Evolutionary Voting-Based Extreme Learning Machines

Table 2

Comparison results among ELM, V-ELM, and EV-ELM algorithms using benchmark UCI and face databases.

	Database	Algorithms	Number of nodes	Number of ensembles	Training time (s)	Testing accuracy (%)	Standard deviation (%)
UCI	Balance	ELM	100	NA	0.06	89.56	1.35
		V-ELM	100	20	1.22	90.24	0.68
		EV-ELM	100	20	3.16	90.84	0.67
	Diabetes	ELM	30	NA	0.06	76.65	1.73
		V-ELM	30	20	0.35	78.67	0.69
		EV-ELM	30	20	2.27	79.18	0.66
	Digit	ELM	200	NA	1.15	96.98	0.23
		V-ELM	200	20	28.51	97.18	0.08
		EV-ELM	200	20	30.77	97.30	0.07
	Hayes	ELM	60	NA	0.01	74.64	5.63
		V-ELM	60	20	0.41	78.42	3.58
		EV-ELM	60	20	2.51	79.93	3.21
	Heart	ELM	20	NA	0.01	79.01	2.82
		V-ELM	20	20	0.19	82.14	1.25
		EV-ELM	20	20	1.99	82.78	1.12
	Iris	ELM	20	NA	0.01	97.20	1.39
		V-ELM	20	20	0.12	98.00	0.70
		EV-ELM	20	20	2.16	98.00	0.39
	Monk1	ELM	100	NA	0.05	78.15	2.63
		V-ELM	100	20	0.79	85.79	1.37
		EV-ELM	100	20	2.82	87.23	1.17
	Monk2	ELM	100	NA	0.06	78.84	2.07
		V-ELM	100	20	0.91	83.51	0.82
		EV-ELM	100	20	3.21	83.81	0.75
	Monk3	ELM	100	NA	0.06	80.62	3.13
		V-ELM	100	20	0.68	89.00	1.03
		EV-ELM	100	20	2.68	89.48	0.97
	Sonar	ELM	60	NA	0.01	77.25	3.44
		V-ELM	60	20	0.29	86.79	1.95
		EV-ELM	60	20	2.23	87.17	1.77
	Waveform	ELM	200	NA	0.44	84.87	0.52
		V-ELM	200	20	12.71	86.44	0.21
		EV-ELM	200	20	14.77	86.60	0.19
	Wine	ELM	20	NA	0.01	97.31	1.50
		V-ELM	20	20	0.12	98.89	0.85
		EV-ELM	20	20	2.21	99.36	0.69
Face	Combo	ELM	200	NA	0.21	84.88	1.06
		V-ELM	200	20	5.16	87.80	0.60
		EV-ELM	200	20	7.58	88.42	0.59
	FERET	ELM	100	NA	0.12	41.85	0.80
		V-ELM	100	20	7.19	49.06	0.49
		EV-ELM	100	20	13.95	49.20	0.47
	GTFD	ELM	200	NA	0.19	54.86	2.01
		V-ELM	200	20	4.60	66.91	1.39
		EV-ELM	200	20	6.77	67.14	1.26