Research Article
Seismic Fragility Analysis of the Reinforced Concrete Continuous Bridge Piers Based on Machine Learning and Symbolic Regression Fusion Algorithms
Table 8
The comparison of fitness evaluation index of single IM and various multivariate IMs.
| Direction | IMs | Goodness of fit | Correlation coefficient | MSE | MAE | Fitting complexity | Number of parameters |
| Transverse | Machine learning and symbolic regression fusion algorithms | 0.984 | 0.993 | 0.100 | 0.234 | 30 | 5 | Single | 0.701 | 0.837 | 1.880 | 1.070 | 2 | 2 | Kiani | 0.711 | 0.843 | 1.816 | 1.156 | 5 | 5 | Lv Dagang | 0.564 | 0.751 | 2.736 | 1.200 | 3 | 3 | Liu Tingting | 0.715 | 0.846 | 1.790 | 1.071 | 7 | 7 | Longitudinal | Machine learning and symbolic regression fusion algorithms | 0.997 | 0.998 | 0.012 | 0.084 | 30 | 5 | Single | 0.796 | 0.892 | 0.755 | 0.731 | 2 | 2 | Kiani | 0.763 | 0.874 | 0.875 | 0.788 | 5 | 5 | Lv Dagang | 0.624 | 0.791 | 1.387 | 0.891 | 3 | 3 | Liu Tingting | 0.793 | 0.891 | 0.765 | 0.697 | 7 | 7 |
|
|
MSE is the mean square error; MAE is the mean absolute error.
|