Machine-Learning Approach to Optimize SMOTE Ratio in Class Imbalance Dataset for Intrusion Detection

Table 10

SVR and SVM parameters.

SVR parameters		Values	SVM parameters	Values
Batch size		100	Batch size	100
C		1	c	1
Filter type		Normalize training data	Filter type	Normalize training data
Kernel		PolyKernel	Epsilon	1.00E–12
RegSMOImproved optimizer	Epsilon	1.0E–12	Calibrator	Logistic
	Epsilon Param.	0.001	Kernel	PolyKernel
	Tolerance	0.001	Tolerance Param.	0.001