Density propagation based adaptive multi-density clustering algorithm

Yizhang Wang, Wei Pang, You Zhou

Research output: Contribution to journalArticle

2 Citations (Scopus)
6 Downloads (Pure)

Abstract

The performance of density based clustering algorithms may be greatly influenced by the chosen parameter values, and achieving optimal or near optimal results very much depends on empirical knowledge obtained from previous experiments. To address this limitation, we propose a novel density based clustering algorithm called the Density Propagation based Adaptive Multi-density clustering (DPAM) algorithm. DPAM can adaptively cluster spatial data. In order to avoid manual intervention when choosing parameters of density clustering and still achieve high performance, DPAM performs clustering in three stages: (1) generate the micro-clusters graph, (2) density propagation with redefinition of between-class margin and intra-class cohesion, and (3) calculate
regional density. Experimental results demonstrated that DPAM could achieve better performance than several state-of-the-art density clustering algorithms in most of the tested cases, the ability of no parameters needing to be adjusted enables the proposed algorithm to achieve promising performance.
Original languageEnglish
Article numbere0198948
Pages (from-to)1-13
Number of pages13
JournalPloS ONE
Volume13
Issue number7
DOIs
Publication statusPublished - 18 Jul 2018

Fingerprint

Clustering algorithms
Cluster Analysis
Experiments
spatial data
cohesion

Cite this

Density propagation based adaptive multi-density clustering algorithm. / Wang, Yizhang; Pang, Wei; Zhou, You.

In: PloS ONE, Vol. 13, No. 7, e0198948, 18.07.2018, p. 1-13.

Research output: Contribution to journalArticle

Wang, Yizhang ; Pang, Wei ; Zhou, You. / Density propagation based adaptive multi-density clustering algorithm. In: PloS ONE. 2018 ; Vol. 13, No. 7. pp. 1-13.
@article{0d9a7b076d144245bbc0880f70c2ee4c,
title = "Density propagation based adaptive multi-density clustering algorithm",
abstract = "The performance of density based clustering algorithms may be greatly influenced by the chosen parameter values, and achieving optimal or near optimal results very much depends on empirical knowledge obtained from previous experiments. To address this limitation, we propose a novel density based clustering algorithm called the Density Propagation based Adaptive Multi-density clustering (DPAM) algorithm. DPAM can adaptively cluster spatial data. In order to avoid manual intervention when choosing parameters of density clustering and still achieve high performance, DPAM performs clustering in three stages: (1) generate the micro-clusters graph, (2) density propagation with redefinition of between-class margin and intra-class cohesion, and (3) calculateregional density. Experimental results demonstrated that DPAM could achieve better performance than several state-of-the-art density clustering algorithms in most of the tested cases, the ability of no parameters needing to be adjusted enables the proposed algorithm to achieve promising performance.",
author = "Yizhang Wang and Wei Pang and You Zhou",
note = "This research was supported by the Science & Technology Development Foundation of Jilin Province (Grants Nos. 20160101259JC, 20180201045GX), the National Natural Science Foundation of China (Grants No. 61772227) and the Natural Science Foundation of Xinjiang Province (Grants No. 2015211C127). This resarch is also supported by the Engineering and Physical Sciences Research Council (EPSRC) funded project on New Industrial Systems: Manufacturing Immortality (EP/R020957/1).",
year = "2018",
month = "7",
day = "18",
doi = "10.1371/journal.pone.0198948",
language = "English",
volume = "13",
pages = "1--13",
journal = "PloS ONE",
issn = "1932-6203",
publisher = "PUBLIC LIBRARY SCIENCE",
number = "7",

}

TY - JOUR

T1 - Density propagation based adaptive multi-density clustering algorithm

AU - Wang, Yizhang

AU - Pang, Wei

AU - Zhou, You

N1 - This research was supported by the Science & Technology Development Foundation of Jilin Province (Grants Nos. 20160101259JC, 20180201045GX), the National Natural Science Foundation of China (Grants No. 61772227) and the Natural Science Foundation of Xinjiang Province (Grants No. 2015211C127). This resarch is also supported by the Engineering and Physical Sciences Research Council (EPSRC) funded project on New Industrial Systems: Manufacturing Immortality (EP/R020957/1).

PY - 2018/7/18

Y1 - 2018/7/18

N2 - The performance of density based clustering algorithms may be greatly influenced by the chosen parameter values, and achieving optimal or near optimal results very much depends on empirical knowledge obtained from previous experiments. To address this limitation, we propose a novel density based clustering algorithm called the Density Propagation based Adaptive Multi-density clustering (DPAM) algorithm. DPAM can adaptively cluster spatial data. In order to avoid manual intervention when choosing parameters of density clustering and still achieve high performance, DPAM performs clustering in three stages: (1) generate the micro-clusters graph, (2) density propagation with redefinition of between-class margin and intra-class cohesion, and (3) calculateregional density. Experimental results demonstrated that DPAM could achieve better performance than several state-of-the-art density clustering algorithms in most of the tested cases, the ability of no parameters needing to be adjusted enables the proposed algorithm to achieve promising performance.

AB - The performance of density based clustering algorithms may be greatly influenced by the chosen parameter values, and achieving optimal or near optimal results very much depends on empirical knowledge obtained from previous experiments. To address this limitation, we propose a novel density based clustering algorithm called the Density Propagation based Adaptive Multi-density clustering (DPAM) algorithm. DPAM can adaptively cluster spatial data. In order to avoid manual intervention when choosing parameters of density clustering and still achieve high performance, DPAM performs clustering in three stages: (1) generate the micro-clusters graph, (2) density propagation with redefinition of between-class margin and intra-class cohesion, and (3) calculateregional density. Experimental results demonstrated that DPAM could achieve better performance than several state-of-the-art density clustering algorithms in most of the tested cases, the ability of no parameters needing to be adjusted enables the proposed algorithm to achieve promising performance.

U2 - 10.1371/journal.pone.0198948

DO - 10.1371/journal.pone.0198948

M3 - Article

VL - 13

SP - 1

EP - 13

JO - PloS ONE

JF - PloS ONE

SN - 1932-6203

IS - 7

M1 - e0198948

ER -