An Efficient Ensemble Learning Method for Gene Microarray Classification

Table 3

Classification results obtained by RotBoost ensemble learning against typical 8 gene datasets in terms of PCA/ICA transformation methods.

Dataset	ICA_based RootBoost	PCA_based RootBoost
Colon	96.10 ± 0.59	95.48 ± 0.61^•
CNS	95.00 ± 0.28	94.80 ± 0.59^•
Leukaemia	98.77 ± 0.03	98.75 ± 0.31
Breast	97.88 ± 0.45	94.39 ± 0.49^•
Lung	99.54 ± 0.11	98.11 ± 0.17^•
Ovarian	99.40 ± 0.26	99.82 ± 0.08^o
MLL	99.31 ± 0.55	98.86 ± 0.23^•
SRBCT	99.59 ± 0.16	99.50 ± 0.31
Win tie loss		5/2/1

•Specifies that RotBoost is significantly better, and opoints out that RotBoost is notably worse at the significance level α = 0.05.