Table 2.

The comparison of classification accuracy for three feature selection methods, MIFS, MRMR and SVM-RFE (denoted as RFE), on 12 datasets

Dataset	Cancer code	N	Method	Number of Features
				4	8	16	40	60	80	100	150	250	500	862
			MIFS	0.696	0.765	0.811	0.819	0.814	0.819	0.821	0.824	0.814	0.815
poor4	A,B,C,D	803	MRMR	0.734	0.772	0.778	0.794	0.791	0.799	0.814	0.814	0.819	0.802	0.809
			RFE	0.567	0.644	0.681	0.706	0.746	0.771	0.794	0.814	0.821	0.821
			MIFS	0.527	0.59	0.615	0.622	0.64	0.654	0.659	0.645	0.649	0.633
poor6	A,B,C,D,E,F	815	MRMR	0.542	0.576	0.588	0.589	0.581	0.596	0.61	0.596	0.610	0.635	0.633
			RFE	0.337	0.37	0.431	0.531	0.551	0.564	0.578	0.593	0.608	0.635
			MIFS	0.338	0.394	0.433	0.469	0.470	0.488	0.496	0.513	0.53	0.486
poor8	A,B,C,D,E,F,G,H	764	MRMR	0.335	0.408	0.454	0.467	0.469	0.482	0.47	0.474	0.489	0.465	0.472
			RFE	0.259	0.274	0.303	0.39	0.423	0.435	0.457	0.456	0.456	0.475
			MIFS	0.621	0.687	0.755	0.784	0.802	0.816	0.816	0.809	0.808	0.806
fair4	B,D,I,J	812	MRMR	0.598	0.685	0.728	0.777	0.796	0.789	0.784	0.777	0.783	0.786	0.798
			RFE	0.466	0.527	0.608	0.693	0.753	0.753	0.771	0.786	0.787	0.806
			MIFS	0.587	0.698	0.754	0.814	0.822	0.825	0.827	0.82	0.82	0.807
fair6	B,C,D,E,F,I	880	MRMR	0.593	0.698	0.767	0.772	0.786	0.807	0.802	0.807	0.801	0.804	0.792
			RFE	0.504	0.64	0.696	0.761	0.775	0.78	0.781	0.78	0.797	0.816
			MIFS	0.536	0.641	0.684	0.7	0.736	0.733	0.727	0.735	0.732	0.713
fair8	B,C,D,E,H,I,K,L	767	MRMR	0.54	0.653	0.681	0.721	0.707	0.712	0.715	0.704	0.698	0.695	0.72
			RFE	0.398	0.528	0.616	0.677	0.687	0.688	0.702	0.70	0.701	0.709
			MIFS	0.586	0.673	0.763	0.773	0.782	0.78	0.783	0.774	0.778	0.767
good4	B,D,H,M	794	MRMR	0.609	0.681	0.755	0.761	0.779	0.78	0.78	0.77	0.772	0.761	0.755
			RFE	0.543	0.61	0.656	0.711	0.718	0.74	0.732	0.735	0.767	0.749
			MIFS	0.455	0.551	0.593	0.645	0.709	0.716	0.724	0.697	0.7	0.694
good6	D,J,K,L,N,O	867	MRMR	0.427	0.532	0.621	0.667	0.68	0.69	0.677	0.687	0.675	0.664	0.696
			RFE	0.339	0.437	0.517	0.597	0.638	0.653	0.66	0.682	0.674	0.698
			MIFS	0.373	0.477	0.567	0.659	0.674	0.676	0.665	0.673	0.666	0.655
good8	D,E,H,J,K,N,P,Q	827	MRMR	0.336	0.461	0.527	0.615	0.634	0.647	0.644	0.646	0.649	0.661	0.652
			RFE	0.258	0.346	0.424	0.508	0.53	0.581	0.605	0.624	0.632	0.654
			MIFS	0.650	0.754	0.763	0.817	0.829	0.832	0.829	0.821	0.838	0.82
best4	A,D,E,R	1158	MRMR	0.667	0.757	0.775	0.785	0.789	0.793	0.798	0.791	0.784	0.802	0.803
			RFE	0.596	0.659	0.708	0.753	0.766	0.789	0.776	0.791	0.803	0.817
			MIFS	0.497	0.568	0.699	0.731	0.767	0.765	0.763	0.77	0.75	0.755
best6	A,D,E,H,O,R	1095	MRMR	0.497	0.568	0.688	0.73	0.731	0.725	0.746	0.739	0.748	0.74	0.75
			RFE	0.449	0.499	0.587	0.667	0.71	0.712	0.727	0.729	0.736	0.749
			MIFS	0.427	0.543	0.635	0.726	0.737	0.733	0.735	0.732	0.735	0.727
best8	A,D,E,F,H,K,L,R	1016	MRMR	0.434	0.563	0.652	0.704	0.7	0.714	0.712	0.7	0.693	0.704	0.707
			RFE	0.342	0.429	0.532	0.641	0.648	0.687	0.694	0.723	0.719	0.724
			MIFS	0.524	0.612	0.673	0.713	0.732	0.736	0.737	0.734	0.735	0.723
Avg	N/A	N/A	MRMR	0.518	0.606	0.664	0.696	0.702	0.709	0.71	0.707	0.707	0.706	0.716
			RFE	0.422	0.497	0.563	0.636	0.662	0.679	0.69	0.7	0.708	0.721

The best accuracy obtained for each dataset is highlighted in bold. Term N denotes the number of cases. The cancer codes are explained in Table 1.