Active selection of clustering constraints: a sequential approach
作者：
Highlights：
• Active constraint selection as an open issue in constrained clustering is examined.
• The method relies on the information of boundaries and transition regions of data.
• A utility measure based on the description of data is proposed for constraints.
• This utility measure considers the constraint utility dependencies.
• Constraints are selected in a sequential approach utilizing the utility measure.
摘要
Highlights•Active constraint selection as an open issue in constrained clustering is examined.•The method relies on the information of boundaries and transition regions of data.•A utility measure based on the description of data is proposed for constraints.•This utility measure considers the constraint utility dependencies.•Constraints are selected in a sequential approach utilizing the utility measure.
论文关键词：Active constraint selection,Constrained clustering,Pairwise constraints,Data description
论文评审过程：Received 20 January 2013, Revised 21 August 2013, Accepted 30 September 2013, Available online 9 October 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.09.034
