By Topic

HClustream: A Novel Approach for Clustering Evolving Heterogeneous Data Stream

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Chunyu Yang ; Dept. of Autom., Tsinghua Univ., Beijing ; Jie Zhou

Recently, the continuously arriving and evolving data stream has become a common phenomenon in many fields, such as sensor networks, Web click stream and Internet traffic flow. One of the most important mining tasks is clustering. Clustering has attracted extensive research by both the community of machine learning and data mining. Many stream clustering methods have been proposed. These methods have proven to be efficient on specific problems. However, most of these methods are on continuous clustering and few of them are about to solve the heterogeneous clustering problems. In this paper, we propose a novel approach based on the CluStream framework for clustering data stream with heterogeneous features. The centroid of continuous attributes and the histogram of the discrete attributes are used to represent the micro clusters, and k-prototype clustering algorithm is used to create the micro clusters and macro clusters. Experimental results on both synthetic and real data sets show its efficiency

Published in:

Data Mining Workshops, 2006. ICDM Workshops 2006. Sixth IEEE International Conference on

Date of Conference:

Dec. 2006