Fuzzy Weighted Least Squares Support Vector Regression with Data Reduction for Nonlinear System Modeling

Table 4

Comparison results of the proposed method, [15], G-LSSVR and Local-LSSVR with the hyper-parameter set , and the overlap factor as 1.5 are shown for Example 2.

: the number of the SRMs	RMSE (Training)		RMSE (Testing)
	our approach	[15]	our approach	[15]
4-SRMs	0.0179	0.0325	0.0180	0.0327
6-SRMS	0.0180	0.0323	0.0180	0.0325
8-SRMs	0.0177	0.0316	0.0178	0.0317
10-SRMs	0.0175	0.0305	0.0175	0.0306
G-LSSVR	0.0289		0.0284
Local-LSSVR
M=49 training points	0.1210		0.1288
M=81 training points	0.0477		0.0558
M=121 training points	0.0249		0.0282
M=169 training points	0.0160		0.0190