3.1.2. Normalizing Data

Using SPSS software, data were normalized in a range between −1 and 1. It seems necessary to mention that the ANN's output can be returned to the initial format using the reverse algorithm. Normalized data are illustrated in Table 2.


**Table 2.** Normalized ANN input data.

**Table 2.** *Cont.* 26 0.90 0.90 0.50 0.90 0.63 0.63 0.90 0.90 0.30 0.70 0.19 0.50 0.50 0.50 27 0.10 0.10 0.50 0.70 0.63 0.63 0.37 0.30 0.50 0.70 0.49 0.70 0.90 0.50

*Symmetry* **2020**, *12*, x FOR PEER REVIEW 7 of 17

 0.90 0.90 0.50 0.30 0.10 0.63 0.90 0.90 0.70 0.90 0.49 0.50 0.70 0.30 0.30 0.37 0.50 0.70 0.63 0.63 0.90 0.90 0.50 0.50 0.77 0.30 0.50 0.10 0.90 0.37 0.70 0.30 0.37 0.90 0.37 0.50 0.70 0.30 0.19 0.70 0.30 0.90 0.70 0.90 0.50 0.90 0.63 0.63 0.90 0.70 0.30 0.30 0.31 0.10 0.10 0.70 0.70 0.37 0.70 0.50 0.63 0.63 0.90 0.10 0.50 0.70 0.12 0.90 0.70 0.30 0.90 0.90 0.50 0.50 0.63 0.37 0.90 0.90 0.50 0.90 0.39 0.70 0.50 0.50 0.90 0.37 0.70 0.70 0.63 0.63 0.63 0.70 0.90 0.90 0.39 0.90 0.50 0.50


### 3.1.3. Determining Hidden Layers of ANN 3.1.3. Determining Hidden Layers of ANN

It is best for the number of hidden layers to be as low as possible. One hidden layer is initially considered for an ANN. Then, after training the ANN, the number of layers will be increased if the output is not suitable. Furthermore, there are a number of functions that can be used to produce the network's outcome. In this study, the Sigmoid Tangent function was exploited. The network introduced into MATLAB software included 14 neurons in its input layer and 3 neurons in its hidden layer. The structure of the network is illustrated in Figure 3. It is best for the number of hidden layers to be as low as possible. One hidden layer is initially considered for an ANN. Then, after training the ANN, the number of layers will be increased if the output is not suitable. Furthermore, there are a number of functions that can be used to produce the network's outcome. In this study, the Sigmoid Tangent function was exploited. The network introduced into MATLAB software included 14 neurons in its input layer and 3 neurons in its hidden layer. The structure of the network is illustrated in Figure 3.

**Figure 3.** ANN introduced into MATLAB**. Figure 3.** ANN introduced into MATLAB.
