Skip to main content
. 2024 Oct 17;19(10):e0305630. doi: 10.1371/journal.pone.0305630

Table 3. Hyperparameters and layer configurations for the LSTM model.

Type of Layer Tuning hyperparameter Value
LSTM
LSTM dropout [0.00, 0.05, 0.10, 0.15, 0.20, 0.25, 0.30, 0.35, 0.40, 0.45, 0.50]
LSTM
LSTM units [70, 60, 50, 40]
Dense - units 3
-activation softmax
Adam optimization compile learning rate minvalue = 1e−10
maxvalue = 1e−1
sampling = LOG