基于属性频度进化的粗糙集属性约简方法  

Attribute Reduction Method of Rough Set Based on Evolvement of Attribute Frequency

作　　者：马疵飞[1] 马航飞[1] 

机构地区：[1]福建经济管理干部学院信息管理系,福建福州350002

出　　处：《通化师范学院学报》2008年第10期17-20,23,共5页Journal of Tonghua Normal University

摘　　要：提出了基于遗传算法的知识相对约简算法,它以条件属性在差别矩阵中出现的频率为启发信息,以决策表的属性核来初始化传统遗传算法的种群,加强了遗传算法的搜索、缩短了计算时间;提出了修正校验算法,提高决策表属性约简的正确性.通过实例分析,证明是求解知识约简的有效方法.A kind of knowledge relative reduction algorithm based on GA was rithm employs appearing frequency of condition feature in differential matrix as heuristic information, and uses the attribute core of decision table as a restriction to improve the binary code initial population which is produced stochastically in the traditional genetic algorithm. This improvement can strengthen the local search ability of genetic algorithm, shorten the calculation time of the algorithm, the algorithm increases a correction operator to raise the accuracy of the results of the attribute reduction in decision tables. The practical results showed that the approach was effective in solving knowledge reduction.

关 键 词：粗糙集 差别矩阵 遗传算法 启发式修正 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]