Table 5 Four new test data-points with various fiber contents to evaluate the effect of this parameter on the CS and examine the performance of machine learning techniques.

From: Application of machine learning techniques to predict the compressive strength of steel fiber reinforced concrete

Fiber type

Fiber content (%)

Fiber length (mm)

Fiber diameter (mm)

w/c

Curing time (days)

Silica fume (%)

Aggregate size (mm)

Superplasticizer (kg/m3)

Glass

0.5

18

0.52

0.45

28

7.3

14

2.4

Glass

0.75

18

0.52

0.45

28

7.3

14

2.4

Glass

1

18

0.52

0.45

28

7.3

14

2.4

Glass

1.25

18

0.52

0.45

28

7.3

14

2.4

Glass

1.5

18

0.52

0.45

28

7.3

14

2.4

Glass

1.75

18

0.52

0.45

28

7.3

14

2.4

Glass

2

18

0.52

0.45

28

7.3

14

2.4