An improved density peaks clustering algorithm based on natural neighbor with a merging strategy

Density peaks clustering (DPC) is a novel density-based clustering algorithm that identifies center points quickly through a decision graph and assigns corresponding labels to remaining non-center points. Although DPC can identify clusters with any shape, its clustering performance is still restrict...

Full description

Saved in:
Bibliographic Details
Published in:Information sciences Vol. 624; pp. 252 - 276
Main Authors: Ding, Shifei, Du, Wei, Xu, Xiao, Shi, Tianhao, Wang, Yanru, Li, Chao
Format: Journal Article
Language:English
Published: Elsevier Inc 01.05.2023
Subjects:
Clustering analysis
Density peaks clustering
Merging strategy
Natural neighbor
Parameter-free
Clustering analysis
Merging strategy
Natural neighbor
Parameter-free
Density peaks clustering
ISSN:0020-0255, 1872-6291
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Density peaks clustering (DPC) is a novel density-based clustering algorithm that identifies center points quickly through a decision graph and assigns corresponding labels to remaining non-center points. Although DPC can identify clusters with any shape, its clustering performance is still restricted by some aspects. Firstly, DPC works poorly on manifold datasets with different densities. Secondly, DPC is sensitive to the cutoff parameter dc. For the sake of addressing these issues and improving the performance of DPC, an improved density peaks clustering algorithm based on natural neighbor with a merging strategy (IDPC-NNMS) is proposed. IDPC-NNMS identifies a natural neighbor set of each data to obtain its local density adaptively, which can effectively eliminate the impact of the cutoff parameter on final results. Then, sub-clusters are formed after selecting as many center points as possible and allocating labels to remaining non-center points. These sub-clusters are merged by a novel merging strategy until the end conditions are satisfied. The performance of IDPC-NNMS is evaluated on both synthetic and real-world datasets, which fully proves the effectiveness and superiority of the proposed IDPC-NNMS algorithm.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2022.12.078