Table 4 Performance measurements of developed models for Fc.

From: Data-driven framework for prediction of mechanical properties of waste glass aggregates concrete

Model

Dataset

SSE

MAE

MSE

RMSE

Error%

Acc

R2

R.

WI

NSE

KGE

SMAPE

DT-Bat

Training

3264

5.37

31.39

5.60

15%

85%

0.83

0.91

0.95

0.82

0.90

15.69

Validation

781

4.90

32.53

5.70

15%

85%

0.90

0.95

0.97

0.88

0.92

14.02

DT-Cuckoo

Training

889

2.69

8.55

2.92

8%

92%

0.95

0.98

0.99

0.95

0.94

8.32

Validation

470

3.77

19.59

4.43

11%

89%

0.94

0.97

0.98

0.93

0.94

12.64

DT-Elephant

Training

3311

5.15

31.84

5.64

15%

85%

0.90

0.95

0.95

0.81

0.87

17.86

Validation

963

5.33

40.11

6.33

16%

84%

0.92

0.96

0.96

0.85

0.88

17.31

DT-FireFly

Training

782

2.68

7.52

2.74

7%

93%

0.98

0.99

0.99

0.96

0.93

10.03

Validation

349

3.28

14.55

3.81

10%

90%

0.99

0.99

0.99

0.95

0.91

11.73

DT-Rhino

Training

4673

6.30

44.93

6.70

18%

82%

0.82

0.91

0.94

0.74

0.82

17.70

Validation

1040

5.48

14.55

6.58

17%

83%

0.91

0.95

0.97

0.84

0.82

15.10

DT-Wolf

Training

1381

3.5

13.3

3.6

10%

90%

0.96

0.98

0.98

0.92

0.91

12.80

Validation

459

3.9

19.1

4.4

11%

89%

0.97

0.99

0.98

0.93

0.89

13.91