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

Table 7

Results of 1DCNN with one convolutional layer architectures and full ensemble.

Architecture	Activation function	Kernel size	RMSE	MAPE	IOA	R^2
CNN	Linear	2	19.3736	0.2395	0.8782	0.6028
		3	19.3865	0.2365	0.8725	0.6023
		6	19.4022	0.2371	0.8695	0.6016