摘要
新的基于网格聚类算法(GCAB)利用网格处理技术对数据进行了预处理,并引进了网格密度阈值处理和网格中心点两种技术.实验表明,GCAB算法不仅具有DBSCAN算法准确挖掘各种形状的聚类和很好的噪声处理能力的优点,而且具有较高聚类速度.
This paper presents a new grid-based clustering algorithm to preprocess the data using grid processing method. It’s disposed of density threshold of grid by density threshold method and improved the efficiency by the use of the grid center. The result of the experiments demonstrate that GCAB is as accurate in discovering density-changeable clustering and handling of noise as DBSCAN, but GCAB has higher clustering speed.
出处
《西南民族大学学报（自然科学版）》
CAS
2009年第3期635-637,共3页
Journal of Southwest Minzu University(Natural Science Edition)
基金
四川省教育厅青年项目(2006B095)
关键词
聚类
网格
数据挖掘
密度阈值
中心点
clustering
grid
data mining (DM)
density threshold
center
