用遗传模拟退火算法挖掘特征项权重的研究  

Using Genetic-Simulated Annealing Algorithm to Find Attribute Weighting

作　　者：齐平[1] 贾瑞玉[2] 贾兆红[1] 王会颖[1] 

机构地区：[1]安徽大学计算机学院,安徽合肥230039 [2]安徽大学计算智能与信息处理教育部重点实验室,安徽合肥230039

出　　处：《计算机技术与发展》2007年第2期143-145,148,共4页Computer Technology and Development

基　　金：安徽省教育厅科研项目(2005kj0552005kj056)

摘　　要：能否在范例库中检索和选择出最为相似的范例决定了范例推理系统性能。文中介绍了遗传算法和模拟退火算法,比较了两种算法的特性,提出一种混合遗传模拟退火算法。该算法不但具有强的局部搜索能力,还缩短了搜索时间。将该算法用于发掘范例库上特征权重,理论分析和实验结果表明了这种混合遗传模拟退火算法优于普通的遗传算法。This article introduces two algorithms, genetic algorithm and simulated annealing algorithm, and puts forward one weighting method by using genetic - simulated annealing algorithm. This algorithm not only has the strong partial searching ability,moreover also reducers the .searching time. The theoretical analysis and experimental results show that this method has better performance than other methods, by using this algorithm to find the characteristic weighting of case base.

关 键 词：遗传算法 模拟退火算法 权重 范例推理 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]