. 2017 May 18;8(29):47816–47830. doi: 10.18632/oncotarget.18001

Table 4. The performance of WEKA SMO classifier using different c and kernel.

Accuracy/AUC		c=2^-5	c=2^-4	c=2^-3	c=2^-2	c=2^-1	c=2⁰	c=2¹	c=2²	c=2³	c=2⁴	c=2⁵
LGG vs. HGG	NormalizedPoly-Kernel	0.030/0.030	0.705/0.705	0.735/0.735	0.760/0.760	0.810/0.810	0.865/0.865	0.920/0.920	0.940/0.940	0.950/0.950	0.950/0.950	0.950/0.950
	PolyKernel	0.920/0.920	0.940/0.940	0.945/0.945	0.945/0.945	0.945/0.945	0.945/0.945	0.945/0.945	0.945/0.945	0.945/0.945	0.945/0.945	0.945/0.945
	RBFKernel	0.390/0.390	0.725/0.725	0.745/0.745	0.795/0.795	0.865/0.865	0.930/0.930	0.955/0.955	0.960/0.960	0.960/0.960	0.960/0.960	0.960/0.960
	PUK	0.295/0.295	0.310/0.310	0.300/0.300	0.265/0.265	0.235/0.235	0.765/0.765	0.745/0.745	0.745/0.745	0.745/0.745	0.745/0.745	0.745/0.745
Grade II, III, and IV	NormalizedPoly-Kernel	0.103/0.141	0.456/0.632	0.436/0.626	0.613/0.732	0.775/0.852	0.843/0.900	0.922/0.957	0.941/0.965	0.966/0.981	0.966/0.981	0.966/0.981
	PolyKernel	0.946/0.966	0.956/0.977	0.961/0.979	0.956/0.975	0.956/0.975	0.956/0.975	0.956/0.975	0.956/0.975	0.956/0.975	0.956/0.975	0.956/0.975
	RBFKernel	0.186/0.310	0.456/0.629	0.598/0.732	0.770/0.846	0.848/0.909	0.917/0.955	0.956/0.977	0.966/0.983	0.971/0.986	0.971/0.986	0.971/0.986
	PUK	0.162/0.350	0.172/0.326	0.152/0.321	0.152/0.309	0.176/0.319	0.745/0.822	0.735/0.819	0.735/0.819	0.735/0.819	0.735/0.819	0.735/0.819