A Rough-Set-based Clustering Algorithm for Multi-stream

The paper propose a rough-set-based clustering algorithm for multiple data stream, which solve the problem that existing clustering algorithm for multiple data streams can not take into account conflicts between clustering quality and efficiency. Firstly, the algorithm calculates the distance between data stream to determine the initial equivalence relations, and calculates the similarity between the initial equivalence relation to determine the initial cluster. In the second place, the similarity between the initial clusters is used to merge the initial clusters. Finally, k-means clustering algorithm is called to dynamically adjust the clustering results, and then real-time clustering structure is obtained. In conclusion Experimental results demonstrated that the algorithm has higher efficiency and clustering quality. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of [CEIS 2011]