Centroid index: Cluster level similarity measure

作者：

Highlights：

• Cluster level similarity measure.

• The measure is intuitive, simple to implement and fast to compute.

• Invariant to model mismatch.

• Expected to generalize other clustering models beyond the centroid-based k-means.

摘要

•Cluster level similarity measure.•The measure is intuitive, simple to implement and fast to compute.•Invariant to model mismatch.•Expected to generalize other clustering models beyond the centroid-based k-means.

论文关键词：Clustering,k-Means,External validity,Similarity measure

论文评审过程：Received 8 May 2013, Revised 25 November 2013, Accepted 18 March 2014, Available online 29 March 2014.

论文官网地址：https://doi.org/10.1016/j.patcog.2014.03.017