Research Article
Prediction of Train Arrival Delay Using Hybrid ELM-PSO Approach
Table 5
Model performance comparison on test set for the five models for different delay bins.
| Delay bin (seconds) | Model | RMSE | MAE | R-squared |
| [0, 1200] | ELM-PSO | 0.5201 | 0.3006 | 0.9655 | CB | 1.2628 | 0.9223 | 0.7967 | GBDT | 1.3968 | 0.9886 | 0.7513 | Lasso | 1.0957 | 0.7903 | 0.8469 | KNN | 1.0195 | 0.5278 | 0.8675 |
| >1200 | ELM-PSO | 5.6009 | 2.8249 | 0.9924 | CB | 6.2335 | 3.1986 | 0.9906 | GBDT | 8.0733 | 4.8589 | 0.9843 | Lasso | 6.5023 | 3.1169 | 0.9898 | KNN | 9.0247 | 4.8611 | 0.9804 |
| All delayed trains (>240) | ELM-PSO | 3.3116 | 1.3457 | 0.9951 | CB | 4.0469 | 2.2680 | 0.9927 | GBDT | 5.1561 | 3.1498 | 0.9881 | Lasso | 3.9251 | 1.7418 | 0.9931 | KNN | 5.5878 | 2.8828 | 0.9860 |
|
|