论文部分内容阅读
目前的增量式核属性更新算法大多建立在可分辨矩阵的基础上,不利于大数据集处理,而且算法的效率也不理想.为了克服上述不足,在改进的基于冲突域求核算法的基础上,提出了基于冲突的增量式核属性求解算法.该算法不需要创建可分辨矩阵,当有新对象加入时,对决策表仅需进行一次遍历便可完成核属性增量更新.算法的时间和空间复杂度分别为O(|C‖U′|)和O(|C|).理论分析和实验结果均表明,所提出的算法是可行且高效的.
The current incremental kernel attribute update algorithms are mostly based on the discernable matrix, which is not conducive to large data sets processing, and the efficiency of the algorithm is not ideal.In order to overcome these shortcomings, based on the improved algorithm , This paper proposes a conflict-based incremental kernel attribute solving algorithm which does not need to create a discernable matrix. When a new object is added, it only needs to traverse the decision table once to complete the incremental updating of kernel attributes. The time and space complexity are O (| C || U |) and O (| C |) respectively.Theoretical analysis and experimental results show that the proposed algorithm is feasible and efficient.