Skip to main content

Table 2 Average accuracy of using 5 to 50 features per method and dataset

From: ClearF: a supervised feature scoring method to find biomarkers using class-wise embedding and reconstruction

  Fisher score Trace ratio Multi SURF ClearF normal ClearF rbf ClearF poly CMIM mRMR t-score
Leukemia 0.945 0.945 0.945 0.973 0.959 0.945 0.973 0.959 0.959
ProstateGE 0.912 0.857 0.857 0.868 0.912 0.922 0.902
TOX171 0.672 0.713 0.819 0.807 0.666 0.683
Lung 0.865 0.841 0.901 0.916 0.935 0.902
LungDiscrete 0.716 0.689 0.811 0.880 0.879 0.811 0.841 0.743
  1. The bold italic numbers indicate the best results for each dataset, and the bold non-italic numbers indicate the second-best result