Density-based clustering algorithm for mixture data sets
WU Tian-hong · Kongzhi yu juece · 2010
Data stream clustering analysis is a hot issue in present research of data mining. A density based data stream clustering algorithm is designed for mixed-attribute data sets. To avoid the shortcoming that CluStream algorithm is not capable enough to handle mixed numerical and categorical data,a data stream cluster algorithm named MCStream is presented by using the idea of dimension-oriented distance. The simulation results show that the proposed algorithm can cluster the mixed-attribute data stream efficiently and quickly.