An Efficient Feature Selection Strategy Based on Multiple Support Vector Machine Technology with Gene Expression Data

Table 9

The performance comparison of RFFS, RFFS-GS, and mRMR algorithm on TCGA data set.

Measure	RFFS	RFFS-GS	mRMR
genes	20	15	12
Accuracy	91.6808%	92.1902%	91.8506%
Precision	100%	97.9630%	100%
Recall	91.6808%	93.7943%	91.8367%
F-score	95.6599%	95.8333%	95.7447%
AUC	0.61494	0.78893	0.85408