CutESC: Cutting edge spatial clustering technique based on proximity graphs
作者：
Highlights：
• We propose a cut-edge algorithm for spatial clustering (CutESC) based on proximity graphs. The CutESC algorithm removes edges when a dynamically calculated cut-edge value for the edge’s endpoints is below a threshold.
• The dynamic cut-edge value is calculated by using statistical features and spatial distribution of data based on its neighborhood.
• The algorithm works without any prior information and preliminary parameter settings while automatically discovering clusters with non-uniform densities, arbitrary shapes, and outliers.
• There is also an option which allows users to set two parameters to better adapt clustering solutions for particular problems.
• Experiments have been conducted on various two-dimensional synthetic data and image segmentation to assess advantages of the CutESC algorithm.
摘要
•We propose a cut-edge algorithm for spatial clustering (CutESC) based on proximity graphs. The CutESC algorithm removes edges when a dynamically calculated cut-edge value for the edge’s endpoints is below a threshold.•The dynamic cut-edge value is calculated by using statistical features and spatial distribution of data based on its neighborhood.•The algorithm works without any prior information and preliminary parameter settings while automatically discovering clusters with non-uniform densities, arbitrary shapes, and outliers.•There is also an option which allows users to set two parameters to better adapt clustering solutions for particular problems.•Experiments have been conducted on various two-dimensional synthetic data and image segmentation to assess advantages of the CutESC algorithm.
论文关键词：Spatial data mining,Clustering,Proximity graphs,Graph theory
论文评审过程：Received 20 May 2018, Revised 18 May 2019, Accepted 24 June 2019, Available online 25 June 2019, Version of Record 13 July 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.06.014
