摘要
数据分类是数据挖掘中的一个重要课题,研究各种高效的分类算法是数据挖掘的重要问题之一。本文将蚁群算法与分类规则抽取问题相结合,提出了一种基于蚁群算法的具有自适应和变异杂交特征的分类规则挖掘方法,自适应地调整信息素增量,在规则构造中进行杂交变异,有效地节省了计算时间,并优化了生成的分类规则。实验结果表明:该算法可以有效克服停滞,提高搜索效率,有效地挖掘出简洁分类规则。
Data classification is an important task of data mining, and developing high-powered classification algorithm is one of the key problems for data mining. This paper combines the Ant Colony Algorithm with the classification rule mining problem, and puts forward an ant colony algorithm with adaptive crossover features, updates the pheromone adaptively, and processes the mutation and crossover operator, which saves the computing time effectively, and can discover better classification rule. Experiment results demonstrate that stagnation can be effectively overcome and searching efficiency is also improved, and succinct rules are discovered.
出处
《农业网络信息》
2007年第10期13-15,共3页
Agriculture Network Information
基金
河南省自然科学基金(0624010002)
关键词
数据挖掘
分类规则
蚁群算法
Data mining
Classification rules
Ant colony algorithm
