A New Robust Classifier on Noise Domains: Bagging of Credal C4.5 Trees

Table 8

Average result of the accuracy of the different algorithms when they are built from data sets with added noise.

Algorithm	Noise 0%	Noise 10%	Noise 20%	Noise 30%	Noise 40%
BA-C4.5-U	85.28	84.00	81.50	76.99	70.02
BA-CDT-U	84.90	84.06	82.15	78.20	71.20
BA-CC4.5-U	84.98	84.42	83.27	80.30	74.51
BA-C4.5	85.29	84.54	83.11	79.61	73.25
BA-CDT	84.24	83.89	83.01	80.97	75.77
BA-CC4.5	84.97	84.47	83.58	81.14	75.86
RF	86.24	84.17	80.99	76.08	68.92