Journal of Cloud Computing

Advances, Systems and Applications

Table 1 Parameters setting for the algorithms used in this study

From: AIoT-driven multi-source sensor emission monitoring and forecasting using multi-source sensor integration with reduced noise series decomposition

Parameters	LSTM	Bi-LSTM	VMD-LSTM	EEMD-LSTM	EEMD-CEEMDAN-LSTM
Number of IMFs				6	6
Alpha			2000
Win length	3	3	3	3	3
Batch size	64	64	64	64	64
Drop out	0.2	0.2	0.2	0.2	0.2
Learning rate	0.008	0.008	0.008	0.008	0.008
Epochs	500	500	500	500	500

Back to article page