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

Table 10

values of the Nemenyi test about the accuracy on data sets without added noise.

	Algorithms
21	BA-CDT versus RF	0
20	BA-C4.5-U versus BA-CDT	0
19	BA-CDT-U versus RF	0.000056
18	BA-C4.5 versus BA-CDT	0.000134
17	BA-CC4.5 versus RF	0.000727
16	BA-C4.5-U versus BA-CDT-U	0.00178
15	BA-CC4.5-U versus BA-CDT	0.00178
14	BA-CC4.5-U versus RF	0.002622
13	BA-CDT versus BA-CC4.5	0.005882
12	BA-C4.5-U versus BA-CC4.5	0.013265
11	BA-C4.5 versus RF	0.020638
10	BA-C4.5-U versus BA-CC4.5-U	0.035183
9	BA-CDT-U versus BA-CDT	0.035183
8	BA-CDT-U versus BA-C4.5	0.086755
7	BA-C4.5-U versus BA-C4.5	0.157987
6	BA-C4.5 versus BA-CC4.5	0.287015
5	BA-CDT-U versus BA-CC4.5-U	0.308487
4	BA-C4.5-U versus RF	0.366699
3	BA-CC4.5-U versus BA-C4.5	0.487453
2	BA-CDT-U versus BA-CC4.5	0.516937
1	BA-CC4.5-U versus BA-CC4.5	0.711138