Skip to main content

Table 3 Average improvements

From: Building gene expression profile classifiers with a simple and efficient rejection option in R

  SOCMT MOCV
   K-NN-OC KMeans-OC PCA-OC Parzen-OC SVM-OC K-NN-OC KMeans-OC PCA-OC Parzen-OC SVM-OC
G_3 K-NN+rule +0.08 +0.01 -0.01 + 0.01 + 0.12 + 0.04 + 0.05 +0.01 +0.05 +0.11
  RF+rule +0.19 +0.12 +0.10 +0.12 +0.23 +0.15 +0.16 +0.12 +0.16 +0.22
  N-NET+rule +0.03 -0.04 -0.06 -0.04 + 0.07 -0.01 + 0.00 -0.04 +0.00 +0.06
G_4 K-NN+rule -0.01 -0.05 -0.01 -0.05 + 0.06 + 0.10 -0.07 -0.08 +0.00 +0.03
  RF+rule +0.13 +0.09 +0.13 +0.09 +0.20 +0.24 +0.07 +0.06 +0.14 +0.17
  N-NET+rule +0.06 +0.02 + 0.06 -0.04 0.13 + 0.17 + 0.00 -0.01 +0.00 0.1
G_5 K-NN+rule -0.04 -0.16 -0.05 -0.15 -0.04 + 0.04 -0.14 -0.14 -0.06 -0.05
  RF+rule + 0.2 +0.08 +0.19 +0.09 +0.20 +0.28 +0.1 + 0.1 +0.18 +0.19
  N-NET+rule +0.11 -0.01 + 0.10 + 0.00 + 0.11 + 0.19 + 0.01 +0.01 +0.09 +0.10
G_6 K-NN+rule +0.06 +0.01 + 0.03 -0.07 + 0.03 + 0.07 + 0.00 +0.01 +0.11 +0.10
  RF+rule +0.19 +0.14 +0.16 + 0.06 + 0.16 +0.20 +0.13 +0.14 +0.24 +0.23
  N-NET+rule +0.07 +0.02 + 0.04 + 0.01 + 0.04 + 0.08 + 0.01 +0.02 +0.19 +0.11
  1. Results are provided in terms of improvement of the accuracy of multi-class classifiers with decision rules versus one-class classifiers.