Cluster analysis is an important data mining issue, where objects under investigation are grouped into subsets of the original set of objects. In recent several years, a few clustering algorithms have been developed for the data stream problem. However these algorithms lack of extensibility or efficiency. In this paper we propose a new evolving data streams system with data fusion. We discuss a fundamentally different philosophy for data stream clustering which is guided by application centered requirements. The system is highly suitable for real-time implementation and is demonstrated through a series of experiments. The experiments over a number of real and synthetic data sets illustrate the effectiveness and efficiency.
展开▼