Title: Fuzzy C-means method with empirical mode decomposition for clustering microarray data

Authors: Yan-Fei Wang; Zu-Guo Yu; Vo Anh

Addresses: Discipline of Mathematical Sciences, Faculty of Science and Technology, Queensland University of Technology, Brisbane Q4001, Australia ' Discipline of Mathematical Sciences, Faculty of Science and Technology, Queensland University of Technology, Brisbane Q4001, Australia; School of Mathematics and Computational Science, Xiangtan University, Hunan 411105, China ' Discipline of Mathematical Sciences, Faculty of Science and Technology, Queensland University of Technology, Brisbane Q4001, Australia

Abstract: Microarray techniques have revolutionised genomic research by making it possible to monitor the expression of thousands of genes in parallel. The Fuzzy C-Means (FCM) method is an efficient clustering approach devised for microarray data analysis. However, microarray data contains noise, which would affect clustering results. In this paper, we propose to combine the FCM method with the Empirical Mode Decomposition (EMD) for clustering microarray data to reduce the effect of the noise. The results suggest the clustering structures of denoised microarray data are more reasonable and genes have tighter association with their clusters than those using FCM only.

Keywords: microarray data; clustering; fuzzy C-means; EMD; empirical mode decomposition; noise; gene expression; bioinformatics.

DOI: 10.1504/IJDMB.2013.053192

International Journal of Data Mining and Bioinformatics, 2013 Vol.7 No.2, pp.103 - 117

Received: 05 Mar 2011
Accepted: 06 Mar 2011
Published online: 20 Oct 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article