Radial Basis Function Neural Network Based on an Improved Exponential Decreasing Inertia Weight-Particle Swarm Optimization Algorithm for AQI Prediction

Table 1

Values of inertia weight 𝜔 by the proposed adaption when 𝑡=𝑇, for varying sets of {𝑐, 𝜔_max, 𝜔_min}.

𝑐	𝜔max	𝜔min	𝜔max	𝜔min	𝜔max	𝜔min	𝜔max	𝜔min	𝜔max	𝜔min	𝜔max	𝜔min
	0.7	0.2	0.9	0.2	0.7	0.3	0.9	0.3	0.7	0.4	0.9	0.4
1	0.3839		0.4575		0.4472		0.5207		0.5104		0.5839
2	0.2677		0.2947		0.3541		0.3812		0.4406		0.4677
3	0.2249		0.2349		0.3199		0.3299		0.4149		0.4249
4	0.2092		0.2128		0.3073		0.3110		0.4055		0.4092
5	0.2034		0.2047		0.3027		0.3040		0.4020		0.4034
6	0.2012		0.2017		0.3010		0.3015		0.4007		0.4012
7	0.2005		0.2006		0.3004		0.3005		0.4003		0.4005
8	0.2002		0.2002		0.3001		0.3002		0.4001		0.4002
9	0.2001		0.2001		0.3000		0.3001		0.4000		0.4001
10	0.2000		0.2000		0.3000		0.3000		0.4000		0.4000