Skip to main content
. 2014 Jun 24;14(6):11204–11224. doi: 10.3390/s140611204

Table 6.

Selected features and training accuracy for different branches of the proposed classification with different kernel functions for both cases.

Case 1 Branch #1 Branch #2 Branch #3 Branch #4 Branch #5
Best Features f11 f12 A(%) f21 f22 A(%) f31 f32 A(%) f42 f42 A(%) f51 f52 A(%)
RBF SD(x) ApEn(zN) 98 SD(y) Mean(Mag) 100 SD(y) SD(x) 100 E(yd) SD(x) 100 SD(y) P(z) 100
Linear Max(x) Mean(x) 93 Max(Mag) Mean(Mag) 97 P(z) E(Mag) 100 Max(x) ApEn(zN) 100 SD(y) P(y) 100
Polynomial SD(x) ApEn(xd) 97 SD(y) P(y) 100 SD(y) SD(x) 100 SD(y) Max(Mag) 100 SD(z) SD(y) 100
Case 2 Branch #1 Branch #2 Branch #3 Branch #4 Branch #5
Best Features f11 f12 A(%) f21 f22 A(%) f31 f32 A(%) f42 f42 A(%) f51 f52 A(%)
RBF Corr(x,y) E(yd) 92 Max(y) Mean(y) 94 E(yd) ApEn(zN) 98 Mean(x) ApEn(yN) 99 Max(y) Max(Mag) 99
Linear ApEn(zN) SD(x) 81 SD(y) Mean(Mag) 86 P(z) E(Mag) 94 E(yd) ApEn(yN) 97 Max(y) P(z) 99
Polynomial ApEn(zN) P(y) 89 SD(y) SD(x) 90 P(z) SD(y) 95 Mean(y) P(z) 97 SD(z) SD(y) 99