Density peak clustering based on relative density relationship

作者：

Highlights：

• We find out the reason behind two major problems afflicting the density peak clustering algorithm.

• We introduce the concept of subordinate to describe the relative density relationship.

• We propose a subordinate based criterion to solve the two problems.

• Experiments and comparisons demonstrate the effect of our approach.

摘要

•We find out the reason behind two major problems afflicting the density peak clustering algorithm.•We introduce the concept of subordinate to describe the relative density relationship.•We propose a subordinate based criterion to solve the two problems.•Experiments and comparisons demonstrate the effect of our approach.

论文关键词：Density based clustering,Density peak,Cluster center,Relative density relationship

论文评审过程：Received 1 March 2019, Revised 20 June 2020, Accepted 19 July 2020, Available online 29 July 2020, Version of Record 2 August 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107554