An evidential clustering algorithm by finding belief-peaks and disjoint neighborhoods
作者：
Highlights：
• A new evidential clustering algorithm based on finding the belief-peaks and disjoint neighborhoods, called BPDNEC, is proposed.
• BPDNEC automatically detects cluster centers based on a new assumption, which concerns the size of neighborhood rather than delta metric.
• BPDNEC determines the appropriate size of disjoint neighborhoods by solving an equation and thus, avoids problem of parameter setting for K.
• BPDNEC creates a credal partition by minimizing an objective function and available for both proximity data and object data.
摘要
•A new evidential clustering algorithm based on finding the belief-peaks and disjoint neighborhoods, called BPDNEC, is proposed.•BPDNEC automatically detects cluster centers based on a new assumption, which concerns the size of neighborhood rather than delta metric.•BPDNEC determines the appropriate size of disjoint neighborhoods by solving an equation and thus, avoids problem of parameter setting for K.•BPDNEC creates a credal partition by minimizing an objective function and available for both proximity data and object data.
论文关键词：Evidential clustering,Belief-peaks,Disjoint neighborhood,Proximity data
论文评审过程：Received 26 April 2020, Revised 31 August 2020, Accepted 3 November 2020, Available online 4 November 2020, Version of Record 19 February 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107751
