基于进化算法的图形数据模式发现  

Evolutionary Algorithm Based Pattern Discovery in Graphical Databases

作　　者：常新功[1,2] 李敏强[1] 寇纪淞[1] 

机构地区：[1]天津大学管理学院,天津300072 [2]山西财经大学信息管理学院,太原030006

出　　处：《模式识别与人工智能》2008年第1期116-121,共6页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金资助项目(No.70571057)

摘　　要：针对当前主流的图形数据挖掘算法常采用的贪婪式查找带来的易陷入局部最优这一问题,将进化算法引入图形数据挖掘.以增强算法的全局查找能力.定义基于图形数据的交叉和变异算子.考虑到进化算法局部搜索能力弱的特点,在变异算子的设计中融入爬山算法的思想,以进一步提高解的质量.另外还改进原算法针对某一特定子结构的实例收集方法.实验表明,以上措施增强系统对假设空间的查找能力,提高解的质量.The greedy search is often used in some existing prevalent graphical data mining systems which often ends up with sub-optimal solutions. To overcome its limits, an evolutionary algorithms based system is developed to perform data mining on databases represented as graphs. New operators of mutation and crossover on graphical databases are defined, and the way of collecting instances of a certain substructure is improved. In addition, a variant of hill-climbing is integrated into the design of mutation operator to improve the capability of local search of evolutionary algorithm, Experimental results show that these measures successfully improve the searching capability of the algorithm and the qualities of solutions.

关 键 词：进化算法(EA) 最小描述长度(MDL) 图形数据挖掘 模式发现 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] P208[自动化与计算机技术—控制科学与工程]