摘要
数据挖掘是指在数据库中发现潜在的、人们感兴趣的关系及特征。聚类的任务是根据一定的标准将数据分组。最常用的一种启发式算法是“爬山法”,这种方法可以保证获得局部最优。遗传算法是一种寻求全局最优的优化技术。本文将遗传算法同“爬山法”结合提出了一种混合遗传算法。
Data mining is the discovery of interesting relationships and characteristics that may exist implicitly in large databases. Clustering is the task of identifying groups in a data set based on some criteria of similarity. The most common heuristics are a form of ＂hill-climbing＂ that guarantees local optimality. However, this is a domain where objective function has many local optima and where genetic algorithms may probe to be capable of producing superior solutions. Therefore, we implemented the hybrid genetic algorithm-a combination of the two.
出处
《微计算机信息》
北大核心
2006年第06X期219-221,共3页
Control & Automation
基金
国家科技成果重点推广项目(2003EC000001)
关键词
数据挖掘
混合遗传算法
爬山法
Data Mining,Hybrid Genetic Algorithm, ＂Hill-climbing＂
