An improved density peaks clustering algorithm by automatic determination of cluster centres

The fast search and find of density peaks clustering (FDP) is an algorithm that can gain satisfactory clustering results with manual selection of the cluster centres. However, this manual selection is difficult for larger and more complex datasets, and it is easy to split a cluster into multiple sub...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Du, Yanting Hao, Zhihe Wang
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2021.2012422
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850176797281353728
author Hui Du
Yanting Hao
Zhihe Wang
author_facet Hui Du
Yanting Hao
Zhihe Wang
author_sort Hui Du
collection DOAJ
description The fast search and find of density peaks clustering (FDP) is an algorithm that can gain satisfactory clustering results with manual selection of the cluster centres. However, this manual selection is difficult for larger and more complex datasets, and it is easy to split a cluster into multiple subclusters. We propose an automatic determination of cluster centres algorithm (A-FDP). On the one hand, a new decision threshold is designed in A-FDP combined with the InterQuartile Range and standard deviation. We select the points larger than the decision threshold as the cluster centres. On the other hand, these cluster centres are made as nodes to construct the connected graphs. These subclusters are merged by finding the connected components of the connected graph. The results show that the A-FDP can obtain better clustering results and have higher accuracy than other classical clustering algorithms on synthetic and UCI datasets.
format Article
id doaj-art-bd8aa3e7e7bb465abf3648cc917f093c
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-bd8aa3e7e7bb465abf3648cc917f093c2025-08-20T02:19:11ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-0134185787310.1080/09540091.2021.20124222012422An improved density peaks clustering algorithm by automatic determination of cluster centresHui Du0Yanting Hao1Zhihe Wang2College of Computer Science & Engineering, Northwest Normal UniversityCollege of Computer Science & Engineering, Northwest Normal UniversityCollege of Computer Science & Engineering, Northwest Normal UniversityThe fast search and find of density peaks clustering (FDP) is an algorithm that can gain satisfactory clustering results with manual selection of the cluster centres. However, this manual selection is difficult for larger and more complex datasets, and it is easy to split a cluster into multiple subclusters. We propose an automatic determination of cluster centres algorithm (A-FDP). On the one hand, a new decision threshold is designed in A-FDP combined with the InterQuartile Range and standard deviation. We select the points larger than the decision threshold as the cluster centres. On the other hand, these cluster centres are made as nodes to construct the connected graphs. These subclusters are merged by finding the connected components of the connected graph. The results show that the A-FDP can obtain better clustering results and have higher accuracy than other classical clustering algorithms on synthetic and UCI datasets.http://dx.doi.org/10.1080/09540091.2021.2012422clusteringdensity peaksautomatic determination of cluster centressubcluster merging
spellingShingle Hui Du
Yanting Hao
Zhihe Wang
An improved density peaks clustering algorithm by automatic determination of cluster centres
Connection Science
clustering
density peaks
automatic determination of cluster centres
subcluster merging
title An improved density peaks clustering algorithm by automatic determination of cluster centres
title_full An improved density peaks clustering algorithm by automatic determination of cluster centres
title_fullStr An improved density peaks clustering algorithm by automatic determination of cluster centres
title_full_unstemmed An improved density peaks clustering algorithm by automatic determination of cluster centres
title_short An improved density peaks clustering algorithm by automatic determination of cluster centres
title_sort improved density peaks clustering algorithm by automatic determination of cluster centres
topic clustering
density peaks
automatic determination of cluster centres
subcluster merging
url http://dx.doi.org/10.1080/09540091.2021.2012422
work_keys_str_mv AT huidu animproveddensitypeaksclusteringalgorithmbyautomaticdeterminationofclustercentres
AT yantinghao animproveddensitypeaksclusteringalgorithmbyautomaticdeterminationofclustercentres
AT zhihewang animproveddensitypeaksclusteringalgorithmbyautomaticdeterminationofclustercentres
AT huidu improveddensitypeaksclusteringalgorithmbyautomaticdeterminationofclustercentres
AT yantinghao improveddensitypeaksclusteringalgorithmbyautomaticdeterminationofclustercentres
AT zhihewang improveddensitypeaksclusteringalgorithmbyautomaticdeterminationofclustercentres