Feature selection with ensemble learning for prostate cancer diagnosis from microarray gene expression

Cancer diagnosis using machine learning algorithms is one of the main topics research in computer-based medical science. Prostate cancer considered reasons that are leading to deaths worldwide. Data analysis gene expression from microarray and soft computing a useful tool for detecting prostate diagnosis. Even though traditional methods have been successfully applied cancer, large number attributes with small sample size data still challenge limits their ability effective Selecting subset relevant features all choosing an appropriate method can exploit information improve accuracy rate detection. In this paper, we propose use correlation feature selection (CFS) random committee (RC) ensemble detect expression. A set experiments conducted on public benchmark dataset 10-fold cross-validation technique evaluate proposed approach. The experimental results revealed approach attains 95.098% accuracy, which higher than related work same dataset.