Margin-maximized redundancy-minimized SVM-RFE for diagnostic classification of mammograms

Classification techniques for digital mammography play an instrumental role in the diagnosis of breast cancer. Recent developments in the derivatives of support vector machines have shown to provide superior classification accuracy rates in comparison with other competing techniques. In this paper, we propose a new classification technique that is based on support vector machines with the additional properties of margin-maximization and redundancy-minimization in order to further increase the accuracy. We have conducted experiments on publicly available data set of mammograms and the empirical results indicated that our proposed technique performs superior to other previously proposed support vector machines-based techniques.