Employing Artificial Neural Networks to Predict the Performance of Domestic Sewage Treatment Terminals in the Rural Region
Table 4
Parameters setting in ANN, ANN-GA, and ANN-PSO.
Model
Common setting for ANN
Others
ANN
Inputnum = 8 (number of input neurons); Hiddennum = 15 (number of hidden neurons); Outputnum = 1 (number of output neurons); Net.trainParam.epochs = 20000; Net.trainParam.lr = 0.01 (learning rate); Net.trainParam.goal = 0.000004 (training goal); Purelin , transfer function from input layer to hidden layer; Tansig, transfer function from hidden layer to output layer;
None
ANN-GA
Maxgen = 100 (number of Iterations); Sizepop = 10 (size of population); Pcross = 0.7 (possibility of crossover); Pmutation = 0.1 (possibility of mutation)