Optimization ELM Based on Rough Set for Predicting the Label of Military Simulation Data

Table 6

Random permutation performance comparison of ELM, SVM, and OELM-S.

Trials	Random permutation; (training set)	TR (%)
		Original dataset			Reduced dataset
		ELM	SVM	OELM-S	ELM	SVM	OELM-S
1	(1, 8, 10, 2, 3, 12)	50.00	33.33	66.67	66.67	33.33	83.33
2	(3, 11, 6, 9,10, 5)	50.00	33.33	50.00	50.00	33.33	66.67
3	(3, 9, 6, 11, 8, 10)	83.33	100	83.33	83.33	100	100
4	(8, 3, 11, 1, 10, 5)	50.00	33.33	50.00	66.67	33.33	83.33
5	(9, 6, 3, 1, 8, 4)	50.00	100	66.67	50.00	100	83.33
6	(9, 8, 12, 7, 1, 6)	50.00	100	66.67	66.67	100	83.33
7	(5, 9, 7, 10, 3, 6)	50.00	33.33	33.33	66.67	33.33	66.67
8	(5, 2, 4, 10, 6, 8)	33.33	16.67	16.67	33.33	16.67	50.00
9	(3, 5, 11, 8, 10, 12)	66.67	100	66.67	83.33	100	100
10	(5, 2, 7, 12, 9, 1)	50.00	33.33	50.00	50.00	33.33	66.67