Title: Serial fusion of random subspace ensemble for subcellular phenotype images classification

Authors: Bailing Zhang; Tuan D. Pham

Addresses: Department of Computer Science and Software Engineering, Xi'an Jiaotong-Liverpool University, Suzhou 215123, China, ' School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT 2600, Australia

Abstract: Subcellular localisation is a key functional characteristic of proteins. In this paper, we apply Haralick texture analysis and Curvelet Transform for feature description and propose a cascade Random Subspace (RS) ensemble with rejection options for subcellular phenotype classification. Serial fusions of RS classifier ensembles much improve classification reliability. The rejection option is implemented by relating the consensus degree from majority voting to a confidence measure and abstaining to classify ambiguous samples if the consensus degree is lower than a threshold. Using the public 2D HeLa cell images, classification accuracy 93% is obtained with rejection rate 2.7% from the proposed system.

Keywords: subcellular phenotype images; image classification; cascade classifier; curvelet transform; Haralick texture features; SVM; support vector machine; MLP; multi-layer perceptron; random subspace; subcellular localisation; proteins; serial fusion; classification accuracy; bioinformatics.

DOI: 10.1504/IJBRA.2013.054689

International Journal of Bioinformatics Research and Applications, 2013 Vol.9 No.4, pp.386 - 406

Received: 26 Apr 2010
Accepted: 04 Apr 2011
Published online: 18 Sep 2014 *

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