Advances in Artificial Intelligence / 2011 / Article / Tab 2

Research Article

Development of Artificial Neural-Network-Based Models for the Simulation of Spring Discharge

Table 2

Selection of the best model from the quick-propagation algorithm.

Model inputsNo. of inputsAlgorithmArchitectureNo. of hidden layerTrainingTestingValidation
RDCRDCRDC

Rt, Et, Tt3[3-2-1]One 0.710 0.039 0.582 −0.179 0.586 −0.626
Qt−1, Rt, Rt−1, Et, Et−1, Tt, Tt−17[ 7-7-1]One
Qt1, Qt2, Rt, Rt1, Rt2, Et, Et1, Et2, Tt, Tt1, Tt211[11-14-1]One 0.984 0.967 0.981 0.963 0.965 0.922
Qt1, Qt2, Qt3, Rt, Rt1, Rt2, Rt3, Et, Et1, Et2,Et3, Tt, Tt1, Tt2, Tt315[15-15-1]One 0.996 0.993 0.977 0.952 0.974 0.944
Qt1, Qt2, Qt3, Qt4, Rt, Rt1, Rt2, Rt3, Rt4, Et, Et1, Et2, Et3, Et4, Tt, Tt1, Tt2, Tt3, Tt419Quick propagation[19-30-1]One 0.997 0.995 0.931 0.854 0.970 0.936
Rt, Et, Tt3[3-2-2-1]Two 0.626 −0.499 0.611 −0.187 0.646 −0.233
Qt1, Rt, Rt1, Et, Et1, Tt, Tt17[7-4-5-1]Two 0.988 0.975 0.975 0.941 0.985 0.970
Qt−1, Qt−2, Rt, Rt−1, Rt−2, Et, Et−1, Et−2, Tt, Tt−1, Tt−211[ 11-6-5-1]Two
Qt−1, Qt−2, Qt−3, Rt, Rt−1, Rt−2, Rt−3, Et, Et−1, Et−2,Et−3, Tt, Tt−1, Tt−2, Tt−315[15-11-14-1]Two 0.998 0.996 0.979 0.948 0.979 0.950
Qt−1, Qt−2, Qt−3, Qt−4, Rt, Rt−1, Rt−2, Rt−3, Rt−4, Et, Et−1, Et−2, Et−3, Et−4, Tt, Tt−1, Tt−2, Tt−3, Tt−419[19-10-13-1]Two 0.998 0.960 0.990 0.978 0.978 0.965

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.