Table 1.

DeepD2V Hyper-parameters, search space, and recommendation.

Calibration Hyper-Parameters	Search Space	Recommendation
Convolutional layer number	{1, 3, 5, 7}	3
Learning rate	{$1\times {10}^{-2}$, $1\times {10}^{-3}$, $1\times {10}^{-4}$, $1\times {10}^{-5}$}	$1\times {10}^{-3}$
Batch Size	{1, 32, 64, 128, 256, 512}	64
Loss Function	/	Binary cross entropy
Optimizer	{Adam, AdaDelta}	Adam
Convolutional neurons number	{8, 16, 32, 64, 128}	16
Convolutional kernel size	{3, 9, 16, 24}	3
Max Pooling window size	{2, 4, 8}	2
Number of bi-LSTM neurons	{8, 16, 32, 64}	16
Dropout ratio	{0.1, 0.2, 0.5}	0.1