A weighted genetic algorithm based method for clustering of heteroscaled datasets

Zulkifli Mohd Nopiah, Muhammad Ihsan Khairir, Shahrum Abdullah, Mohd Noor Baharin

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

6 Citations (Scopus)

Abstract

This paper introduces a weighted genetic algorithm (GA) based clustering method for datasets with differently scaled dimensions. Several types of synthetic two dimensional scatter data were clustered using the typical k-means clustering method. The weighted GA-based clustering method was developed to address the problem of clustering data with differently scaled (heteroscaled) dimensions. Cluster analysis results obtained from using this method was compared to the results produced from the application of the traditional k-means clustering. By introducing weights in the fitness evaluation component of the meta-heuristic search method, a more efficient clustering of heteroscaled data was produced. In real applications, this method can be used in cluster analyses of scatter data with significantly different scales in dimensions, such as kurtosis versus fatigue damage relationship scatter data.

Original languageEnglish
Title of host publication2009 International Conference on Signal Processing Systems, ICSPS 2009
Pages971-975
Number of pages5
DOIs
Publication statusPublished - 2009
Event2009 International Conference on Signal Processing Systems, ICSPS 2009 - Singapore
Duration: 15 May 200917 May 2009

Other

Other2009 International Conference on Signal Processing Systems, ICSPS 2009
CitySingapore
Period15/5/0917/5/09

Fingerprint

Genetic algorithms
Cluster analysis
Fatigue damage

Keywords

  • Cluster analysis
  • Data clustering
  • Genetic algorithm
  • Heteroscaled data set
  • K-means clustering
  • Scattered data set

ASJC Scopus subject areas

  • Signal Processing

Cite this

Mohd Nopiah, Z., Khairir, M. I., Abdullah, S., & Baharin, M. N. (2009). A weighted genetic algorithm based method for clustering of heteroscaled datasets. In 2009 International Conference on Signal Processing Systems, ICSPS 2009 (pp. 971-975). [5166936] https://doi.org/10.1109/ICSPS.2009.185

A weighted genetic algorithm based method for clustering of heteroscaled datasets. / Mohd Nopiah, Zulkifli; Khairir, Muhammad Ihsan; Abdullah, Shahrum; Baharin, Mohd Noor.

2009 International Conference on Signal Processing Systems, ICSPS 2009. 2009. p. 971-975 5166936.

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

Mohd Nopiah, Z, Khairir, MI, Abdullah, S & Baharin, MN 2009, A weighted genetic algorithm based method for clustering of heteroscaled datasets. in 2009 International Conference on Signal Processing Systems, ICSPS 2009., 5166936, pp. 971-975, 2009 International Conference on Signal Processing Systems, ICSPS 2009, Singapore, 15/5/09. https://doi.org/10.1109/ICSPS.2009.185
Mohd Nopiah Z, Khairir MI, Abdullah S, Baharin MN. A weighted genetic algorithm based method for clustering of heteroscaled datasets. In 2009 International Conference on Signal Processing Systems, ICSPS 2009. 2009. p. 971-975. 5166936 https://doi.org/10.1109/ICSPS.2009.185
Mohd Nopiah, Zulkifli ; Khairir, Muhammad Ihsan ; Abdullah, Shahrum ; Baharin, Mohd Noor. / A weighted genetic algorithm based method for clustering of heteroscaled datasets. 2009 International Conference on Signal Processing Systems, ICSPS 2009. 2009. pp. 971-975
@inproceedings{b0a4e13b69d249fcabd93923816adb14,
title = "A weighted genetic algorithm based method for clustering of heteroscaled datasets",
abstract = "This paper introduces a weighted genetic algorithm (GA) based clustering method for datasets with differently scaled dimensions. Several types of synthetic two dimensional scatter data were clustered using the typical k-means clustering method. The weighted GA-based clustering method was developed to address the problem of clustering data with differently scaled (heteroscaled) dimensions. Cluster analysis results obtained from using this method was compared to the results produced from the application of the traditional k-means clustering. By introducing weights in the fitness evaluation component of the meta-heuristic search method, a more efficient clustering of heteroscaled data was produced. In real applications, this method can be used in cluster analyses of scatter data with significantly different scales in dimensions, such as kurtosis versus fatigue damage relationship scatter data.",
keywords = "Cluster analysis, Data clustering, Genetic algorithm, Heteroscaled data set, K-means clustering, Scattered data set",
author = "{Mohd Nopiah}, Zulkifli and Khairir, {Muhammad Ihsan} and Shahrum Abdullah and Baharin, {Mohd Noor}",
year = "2009",
doi = "10.1109/ICSPS.2009.185",
language = "English",
isbn = "9780769536545",
pages = "971--975",
booktitle = "2009 International Conference on Signal Processing Systems, ICSPS 2009",

}

TY - GEN

T1 - A weighted genetic algorithm based method for clustering of heteroscaled datasets

AU - Mohd Nopiah, Zulkifli

AU - Khairir, Muhammad Ihsan

AU - Abdullah, Shahrum

AU - Baharin, Mohd Noor

PY - 2009

Y1 - 2009

N2 - This paper introduces a weighted genetic algorithm (GA) based clustering method for datasets with differently scaled dimensions. Several types of synthetic two dimensional scatter data were clustered using the typical k-means clustering method. The weighted GA-based clustering method was developed to address the problem of clustering data with differently scaled (heteroscaled) dimensions. Cluster analysis results obtained from using this method was compared to the results produced from the application of the traditional k-means clustering. By introducing weights in the fitness evaluation component of the meta-heuristic search method, a more efficient clustering of heteroscaled data was produced. In real applications, this method can be used in cluster analyses of scatter data with significantly different scales in dimensions, such as kurtosis versus fatigue damage relationship scatter data.

AB - This paper introduces a weighted genetic algorithm (GA) based clustering method for datasets with differently scaled dimensions. Several types of synthetic two dimensional scatter data were clustered using the typical k-means clustering method. The weighted GA-based clustering method was developed to address the problem of clustering data with differently scaled (heteroscaled) dimensions. Cluster analysis results obtained from using this method was compared to the results produced from the application of the traditional k-means clustering. By introducing weights in the fitness evaluation component of the meta-heuristic search method, a more efficient clustering of heteroscaled data was produced. In real applications, this method can be used in cluster analyses of scatter data with significantly different scales in dimensions, such as kurtosis versus fatigue damage relationship scatter data.

KW - Cluster analysis

KW - Data clustering

KW - Genetic algorithm

KW - Heteroscaled data set

KW - K-means clustering

KW - Scattered data set

UR - http://www.scopus.com/inward/record.url?scp=70449623639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449623639&partnerID=8YFLogxK

U2 - 10.1109/ICSPS.2009.185

DO - 10.1109/ICSPS.2009.185

M3 - Conference contribution

SN - 9780769536545

SP - 971

EP - 975

BT - 2009 International Conference on Signal Processing Systems, ICSPS 2009

ER -