Table 4.

The ranges for each hyperparameter

Optimizer	Category	Definition	Range
AO	CNN Learning	Loss Function	Categorical Crossentropy, Categorical Hinge, KL Divergence, Poisson, Squared Hinge, and Hinge
		Batch Size	From 8 to 64 with a step of 8
		Parameters (i.e., weights) & Optimizer	Adam, Nadam, Adagrad, Adadelta, Adamax, RMSProp, SGD, Ftrl, SGD Nesterov, RMSProp Centered, Adam, and AMSGrad
	CNN Model Structure	Dropout ratio	[0.0, 0.6]
		TL learning ratio	From 0 to 100 with a step of 1
	CNN Data Augmentation	Rotation Range	From 0 to 45 with a step of 1
		Width Shift Range	[0, 0.25]
		Height Shift Range
		Shear Range
		Zoom Range
		Horizontal Flipping	[True, False]
		Vertical Flipping
		Brightness Change (From)	[0.5, 2.0]
		Brightness Change (To)
GS	KNN	nNeighbors	[1, 2, 3, 5, 7, 10]
		leafSize	[1, 5, 10, 15]
		p	[1, 2]
	SVM	degree	[1, 2, 3, 4, 5]
		C	[0.1, 1, 10, 100, 1000]
		gamma	[1, 0.1, 0.01, 0.001, 0.0001]
		kernel	[Linear, Poly, RBF, Sigmoid, Precomputed]
	DT	criterion	[Gini, Entropy]
		splitter	[Best, Random]
		maxDepth	From 3 to 14 with a step of 1
	NB	alpha	[0, 0.1, 0.5, 1.0, 1.5, 2, 3, 5, 10]
	Variance Threshold	threshold	[0, 0.001, 0.005, 0.01, 0.05, 0.1, 0.5]