.png){kind=icon}
Return
A clustering algorithm based on dominating (dominated) roughness
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.129705.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Asa pivotal technique within data mining, clustering is integral to a variety of downstream applications. Clustering methods that employ rough sets are often prone to issues of system instability. However, the dominance-based rough set approach (DRSA) enhances semantic interpretation and generalization capabilities in data object description. This paper integrates the generalization potential of DRSA with rough set approximation concepts to devise a measure of object similarity. Utilizing a heuristic framework, strategies for both initial configuration and partitioning are formulated. From a novel viewpoint, this study introduces a DRSA-based clustering algorithm. Subsequent analyses on real datasets evaluate the accuracy and robustness of the proposed algorithm. Visual assessments underscore the effectiveness of this approach in managing complex spatial structures. Furthermore, experiments concerning fuzzy boundary disturbances, normalization variations, and noise resistance affirm the robustness of the method.
Keywords:
Dominance-based rough set
Dominating roughness
Dominated roughness
Clustering
Robustness
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSave
View more