Safety Monitoring Model of a Super-High Concrete Dam by Using RBF Neural Network Coupled with Kernel Principal Component Analysis

Table 3

Parameters of RBF-NN.

Model	Input layer	Spread	Hidden nodes	Minimum RMSE
Model 1: PCA and RBF-NN	13	2.40	28	1.134
Model 2: K-type KPCA and RBF-NN	9	1.11	36	1.138
Model 3: Polynomial KPCA and RBF-NN	9	1.13	36	0.853
Model 4: Hybrid-KPCA and RBF-NN	9	1.33	36	0.819