Adaptive core fusion-based density peak clustering for complex data with arbitrary shapes and densities

作者：

Highlights：

• An adaptive clustering based on density peaks and core fusion is proposed for clustering complex data.

• Core points are found efficiently and adaptively based on the density distribution of data points without setting density thresholds.

• A within-cluster similarity-based fusion strategy is proposed to guarantee meaningful clustering.

• The high performance of ACDPCF is verified on several benchmark complex datasets with diverse shapes and densities.

摘要

•An adaptive clustering based on density peaks and core fusion is proposed for clustering complex data.•Core points are found efficiently and adaptively based on the density distribution of data points without setting density thresholds.•A within-cluster similarity-based fusion strategy is proposed to guarantee meaningful clustering.•The high performance of ACDPCF is verified on several benchmark complex datasets with diverse shapes and densities.

论文关键词：Clustering,Density peak,Core fusion,Arbitrary shape,Arbitrary density

论文评审过程：Received 12 October 2019, Revised 14 March 2020, Accepted 13 May 2020, Available online 2 June 2020, Version of Record 12 June 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107452