Skip to main content

Table 4 Performance of mGOASVM using different kernels with different parameters based on leave-one-out cross validation (LOOCV) using the virus dataset

From: mGOASVM: Multi-label protein subcellular localization based on gene ontology and support vector machines

Kernel

Parameter

Locative accuracy

Actual accuracy

Linear SVM

–

244/252 = 96.8%

184/207 = 88.9%

RBF SVM

σ=2−2

182/252 = 72.2%

53/207 = 25.6%

RBF SVM

σ=2−1

118/252 = 46.8%

87/207 = 42.0%

RBF SVM

σ=1

148/252 = 58.7%

116/207 = 56.0%

RBF SVM

σ=21

189/252 = 75.0%

142/207 = 68.6%

RBF SVM

σ=22

223/252 = 88.5%

154/207 = 74.4%

RBF SVM

σ=23

231/252 = 91.7%

150/207 = 72.5%

RBF SVM

σ=24

233/252 = 92.5%

115/207 = 55.6%

RBF SVM

σ=25

136/252 = 54.0%

5/207 = 2.4%

Polynomial SVM

d=2

231/252 = 91.7%

180/207 = 87.0%

Polynomial SVM

d=3

230/252 = 91.3%

178/207 = 86.0%

  1. The penalty parameter (C) was set to 0.1 for all cases. σ is the kernel parameter for the RBF SVM; d is the polynomial degree in the Polynomial SVM.