A Feature Selection Method of the Island Algorithm Based on Gaussian Mutation

Table 6

Experimental results of four algorithms on six UCI datasets.

Datasets	Average classification accuracy				Optimum value
	FSARSR	PSORSFS	FSRSWOA	IAGMFS	FSARSR	PSORSFS	FSRSWOA	IAGMFS
Breast cancer	0.7023	0.7022	0.7041	0.8033	0.7156	0.7134	0.7163	0.8077
Spectfheart	0.7941	0.7940	0.7944	0.8074	0.7953	0.7977	0.8023	0.8174
Vehicle	0.6079	0.6169	0.6362	0.7671	0.6550	0.6844	0.6972	0.7731
Tic-tac-toe	0.7776	0.7628	0.8038	0.9388	0.8299	0.8310	0.8298	0.9572
Wine	0.8924	0.8983	0.9121	0.9200	0.9775	0.9716	0.9778	0.9315
Zoo	0.8729	0.8733	0.8742	0.8740	0.9127	0.9118	0.9118	0.9044