Gravitational search algorithm with heuristic search for clustering problems

Abdolreza Hatamlou, Salwani Abdullah, Zalinda Othman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Citations (Scopus)

Abstract

In this paper, we present an efficient algorithm for cluster analysis, which is based on gravitational search and a heuristic search algorithm. In the proposed algorithm, called GSA-HS, the gravitational search algorithm is used to find a near optimal solution for clustering problem, and then at the next step a heuristic search algorithm is applied to improve the initial solution by searching around it. Four benchmark datasets are used to evaluate and to compare the performance of the presented algorithm with two other famous clustering algorithms, i.e. K-means and particle swarm optimization algorithm. The results show that the proposed algorithm can find high quality clusters in all the tested datasets.

Original languageEnglish
Title of host publicationConference on Data Mining and Optimization
Pages190-193
Number of pages4
DOIs
Publication statusPublished - 2011
Event2011 3rd Conference on Data Mining and Optimization, DMO 2011 - Putrajaya
Duration: 28 Jun 201129 Jun 2011

Other

Other2011 3rd Conference on Data Mining and Optimization, DMO 2011
CityPutrajaya
Period28/6/1129/6/11

Fingerprint

Cluster analysis
Clustering algorithms
Particle swarm optimization (PSO)

Keywords

  • Cluster analysis
  • Gravitational search algorithm
  • Heuristic search

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Software

Cite this

Gravitational search algorithm with heuristic search for clustering problems. / Hatamlou, Abdolreza; Abdullah, Salwani; Othman, Zalinda.

Conference on Data Mining and Optimization. 2011. p. 190-193 5976526.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hatamlou, A, Abdullah, S & Othman, Z 2011, Gravitational search algorithm with heuristic search for clustering problems. in Conference on Data Mining and Optimization., 5976526, pp. 190-193, 2011 3rd Conference on Data Mining and Optimization, DMO 2011, Putrajaya, 28/6/11. https://doi.org/10.1109/DMO.2011.5976526
Hatamlou, Abdolreza ; Abdullah, Salwani ; Othman, Zalinda. / Gravitational search algorithm with heuristic search for clustering problems. Conference on Data Mining and Optimization. 2011. pp. 190-193
@inproceedings{7f0e17d68a3048a49111a5c5c5822ea5,
title = "Gravitational search algorithm with heuristic search for clustering problems",
abstract = "In this paper, we present an efficient algorithm for cluster analysis, which is based on gravitational search and a heuristic search algorithm. In the proposed algorithm, called GSA-HS, the gravitational search algorithm is used to find a near optimal solution for clustering problem, and then at the next step a heuristic search algorithm is applied to improve the initial solution by searching around it. Four benchmark datasets are used to evaluate and to compare the performance of the presented algorithm with two other famous clustering algorithms, i.e. K-means and particle swarm optimization algorithm. The results show that the proposed algorithm can find high quality clusters in all the tested datasets.",
keywords = "Cluster analysis, Gravitational search algorithm, Heuristic search",
author = "Abdolreza Hatamlou and Salwani Abdullah and Zalinda Othman",
year = "2011",
doi = "10.1109/DMO.2011.5976526",
language = "English",
isbn = "9781612842127",
pages = "190--193",
booktitle = "Conference on Data Mining and Optimization",

}

TY - GEN

T1 - Gravitational search algorithm with heuristic search for clustering problems

AU - Hatamlou, Abdolreza

AU - Abdullah, Salwani

AU - Othman, Zalinda

PY - 2011

Y1 - 2011

N2 - In this paper, we present an efficient algorithm for cluster analysis, which is based on gravitational search and a heuristic search algorithm. In the proposed algorithm, called GSA-HS, the gravitational search algorithm is used to find a near optimal solution for clustering problem, and then at the next step a heuristic search algorithm is applied to improve the initial solution by searching around it. Four benchmark datasets are used to evaluate and to compare the performance of the presented algorithm with two other famous clustering algorithms, i.e. K-means and particle swarm optimization algorithm. The results show that the proposed algorithm can find high quality clusters in all the tested datasets.

AB - In this paper, we present an efficient algorithm for cluster analysis, which is based on gravitational search and a heuristic search algorithm. In the proposed algorithm, called GSA-HS, the gravitational search algorithm is used to find a near optimal solution for clustering problem, and then at the next step a heuristic search algorithm is applied to improve the initial solution by searching around it. Four benchmark datasets are used to evaluate and to compare the performance of the presented algorithm with two other famous clustering algorithms, i.e. K-means and particle swarm optimization algorithm. The results show that the proposed algorithm can find high quality clusters in all the tested datasets.

KW - Cluster analysis

KW - Gravitational search algorithm

KW - Heuristic search

UR - http://www.scopus.com/inward/record.url?scp=80055062743&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055062743&partnerID=8YFLogxK

U2 - 10.1109/DMO.2011.5976526

DO - 10.1109/DMO.2011.5976526

M3 - Conference contribution

SN - 9781612842127

SP - 190

EP - 193

BT - Conference on Data Mining and Optimization

ER -