基于代价敏感和近似分类质量的决策粗糙集属性约简研究

针对决策粗糙集属性约简在引入代价后分类精度不高的问题，对其中代价敏感与分类精度的平衡进行了研究。将分类总代价和近似分类质量作为属性约简过程中的约束条件，结合模拟退火方法，提出了一个基于代价敏感和近似分类质量的决策粗糙集属性约简（ARACOQ）算法。利用UCI数据集对算法进行了模拟实验，实验结果验证了ARACOQ算法的有效性，该算法能够在可承受代价范围内找到一个分类精度最高的属性约简集。

Study on DTRS attribute reduction constrained by cost-sensitive and classification quality

Aiming at the low precision problem while the cost is introduced into attribute reduction of decision-theoretic rough set, it is studied the balance between the total cost and the precision in classification. The total cost of the classification and the approximate classification quality are used as the constrained criteria in the attribute reduction procedure, combined with simulated annealing method, it is proposed a DTRS attribute reduction algorithm constrained by cost-sensitive and classification quality (hereinafter referred as ARACOQ) . The simulation experiments are carried out by using UCI data set, the results verify the effectiveness of the ARACOQ algorithm, it can find an attribute reduction set with the highest classification precision within the affordable cost range.