New Strategy for Analog Circuit Performance Evaluation under Disturbance and Fault Value

Table 1

Result of data feature and comparative experiment of regression problem on experiment data.

TRSN	TESN	FN	Method	Parameter (𝜎,𝜀,𝛾)	SVN	TRMSE	TEMSE	CPU/s
259 × 100	59 × 100	8	MKALSSVR	(200, 0.1, 0.75)	30	1.6982𝑒−014	1.7001𝑒−028	0.021
259 × 100	59 × 100	8	LSSVR	(200, 0.1, /)	1376	4.5544𝑒−015	4.2437𝑒−012	2.981
259 × 100	59 × 100	8	𝜀-SVR	(200, 0.1, /)	1607	5.4003𝑒−017	5.3025𝑒−004	0.062

SVN denotes the number of support vector, TRSN denotes the number of training support vector, TESN denotes the number of testing support vector, FN denotes the number of the data feature, TEMSE denotes the testing data mean square error, and TDMSE denotes the training data mean square error.