An Improved K-Means Algorithm Based on Evidence Distance

The main influencing factors of the clustering effect of the k-means algorithm are the selection of the initial clustering center and the distance measurement between the sample points. The traditional k-mean algorithm uses Euclidean distance to measure the distance between sample points, thus it su...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ailin Zhu, Zexi Hua, Yu Shi, Yongchuan Tang, Lingwei Miao
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	k-means clustering evidence distance cluster analysis evidence theory Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/5c58faae16fa4d58a97998719456d345
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5c58faae16fa4d58a97998719456d345
record_format	dspace
spelling	oai:doaj.org-article:5c58faae16fa4d58a97998719456d3452021-11-25T17:30:55ZAn Improved K-Means Algorithm Based on Evidence Distance10.3390/e231115501099-4300https://doaj.org/article/5c58faae16fa4d58a97998719456d3452021-11-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1550https://doaj.org/toc/1099-4300The main influencing factors of the clustering effect of the k-means algorithm are the selection of the initial clustering center and the distance measurement between the sample points. The traditional k-mean algorithm uses Euclidean distance to measure the distance between sample points, thus it suffers from low differentiation of attributes between sample points and is prone to local optimal solutions. For this feature, this paper proposes an improved k-means algorithm based on evidence distance. Firstly, the attribute values of sample points are modelled as the basic probability assignment (BPA) of sample points. Then, the traditional Euclidean distance is replaced by the evidence distance for measuring the distance between sample points, and finally k-means clustering is carried out using UCI data. Experimental comparisons are made with the traditional k-means algorithm, the k-means algorithm based on the aggregation distance parameter, and the Gaussian mixture model. The experimental results show that the improved k-means algorithm based on evidence distance proposed in this paper has a better clustering effect and the convergence of the algorithm is also better.Ailin ZhuZexi HuaYu ShiYongchuan TangLingwei MiaoMDPI AGarticlek-means clusteringevidence distancecluster analysisevidence theoryScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1550, p 1550 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	k-means clustering evidence distance cluster analysis evidence theory Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	k-means clustering evidence distance cluster analysis evidence theory Science Q Astrophysics QB460-466 Physics QC1-999 Ailin Zhu Zexi Hua Yu Shi Yongchuan Tang Lingwei Miao An Improved K-Means Algorithm Based on Evidence Distance
description	The main influencing factors of the clustering effect of the k-means algorithm are the selection of the initial clustering center and the distance measurement between the sample points. The traditional k-mean algorithm uses Euclidean distance to measure the distance between sample points, thus it suffers from low differentiation of attributes between sample points and is prone to local optimal solutions. For this feature, this paper proposes an improved k-means algorithm based on evidence distance. Firstly, the attribute values of sample points are modelled as the basic probability assignment (BPA) of sample points. Then, the traditional Euclidean distance is replaced by the evidence distance for measuring the distance between sample points, and finally k-means clustering is carried out using UCI data. Experimental comparisons are made with the traditional k-means algorithm, the k-means algorithm based on the aggregation distance parameter, and the Gaussian mixture model. The experimental results show that the improved k-means algorithm based on evidence distance proposed in this paper has a better clustering effect and the convergence of the algorithm is also better.
format	article
author	Ailin Zhu Zexi Hua Yu Shi Yongchuan Tang Lingwei Miao
author_facet	Ailin Zhu Zexi Hua Yu Shi Yongchuan Tang Lingwei Miao
author_sort	Ailin Zhu
title	An Improved K-Means Algorithm Based on Evidence Distance
title_short	An Improved K-Means Algorithm Based on Evidence Distance
title_full	An Improved K-Means Algorithm Based on Evidence Distance
title_fullStr	An Improved K-Means Algorithm Based on Evidence Distance
title_full_unstemmed	An Improved K-Means Algorithm Based on Evidence Distance
title_sort	improved k-means algorithm based on evidence distance
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/5c58faae16fa4d58a97998719456d345
work_keys_str_mv	AT ailinzhu animprovedkmeansalgorithmbasedonevidencedistance AT zexihua animprovedkmeansalgorithmbasedonevidencedistance AT yushi animprovedkmeansalgorithmbasedonevidencedistance AT yongchuantang animprovedkmeansalgorithmbasedonevidencedistance AT lingweimiao animprovedkmeansalgorithmbasedonevidencedistance AT ailinzhu improvedkmeansalgorithmbasedonevidencedistance AT zexihua improvedkmeansalgorithmbasedonevidencedistance AT yushi improvedkmeansalgorithmbasedonevidencedistance AT yongchuantang improvedkmeansalgorithmbasedonevidencedistance AT lingweimiao improvedkmeansalgorithmbasedonevidencedistance
_version_	1718412224326795264

An Improved K-Means Algorithm Based on Evidence Distance

Ejemplares similares