Fig. 1From: Feature selection algorithm based on dual correlation filters for cancer-associated somatic variantsClassification results in case of using machine learning. This figure shows the classification results of two data sets using DNN classifier according to the number of selected features. For the SKCM set, DNN classifier could perform good classification in cases of using \(D_1\) and \(D_2\) features regardless of CFS and DCFS. For the BRCA set, DNN classifier had similar performance for CFS and DCFS methods, but the gap between the cases using \(D_1\) and \(D_2\) features was relatively largeBack to article page