Density peaks clustering with gap-based automatic center detection

作者：

Highlights：

• In density peaks clustering, a subset of input data points is set as cluster centers.

• The cluster centers are selected from a decision graph.

• We propose automated center detection by finding gaps in the decision graph.

• The gaps are detected heuristically by measuring point distance.

• The threshold point is based on the last distance greater than the average distance.

摘要

•In density peaks clustering, a subset of input data points is set as cluster centers.•The cluster centers are selected from a decision graph.•We propose automated center detection by finding gaps in the decision graph.•The gaps are detected heuristically by measuring point distance.•The threshold point is based on the last distance greater than the average distance.

论文关键词：62H30,68T10,65D05,Data clustering,Density peaks clustering,Decision graph,Automatic center detection

论文评审过程：Received 25 October 2019, Revised 22 June 2020, Accepted 30 July 2020, Available online 8 August 2020, Version of Record 12 August 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.106350