Journal of Beijing University of Posts and Telecommunications

  • EI核心期刊

JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM

Previous Articles     Next Articles

Clustering Datasets Containing Clusters of Various Densities 

    

  1. Electronic Engineering School, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Supported by:
     

Abstract: The datasets for clustering usually contain clusters of various densities. Few clustering algorithms can handle such kind of datasets. Our algorithm strives to solve the problem in a multi-stage manner. It can discover clusters of different densities effectively. Besides, it can handle high-dimensional datasets and can cluster time-series datasets as well.

Key words: data mining, clustering, time series

CLC Number: