A NEW THICKNESS PREDICTION METHOD OF ATMOSPHERIC POLLUTANTS PM2.5 USING IMPROVED PSO-FNN COMBINED WITH DEEP CONFIDENCE NETWORK

Aiming at the serious threat of heavy haze pollution with PM2.5 as the main pollutant to the national economy and residents' health, an improved PSO combined with deep confidence network was proposed to predict the thickness of atmospheric pollutant PM2.5. Firstly, an improved particle swarm optimization (PSO) fuzzy neural network (FNN) was adopted to integrate algorithm with fuzzy-neural-network, and the characteristics of PSO algorithm in global optimization were given play to forecast the change law of PM2.5 particle thickness. Secondly, a DBN classifier with nonlinear feature extraction preprocessing mechanism is constructed by taking the extracted nonlinear features as input of deep brief networks (DBN). Finally, the effectiveness of the proposed method of predicting PM2.5 thickness of atmospheric pollutants with improved PSO combined with deep confidence network was verified by an example of influencing factor diagnosis and PM2.5 thickness prediction. And the results were compared with the traditional classifier, which showing the advantages of the proposed method in modeling accuracy and convergence speed.