Evaluation of Key Parameters Using Deep Convolutional Neural Networks for Airborne Pollution (PM10) Prediction

Table 11

Architectures present in 1DCNN ensemble.

Architecture	Activation function	First kernel size	Second kernel size	RMSE	MAPE	IOA	R^2
CNN	Linear	2	2	18.9024	0.215	0.8762	0.6093
		2	3
		2	5
		2	6
		4	2
		5	2
	ReLU	3	3
		6	2
	Sigmoid	2	2
		2	3
		2	4
	Softplus	2	2
		2	3