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

Table 14

values of the Nemenyi test about the accuracy on data sets with 40% of added noise.

	Algorithms
21	BA-C4.5-U versus BA-CC4.5	0
20	BA-CC4.5 versus RF	0
19	BA-C4.5-U versus BA-CDT	0
18	BA-CDT versus RF	0
17	BA-CDT-U versus BA-CC4.5	0
16	BA-C4.5-U versus BA-CC4.5-U	0
15	BA-CDT-U versus BA-CDT	0
14	BA-CC4.5-U versus RF	0
13	BA-C4.5 versus BA-CC4.5	0.000001
12	BA-C4.5 versus BA-CDT	0.000056
11	BA-C4.5-U versus BA-C4.5	0.000056
10	BA-CDT-U versus BA-CC4.5-U	0.000161
9	BA-C4.5 versus RF	0.000177
8	BA-CC4.5-U versus BA-CC4.5	0.00178
7	BA-C4.5-U versus BA-CDT-U	0.031355
6	BA-CC4.5-U versus BA-CDT	0.033222
5	BA-CC4.5-U versus BA-C4.5	0.057705
4	BA-CDT-U versus BA-C4.5	0.060822
3	BA-CDT-U versus RF	0.060822
2	BA-CDT versus BA-CC4.5	0.319611
1	BA-C4.5-U versus RF	0.781207