Skip to main content

Advertisement

Table 2 The comparisons in ReliefF, mRMR and mRMR-ReliefF algorithms (gene number = 30)

From: Gene selection algorithm by combining reliefF and mRMR

Feature Selection Method Classifier ALL ARR LYM HBC NCI60 MLL GCM
ReliefF SVM 96.37% 79.29% 100% 95.45% 58.33% 94.44% 55.25%
  Naive Bayes 92.34% 75% 95.16% 90.91% 53.33% 91.67% 55.56%
mRMR SVM - 75.35% 100% 95.45% 53.33% - -
  Naive Bayes - 73.21% 97.33% 87.51% 51.20% - -
mRMR-ReliefF SVM 96.77% 81.43% 100% 95.45% 68.33% 98.61% 64.65%
  Naive Bayes 95.97% 79.05% 100% 95.45% 61.67% 98.61% 61.11%