Investigation on thermal performance calculation of two type solar air collectors using artificial neural network

Estimation of net surface radiation using eddy flux tower data over a tropical mangrove forest of Sundarban, West Bengal

“…input layer, hidden layers, and an output layer (Caner et al, 2011). It has ability to train input data using input-output relationship based on their connections in order to provide desired function.…”

“…Three steps are followed while developing ANN Model i) selection of input and target data to the network along with network parameters, ii) training of the network to estimate the output and iii) testing step for validating output data with input data, which are not used in developing the model. Further details about it can be found in Caner et al (2011). The performance of the model has been evaluated using statistical error estimates such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R 2 (Caner et al, 2011;Ferreira et al, 2011).…”

Comparison of Neural Network Models in the Estimation of the Performance of Solar Still Under Jordanian Climate

“…Finally, the testing step, in this step estimating output data are obtained by using the input data, which are not used in the training step. More details about these steps is found in [15].…”

“…The performance of the proposed model has been carried out using three global statistics: coefficient of determination (R 2 ), root mean squared error (RMSE) and mean bias error (MBE). More details about these parameters is found in [15]. These three parameters are given by: …”

“…In general, they are composed of three layers, which are an input layer, some hidden layers and an output layer [15]. The advantages of the ANNs are speed, simplicity and ability to train past data to provide the necessary predictions.…”