Improving Classification Performance through an Advanced Ensemble Based Heterogeneous Extreme Learning Machines

Table 5

Wilcoxon signed rank statistical test result of AELME versus all the algorithms upon all data sets. values are small which implies the significance of the AELME approach as compared to the other algorithms (here Alg means Algorithm).

AELME versus Alg	value
ELML2	0.0009770
RELM	0.0009766
ELMK	0.0097000
Bagging	0.0019500
DELM	0.0029200
EnELM	0.0019500
DSELME	0.0009766
Adaboost	0.0019500
ELM	0.0009765
SVM	0.0009760