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

Table 9

Summary results of 1DCNN with two convolutional layers architectures.

Architecture	Activation function	Mean
		RMSE	MAPE	IOA	R^2
CNN	Linear	19.557	0.2411	0.8694	0.5952
	ReLU	23.0543	0.2759	0.8278	0.4373
	Sigmoid	21.2224	0.2602	0.8633	0.5229
	Softplus	21.2177	0.2586	0.8541	0.5233
Total		21.2628	0.2589	0.8537	0.5197