Genetic-based K-means algorithm for selection of feature variables

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

6 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages744-747
Volume2
Publication statusPublished - 2006

Publication series

Name
Volume2
ISSN (Print)1051-4651

Conference

Title18th International Conference on Pattern Recognition, ICPR 2006
PlaceChina
CityHong Kong
Period20 - 24 August 2006

Abstract

This paper proposes a genetic-based K-means(GK) algorithm for selection of the k value and selection of feature variables by minimizing an associated objective function. The algorithm combines the advantage of genetic algorithm(GA) and K-means to search the subspace thoroughly. Therefore, our algorithm converges globally. A weighting function is then introduced to initialize the parameters of the algorithm. The experiments on a synthetic dataset and a real dataset shows that (i) GK outperforms K-means since GK achieves the minimal value of the objective function and (ii) GK with the weighting function performs better than GK. © 2006 IEEE.

Citation Format(s)

Genetic-based K-means algorithm for selection of feature variables. / Yu, Zhiwen; Wong, Hau-San.

Proceedings - International Conference on Pattern Recognition. Vol. 2 2006. p. 744-747 1699312.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review