Table 4.

Comparison results of BLOEO algorithm with state-of-the-art algorithms.

Specificity	Sensitivity	Precision	#Features	Fitness	Accuracy	Methods	Datasets
0.957	0.932	0.964	16.7	0.059	0.941	BHOA	NSL-KDD
0.959	0.943	0.962	14.6	0.053	0.947	BIMEO
–	0.637	–	37	0.218	0.782	Tama et al.62
–	0.817	–	18	0.131	0.869	Alazzam et al.38
0.973	0.913	–	14.7	0.045	0.955	Kareem et al.63
0.977	0.957	0.982	14.3	0.042	0.958	BLOEO
0.950	0.938	0.951	16.8	0.059	0.941	BHOA	CICIDS2017
0.934	0.914	0.939	17.9	0.078	0.922	BIMEO
o.996	0.927	–	10	0.013	0.987	Kareem et al.63
0.966	0.954	0.971	18.4	0.055	0.945	BLOEO
0.981	0.970	1.000	11.6	0.025	0.975	BHOA	UNSW-NB15
0.983	0.973	1.000	12.3	0.027	0.973	BIMEO
–	0.863	–	19	0.105	0.895	Tama et al.62
–	0.897	–	14	0.087	0.913	Alazzam et al.38
0.877	0.815	–	16.6	0.29	0.710	Kareem et al.63
0.983	0.973	1.000	10.8	0.024	0.976	BLOEO

Significant values are in bold.