Table 2
Comparison of the error metrics for all tree regression algorithms.
| ML algorithm | MAE log10 (years) | RMSE log10 (years) | R2 |
|---|---|---|---|
| ETR | 0.2228 | 0.3057 | 0.9895 |
| RFR | 0.2388 | 0.3020 | 0.9898 |
| GBR | 0.2376 | 0.3142 | 0.9889 |
| KNN | 0.2441 | 0.3145 | 0.9889 |
| DT | 0.2670 | 0.3773 | 0.9840 |
| BR | 0.8576 | 1.2852 | 0.8153 |
| LR | 2.7604 | 4.8142 | −1.5901 |
| Lasso regression | 0.866 | 1.2713 | 0.8193 |
| SVR | 0.6843 | 1.4065 | 0.7789 |
Notes. MAE = Mean absolute error, RMSE = Root-mean-square error, R2 = Coefficient of determination, ETR: Extra tree regressor, RFR = random forest regressor, GBR: Gradient boosting regressor, KNN: K-neighbor regressor, DT = Decision tree regressor, BR = Bayesian ridge, LR: Linear regression, SVR = Support-vector regression.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.