摘要
离群挖掘是数据挖掘研究的重要内容,在实际生活中获得广泛应用。该文首先给出了离群数据的量化定义,并用基于蚁群的聚类学习方法,产生了状态空间的整体特征。然后结合具体的设备对象,提出了离群数据的挖掘方法。最后进行了实验验证,结果表明该文提出的方法是有效的。
Outlier mining is an important issue in data mining community.It was applied widely in practice.A quantitative definition is proposed at the beginning of this paper.The integral character of the state space is created using the clustering method based on ant colony.And a method of mining outlier is put forward according to the practical device.At the end,an experiment has been done and the result proves the effectiveness of the method.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第9期12-13,37,共3页
Computer Engineering and Applications
关键词
离群数据
数据挖掘
蚁群
聚类
outlier mining,data mining,ant colony,clustering
