Research On Interactive Web Air Quality Monitoring Data Analysis Technology Based On Rstudio

In recent years,air pollution has become increasingly serious.Effective collection of air quality data,reasonable analysis of air quality data,and accurate prediction of air quality data will be of great significance to the control and prevention of air pollution.The main work of this paper is to study the air quality monitoring data of Shenyang City from November 2016 to March 2019,use R language analysis tools to analyze the characteristics of air pollutants,establish a recurrent neural network model to predict the concentration of pollutants,and thus provide Shenyang Governance of air pollution provides scientific basis and theoretical support.The main work of this paper is as follows:(1)The self-edited crawler program is used to obtain the air quality data of eight national control monitoring points in Shenyang.The outliers are identified by the box plot method and the missing value analysis is performed on the air quality data using the R "VIM" package.The missing values are interpolated using multiple interpolation methods.(2)The change of hourly mean concentration during heating and non-heating periods,monthly mean concentration and annual concentration of air pollutants in Shenyang city are analyzed.(3)The stepwise regression screening method and principal component analysis method are used to screen the input variables of the prediction model,and the selected variables are used as input variables to build the prediction model.Contrast experiments with univariate prediction models and full-variable prediction models.The experimental results show that the prediction model combined with stepwise regression screening method and long and short time memory network(LSTM)is better for the prediction of air pollutant concentration in Shenyang.(4)Development of an air quality monitoring data analysis system based on Ubuntu operating system,Shiny-server and R language.From the perspective ofpractical applications,the requirements around the system's low cost,visualization diversity,and interactivity.Visualize air quality data by combining GIS maps,time series charts,and calendar charts.Experiments show that the system can better analyze and process air quality data,provide users with interactive analysis tools,and realize that users can mine rules and information in air quality data from multiple angles.