Skip to content

csliangdu/clustering-ensemble

 
 

Repository files navigation

clustering-ensemble

To demonstrate: Removal of some negative information from co-association matrix may lead to improvement of the clustering ensemble performance.

  • RUN RemoveNegativeInfo.m to demonstrate the negative information removal on a dataset with three Gaussian clusters, please see Readme.pdf.

  • RUN CluEnsemble.m to cluster 8 synthetic datasets and 8 real datesets.

The project was tested in WIN7 (64bits) and MATLAB2012a.

Reference:

Caiming Zhong et al., Ensemble clustering based on evidence extracted from the co-association matrix, Pattern Recognition, Volume 92, August 2019, Pages 93-106

About

Removal of information from co-association matrix for clustering ensemble

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • MATLAB 84.8%
  • C++ 15.2%