Research Article

Comparison of Machine Learning Techniques for the Prediction of Compressive Strength of Concrete

Algorithm 3: Summary of the neural network model architecture (built using nnet) [39].

A 6-10-1 network with 87 weights.
Inputs: c, w, sand, ca, 28 days compressive strength, 56 days compressive strength.
Output: 91 days compressive strength.
Sum of Squares Residuals: 21.2436.
NN build options: skip-layer connections; linear output units.
In the following table:
b represents the bias associated with a node
h1 represents hidden layer node 1
i1 represents input node 1 (i.e., input variable 1)
o represents the output node
Weights for node h1:
b->h1 i1->h1 i2->h1 i3->h1 i4->h1 i5->h1 i6->h1
-0.66 0.23 0.29 -0.31 -0.68 -0.36 0.27
Weights for node h2:
b->h2 i1->h2 i2->h2 i3->h2 i4->h2 i5->h2 i6->h2
1.37 -2.30 -14.01 7.40 -0.19 22.80 -20.86
Weights for node h3:
b->h3 i1->h3 i2->h3 i3->h3 i4->h3 i5->h3 i6->h3
0.39 0.25 -0.16 -0.55 -0.52 0.25 -0.65
Weights for node h4:
b->h4 i1->h4 i2->h4 i3->h4 i4->h4 i5->h4 i6->h4
-0.47 -0.16 -40.54 14.61 -1.09 -0.81 35.27
Weights for node h5:
b->h5 i1->h5 i2->h5 i3->h5 i4->h5 i5->h5 i6->h5
0.56 0.44 0.41 0.51 0.38 0.22 0.47
Weights for node h6:
b->h6 i1->h6 i2->h6 i3->h6 i4->h6 i5->h6 i6->h6
-0.41 0.15 -0.22 0.46 -0.08 -0.41 0.33
Weights for node h7:
b->h7 i1->h7 i2->h7 i3->h7 i4->h7 i5->h7 i6->h7
-0.54 0.56 0.59 0.64 0.13 -0.68 -0.51
Weights for node h8:
b->h8 i1->h8 i2->h8 i3->h8 i4->h8 i5->h8 i6->h8
0.55 0.05 0.15 0.31 -0.15 0.24 0.02
Weights for node h9:
b->h9 i1->h9 i2->h9 i3->h9 i4->h9 i5->h9 i6->h9
0.33 -0.44 -0.47 -0.68 0.07 0.30 0.35
Weights for node h10:
b->h10 i1->h10 i2->h10 i3->h10 i4->h10 i5->h10 i6->h10
-0.01 0.09 0.65 -0.36 -0.41 -0.56 0.50
Weights for node o:
 b->o h1->o h2->o h3->o h4->o h5->o h6->o h7->o h8->o h9->o h10->o
4.90 -0.19 -0.97 -0.62 -0.52 4.96 5.30 5.15 5.76 0.44 -0.07
i1->o i2->o i3->o i4->o i5->o i6->o
0.09 -0.22 0.02 0.00 0.06 0.42
Algorithm 3: Summary of the neural network model architecture (built using nnet) [39].