论文部分内容阅读
针对以往文献为克服基于差别矩阵的属性约简算法存储代价高的不足而提出的基于浓缩树(C-Tree)的高效属性约简算法仅考虑决策表不变的情况,提出了一种基于C-Tree的属性约简增量式更新算法,主要考虑对象动态增加情况下属性约简的更新问题.该算法可通过快速更新C-Tree,在动态求解核的基础上,利用原有的属性约简有效地进行属性约简的增量式更新.理论分析和实验结果表明,所提出的算法是有效可行的.
In order to overcome the shortcomings of high storage cost of attribute reduction algorithm based on discernibility matrix, the efficient attribute reduction algorithm based on C-Tree proposed by previous literatures only considers the situation of decision table unchanged, -Tree attribute reduction incremental update algorithm, the main consideration of the object attribute reduction under the dynamic increase of the update problem.This algorithm can quickly update the C-Tree, based on the dynamic solution of the kernel, the use of the original attribute reduction effective The incremental updating of attribute reduction is carried out.Theoretical analysis and experimental results show that the proposed algorithm is effective and feasible.