Clustering interval-valued data with adaptive Euclidean and City-Block distances

作者：

Highlights：

• New clustering algorithms for interval-valued data are proposed.

• The methods introduce local and global adaptive distances.

• The distances consider the joint relevance of the variables of each boundary.

• Experiments on synthetic and real data sets show the usefulness of the approaches.

摘要

•New clustering algorithms for interval-valued data are proposed.•The methods introduce local and global adaptive distances.•The distances consider the joint relevance of the variables of each boundary.•Experiments on synthetic and real data sets show the usefulness of the approaches.

论文关键词：Interval-valued data analysis,Partitioning clustering,Adaptive distances,Robust clustering

论文评审过程：Received 14 May 2020, Revised 27 December 2021, Accepted 25 February 2022, Available online 9 March 2022, Version of Record 16 March 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116774