Selected Contributions in Data Analysis and Classification

Part of the series Studies in Classification, Data Analysis, and Knowledge Organization pp 225-233

Hybrid k-Means: Combining Regression-Wise and Centroid-Based Criteria for QSAR

  • Robert StanforthAffiliated withID Business SolutionsSchool of Computer Science, Birkbeck, University of London
  • , Evgueni KolossovAffiliated withID Business Solutions
  • , Boris MirkinAffiliated withSchool of Computer Science, Birkbeck, University of London

* Final gross prices may vary according to local VAT.

Get Access


This paper further extends the ‘kernel’-based approach to clustering proposed by E. Diday in early 70s. According to this approach, a cluster’s centroid can be represented by parameters of any analytical model, such as linear regression equation, built over the cluster. We address the problem of producing regression-wise clusters to be separated in the input variable space by building a hybrid clustering criterion that combines the regression-wise clustering criterion with the conventional centroid-based one.