于决策差别集的属性约简定义,同时研究了由该定义获得的约简与正区域约简之间的等价性。接着,给出水平划分决策表的方法,并将子决策表分配到不同的网络节点上构建子决策差别集,并行完成核属性和属性约简求解。实例分析和UCI中数据集的实验比较表明所提出的约简算法是正确的、高效的。更多还原

【Abstract】 The notion of decision discernibility set and definition of attribute reduction based on decision discernibility set were presented. It was proved that attribute reduction acquired from the definition is equivalence to attribute reduction based on positive region. And then,the method of horizontally partitioning decision table was proposed and the sub-decision table can be assigned to different network nodes and finish computing core attribute and attribute reduction based on sub-decision discernibility set. Finally,the example analysis experiment results form datasets of UCI showed that the proposed parallel algorithms are efficient and effective.更多还原