Table 9 Performance of RBFNN model 1 for 20 RBF units.

From: Image-processing-based model for surface roughness evaluation in titanium based alloys using dual tree complex wavelet transform and radial basis function neural networks

Width

0.15

0.20

0.25

Training data accuracy (%)

97.3988

92.3913

79.7688

Test data accuracy (%)

95.6522

90.9075

73.9130

Average MSE

0.0179

0.0313

0.0742

Back to article page