Skip to main content

Table 4 Performance evaluation, testing FS methods on reduced ‘multi-class high-dimension’ datasets (1000 features)

From: GARS: Genetic Algorithm for the identification of a Robust Subset of features in high-dimensional datasets

  ACCSENSPEPPVNPVTimeNfeats
3GARS0.920.900.950.880.9426 min18
3RFE0.940.920.960.910.963 s999
3SBF0.950.940.970.940.971 min 58 s289
3rfGA0.930.910.950.910.9519 h 55 min598
3svmGA
3LASSO0.950.930.960.930.972 s54
5GARS0.930.890.970.890.971 h 22 min17
5RFE0.930.890.970.880.976 s21
5SBF0.930.890.970.870.979 min 38 s890
5rfGA
5svmGA
5LASSO0.960.930.980.930.982 s74
7GARS0.900.840.970.810.973 h 6 min16
7RFE0.950.910.980.890.9813 s999
7SBF0.950.920.990.900.9916 min 7 s959
7rfGA
7svmGA
7LASSO0.960.930.990.900.994 s105
9GARS0.920.860.980.850.986 h 6 min22
9RFE0.930.890.980.870.9811 s25
9SBF0.950.910.990.890.9922 min 47 s963
9rfGA
9svmGA
9LASSO0.960.920.990.900.996 s123
11GARS0.930.880.990.860.9810 h 31 min19
11RFE0.940.900.990.880.9917 s999
11SBF0.950.910.990.890.9930 min 44 s976
11rfGA
11svmGA
11LASSO0.960.920.990.900.999 s134
  1. ACC Accuracy, SEN Sensitivity, SPE Specificity, PPV Positive Predictive Value, NPV Negative Predictive Value, AUC Area Under ROC Curve, Time average learning time for each cross-validation fold, Nfeats n. of selected features