Table 6 Results of the validation process.

From: An efficient machine learning approach for predicting concrete chloride resistance using a comprehensive dataset

Water (kg/m3)

Cement (kg/m3)

Slag (kg/m3)

Fly ash (kg/m3)

Silica fume (kg/m3)

Fine aggregate (kg/m3)

Coarse aggregate (kg/m3)

Super plasticizer (kg/m3)

Fresh density (kg/m3)

fc (MPa)

Dnssm (× 10−12 m2/s)

Actual value

Predicted value

Error (%)

Regression

Classification

Regression

Classification

Regression

Classification

96.11

222.48

148.32

0

0

730.32

1096.37

0

2301.85

45.81

5.09

2

4.66

2

-9

0

120.46

250.96

83.65

0

0

768.89

1105.87

0

2332.61

34.82

17.56

0

18.02

0

3

0

153.07

355.97

0

0

0

637.18

1187.15

0

2280.55

42.58

9.2

2

10.01

2

8

0

95.79

231.38

124.59

0

0

725.58

1117.73

0

2300.25

49.3

7.16

2

7.02

2

 − 2

0

114.86

261.04

101.45

0

0

745.16

1013.91

0

2244.83

37.34

9.33

2

8.9

2

 − 5

0

97.45

226.63

151.29

0

0

759.99

1045.35

0

2292.24

44.29

7.12

2

7.13

2

0

0

99.78

227.82

151.88

0

0

671

1061.37

0

2247.39

45.09

6.98

2

6.98

2

0

0

153.24

373.76

0

0

29.66

644.3

1072.05

0

2258.6

47.68

12.42

1

12.43

1

0

0

82.23

195.78

160.18

0

0

702.52

1116.74

0

2292.24

46.57

6.23

2

6.22

2

0

0

115.54

281.81

0

74.16

23.73

731.51

1017.47

0

2240.98

39.64

16

0

15.92

0

0

0

115.54

281.81

0

74.16

23.73

742.78

1020.44

0

2240.98

39.64

13.59

1

13.73

1

1

0

95.63

255.7

0

45.68

0

591.5

767.11

0

2338.7

46.24

9.02

2

8.89

2

 − 2

0