Table 3 Comparison of the model performance before and after PCA.

From: Principal component analysis–artificial neural network-based model for predicting the static strength of seasonally frozen soils

 

ANN

PCA–ANN

Training set

validation set

Training set

validation set

MSE

66.1

141.3

73.8

115.0

MAE

5.7

8.1

6.1

7.7

RMSE

8.1

11.9

8.6

10.7

R2

0.97

0.96

0.97

0.97

Back to article page