Tracking High Quality Clusters over Uncertain Data Streams

Recently, data mining over uncertain data streams has attracted a lot of attentions because of the widely existed imprecise data generated from a variety of streaming applications. In this paper, we try to resolve the problem of clustering over uncertain data streams. Facing uncertain tuples with different probability distributions, the clustering algorithm should not only consider the tuple value but also emphasis on its uncertainty. To fulfill these dual purposes, a metric named tuple uncertainty will be integrated into the overall procedure of clustering. Firstly, we survey uncertain data model and propose our uncertainty measurement and corresponding properties. Secondly, based on such uncertainty quantification method, we provide a two phase stream clustering algorithm and elaborate implementation detail. Finally, performance experiments over a number of real and synthetic data sets demonstrate the effectiveness and efficiency of our method.

• Type: Conference
• Year: 2009
• Where: ICDE
• Authors: Chen Zhang, Ming Gao, Aoying Zhou
• Keywords: Database, ICDE 2009, Stream Clustering Algorithm, Synthetic Data Sets, Uncertain Data Model, Uncertain Data Streams, Uncertainty Quantification Method