Abstract
We address general-shaped clustering problems under very weak parametric assumptions with a two-step hybrid robust clustering algorithm based on trimmed k-means and hierarchical agglomeration. The algorithm has low computational complexity and effectively identifies the clusters also in the presence of data contamination. Its generalizations and an adaptive procedure to estimate the amount of contamination are also presented.
Type
Publication
Part of the Advances in Intelligent Systems and Computing book series
Luca Insolia
Postdoctoral Researcher
