Parameter Selection Method for Support Vector Regression Based on Adaptive Fusion of the Mixed Kernel Function

Table 4

Results of sample prediction error.

Data	Statistical indicators	Algorithms
		Algo1	Algo2	Algo3	Algo4	Algo5
Train data	MAE	0.0053	0.0073	0.0094	0.0156	0.0200
	RMSE	0.0098	0.0146	0.0198	0.0298	0.0399
	SD	0.0060	0.0090	0.0110	0.0179	0.0228
Test data	MAE	0.0095	0.0128	0.0171	0.0208	0.0274
	RMSE	0.0111	0.0152	0.0195	0.0241	0.0319
	SD	0.0110	0.0150	0.0203	0.0252	0.0331

Here, MAE represents mean absolute error, RMSE represents mean square error, and SD represents standard deviation.