PM2.5 Monitoring and Prediction Based on IOT and RNN Neural Network

With the rapid development of social economy and the increasing improvement of people’s living standards, the consumption of fossil energy and the use of transportation are increasing day by day. Leading to a large number of PM2.5 and a variety of air pollutants increasingly serious problems. Therefore, it is very important to monitor and predict air quality and pollutant index in real time, and more accurate algorithms and more convenient visual interfaces can make people better understand the air pollution situation. it is of great significance to analyze the real-time changes in the concentration of air pollutants such as PM2.5 in the atmosphere as well as accurately forecast and early warning. This study monitors the contents of various gases in the atmosphere in real time by building an air quality monitoring platform. The structure and implementation process of the RNN and the neural network optimized by particle swarm optimization algorithm and genetic algorithm are analyzed and introduced. Various basic data of Nanjing city are taken as data samples, and the RNN under the action of the optimization algorithm is iteratively trained, and then the optimization of the two algorithms for the RNN is compared The improved particle swarm optimization algorithm is more advantageous