A Feature Selection Method by using Chaotic Cuckoo Search Optimization Algorithm with Elitist Preservation and Uniform Mutation for Data Classification

Table 4

Results of different chaos maps on different datasets.

No.	Chaotic maps	D1		D2		D3		D4		D5		D6		D7		D8		D9		D10
		ACC	SF	ACC	SF	ACC	SF	ACC	SF	ACC	SF	ACC	SF	ACC	SF	ACC	SF	ACC	SF	ACC	SF
1	Logistic	0.9021	53.06	0.9530	57.84	0.8945	53.63	0.8995	56.67	0.8016	61.25	0.9731	85.56	0.8839	52.59	0.9837	75.28	0.9468	64.49	1.0000	68.64
2	Singer	0.9350	66.93	0.9696	67.72	0.8830	54.09	0.8602	54.50	0.7610	68.75	0.9719	72.22	0.8830	50.48	0.9798	78.05	0.9466	69.82	1.0000	66.82
3	Sinusoidal	0.9330	63.63	0.9706	58.52	0.8869	49.54	0.8529	52.17	0.7633	73.75	0.9707	67.77	0.8858	51.08	0.9799	78.05	0.9472	62.63	1.0000	59.90
4	Iterative	0.9319	59.43	0.9696	56.25	0.8533	49.55	0.8582	52.83	0.7630	75.00	0.9733	78.88	0.8850	50.66	0.9803	65.00	0.9468	60.52	1.0000	50.90
5	Sine	0.9303	71.59	0.9688	61.70	0.8807	52.27	0.8600	56.00	0.7626	72.50	0.8600	56.00	0.7626	72.50	0.8440	55.38	0.9315	93.33	0.9000	58.00
6	Gauss/mouse	0.9320	84.65	0.9686	73.75	0.8500	56.37	0.8255	58.00	0.7537	77.50	0.9704	78.88	0.8702	55.30	0.9840	87.77	0.9470	87.36	1.0000	100

The bold values show the best result of the chaotic maps in different datasets.