Method of identifying robust clustering

A method of finding robust clusters comprises the use of principal component analysis and consensus ensemble clustering. In another aspect, the method may comprise normalizing a data set; identifying attributes of the data set that contribute to most of variation in the normalized data set; selectin...

Full description

Saved in:
Bibliographic Details
Main Authors Alexe, Gabriela, Bhanot, Gyan V, Royyuru, Ajay K
Format Patent
LanguageEnglish
Published 24.04.2012
Online AccessGet full text

Cover

More Information
Summary:A method of finding robust clusters comprises the use of principal component analysis and consensus ensemble clustering. In another aspect, the method may comprise normalizing a data set; identifying attributes of the data set that contribute to most of variation in the normalized data set; selecting data having the attributes that contribute to most of variation in the normalized data set; identifying a plurality of clusters from the selected data using consensus ensemble clustering; and identifying robust clusters from the plurality of clusters. The method can be used in healthcare and life science.