Kernel-based hard clustering methods with kernelization of the metric and automatic weighting of the variables
作者：
Highlights：
• Presents kernel-based clustering methods with automatic weighting of the variables.
• Kernelized local and global adaptive distances are introduced.
• The proposed algorithms are suitable to learn the weights of the variables.
• Partition and cluster interpretation tools are given.
• Experiments with several benchmark data sets corroborate the proposed methods.
摘要
Highlights•Presents kernel-based clustering methods with automatic weighting of the variables.•Kernelized local and global adaptive distances are introduced.•The proposed algorithms are suitable to learn the weights of the variables.•Partition and cluster interpretation tools are given.•Experiments with several benchmark data sets corroborate the proposed methods.
论文关键词：Kernel clustering,Kernelization of the metric,Weighting of the variables,Adaptive distances
论文评审过程：Received 4 September 2014, Revised 18 September 2015, Accepted 21 September 2015, Available online 1 October 2015, Version of Record 27 November 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.09.025
