Skip to main content
. 2022 Jan 28;17(1):e0262708. doi: 10.1371/journal.pone.0262708

Fig 8. Univariate LSTM, BD-LSTM and ED-LSTM model performance accuracy (RMSE) with a random-split for the train and test datasets, and the test prediction horizons (steps).

Fig 8

The error bars represent the mean and 95% confidence interval for 30 experiment runs.