network typically comprised of three layers including input,
hidden and output layers. Input data are first collected
in input layer, and then sent to different processing units
(neuron), which constitute the hidden layer of the networks
[19]. The structure of a neuron showed in Fig. 1 consists
of two major term of weight and transfer function. A
transfer function receives an argument n and generates an
output a. The network input for each neuron is the sum of
all input values, each multiplied by its weight and a bias
term which may be considered as the weight from a supplementary
input equaling one. The output value can be
calculated by feeding the network input into the transfer
function of the neuron [20]. Many transfer functions were
applied in ANN model such as hard limit, pure line, log sigmoid,
soft max, tan sigmoid and triangular basis. The ANN
compares the calculated output with actual data (target)
and computes the error term. Indeed, the ANN is trained
to minimize the error between the ANN output and the target,
resulting in an optimal solution.