Figure 8
From: Selecting dissimilar genes for multi-class classification, an application in cancer subtyping

5-fold cross validation classification accuracies on the Carcinomas dataset. 5-fold cross validation classification accuracies of the KNN- and SVM-classifiers, where genes are selected using d(·, ·) and d1(·,·) distances combined with the F-test method, on the Carcinomas dataset.