A tuned LSTM with random forest feature selection and zero-crossing-based window sizes reports 54.05% lower RMSE than a standard LSTM on a single industrial boiler dataset, though the baseline is not fairly specified.
Time series prediction with recurrent neural networks trained by a hybrid pso–ea algorithm,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
LSTM-based Flow Prediction
A tuned LSTM with random forest feature selection and zero-crossing-based window sizes reports 54.05% lower RMSE than a standard LSTM on a single industrial boiler dataset, though the baseline is not fairly specified.