Table 5 Performance of the proposed models on the validation datasets.

From: An interpretable dynamic ensemble selection multiclass imbalance approach with ensemble imbalance learning for predicting road crash injury severity

Models

Precision

Recall

F1 Score

G-Mean

Internal Validation

DES-MI(BRF)

0.72

0.6

0.64

0.65

DES-MI(RBC)

0.56

0.69

0.62

0.37

DES-MI(OBC)

0.71

0.62

0.66

0.65

DES-MI(SPE)

0.72

0.61

0.65

0.65

DES-MI(EIL)

0.71

0.61

0.65

0.65

External Validation-1

DES-MI(BRF)

0.76

0.59

0.65

0.66

DES-MI(RBC)

0.68

0.72

0.66

0.57

DES-MI(OBC)

0.75

0.65

0.69

0.68

DES-MI(SPE)

0.76

0.62

0.68

0.68

DES-MI(EIL)

0.76

0.61

0.65

0.66

External Validation-2

DES-MI(BRF)

0.93

0.92

0.92

0.93

DES-MI(RBC)

0.83

0.84

0.83

0.83

DES-MI(OBC)

0.84

0.78

0.79

0.84

DES-MI(SPE)

0.91

0.91

0.9

0.89

DES-MI(EIL)

0.93

0.93

0.92

0.93

  1. Significant values are in bold.