Table 1 Prediction results of the base learners used in this work

From: A novel stacking ensemble learner for predicting residual strength of corroded pipelines

Model

R2

MSE

MAE

MAPE

Performance ranking

KNN

0.878

8.133

1.706

0.145

7

SVR

0.939

4.052

1.187

0.106

1

RF

0.903

6.479

1.718

0.149

5

MLP

0.902

6.552

1.492

0.101

6

ETR

0.927

4.842

1.438

0.127

4

LightGBM

0.931

4.568

1.412

0.097

3

XGBoost

0.937

4.171

1.281

0.087

2

  1. RF Random forest, ETR extra trees regressor, MSE mean squared error, MAE mean absolute error, MAPE mean absolute percentage error.
Back to article page