Skip to main content

Table 7 Ranking of the classifiers for real breast cancer microarray datasets. The table reports the ranking of the classifiers when considering the highest g-means obtained with different number boosting iterations for different datasets/classification tasks

From: Boosting for high-dimensional two-class prediction

  1. With n we denote the number of samples used in the analysis after randomly down-sizing the majority class; g-means is the averaged cross-validated g-means of CART(5). Darker shading denotes better classifier’s performance in terms of its g-means
  2. 1 = CART(5), 2 = AdaBoost.M1(5), 3 = AdaBoost.M1.ICV(5), 4 = AdaBoost.M1(1), 5 = LogitBoost(1), 6 = St-GrBoost(1), 7 = GrBoost(1), 8 = St-GrBoost(5), 9 = GrBoost(5)
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us