Back to Search
Start Over
Prediction of air quality in Shenzhen based on neural network algorithm.
- Source :
-
Neural Computing & Applications . Apr2020, Vol. 32 Issue 7, p1879-1892. 14p. - Publication Year :
- 2020
-
Abstract
- Urban air pollution is the most serious environmental pollution problem in China. It not only causes serious losses to our economy, but also brings great hidden dangers to the physical and mental health of urban residents. Therefore, it is urgent to prevent and control air pollution. Air quality prediction and forecasting must be carried out to prevent air pollution. Timely and accurate air quality prediction can not only help urban managers to make scientific and effective preventive measures, but also provide more healthy and safe travel strategies for urban residents. China's air monitoring system is gradually improving, its scale is expanding, and a large amount of air quality data is accumulating. With the rapid expansion of data scale, the traditional method of air quality prediction technology has been unable to deal with these massive data. In this paper, 365 sets of air pollutant data from January 1, 2018 to December 31, 2018 in Shen Zhen were used as experimental objects. The improved SAPSO algorithm and PSO algorithm were used to optimize the parameters of SVM model and construct the air quality evaluation model. By analyzing the classification results of air quality grade, selecting relevant data and using partial least squares, the correlation coefficient matrix is established for the classification results, and the pollutant factors affecting air quality in Shenzhen are obtained. The results are ideal, which provides a scientific theoretical basis for the prevention and control of air pollution and urban management planning. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09410643
- Volume :
- 32
- Issue :
- 7
- Database :
- Academic Search Index
- Journal :
- Neural Computing & Applications
- Publication Type :
- Academic Journal
- Accession number :
- 142471893
- Full Text :
- https://doi.org/10.1007/s00521-019-04492-3