Robot Ground Media Classification Based on Hilbert–Huang Transform and Attention-Based Spatiotemporal Coupled Network

Table 1

Hyperparameter optimal combination.

Hyperparameter	Optimal value
Number of convolutional kernels	128
Size of convolutional kernel	3
Number of nodes of the LSTM layer	100
Time step of the LSTM	128
Probability values for the dropout layer	0.3
Learning rate	0.001