Table 13 Comparative evaluation of developed RBFNN models.

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

Model considered

Training data accuracy (%)

Test data accuracy (%)

MSE

No. of hidden neurons

RBFNN model 1

97.3988

95.6522

0.0179

20

RBFNN model 2

98.9130

98.5549

0.0161

25

RBFNN model 3

97.6879

96.7391

0.0164

25

RBFNN model 4

98.9130

98.8439

0.0144

30

RBFNN model 5

98.8439

97.8261

0.0148

35

RBFNN model 6

100

99.1329

0.0131

35

Back to article page