Title: Margin-maximised redundancy-minimised SVM-RFE for diagnostic classification of mammograms
Authors: Saejoon Kim
Addresses: Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 121-742, Korea
Abstract: Classification techniques function as a main component in digital mammography for breast cancer treatment. While many classification techniques currently exist, recent developments in the derivatives of Support Vector Machines (SVM) with feature selection have shown to yield superior classification accuracy rates in comparison with other competing techniques. In this paper, we propose a new classification technique that is derived from SVM in which margin is maximised and redundancy is minimised during the feature selection process. We have conducted experiments on the largest publicly available data set of mammograms. The empirical results indicate that our proposed classification technique performs superior to other previously proposed SVM-based techniques.
Keywords: digital mammography; mammogram classification; SVM; SVM-RFE; recursive feature elimination; feature selection; support vector machines; mammograms; breast cancer treatment; bioinformatics.
DOI: 10.1504/IJDMB.2014.064889
International Journal of Data Mining and Bioinformatics, 2014 Vol.10 No.4, pp.374 - 390
Received: 25 Jul 2012
Accepted: 08 Aug 2012
Published online: 21 Oct 2014 *