Data Driven based PM2.5 Concentration Forecasting

DOI

10.2991/bep-16.2017.64How to use a DOI?

Keywords

SVR modeling; PM2.5 concentration forecasting; data-driven

Abstract

A PM2.5 concentration prediction approach using data-driven model is proposed in this paper, which uses support vector machine regression (SVR) and SVR combined with Particle Swarm Optimization (PSO) respectively. The forecast results have a certain advantageous by comparing PSO-SVR prediction model and single SVR model. In PSO-SVR prediction model, the parameters of the SVR are optimized by particle swarm optimization algorithm. Then PM2.5 concentration of regional air can be precisely forecasted by using this method. The simulation results show that the PSO-SVR model is a good forecasting method.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Haiqin LI
AU  - Xuhua SHI
PY  - 2016/12
DA  - 2016/12
TI  - Data Driven based PM2.5 Concentration Forecasting
BT  - Proceedings of the 2016 International Conference on Biological Engineering and Pharmacy (BEP 2016)
PB  - Atlantis Press
SP  - 301
EP  - 304
SN  - 2468-5747
UR  - https://doi.org/10.2991/bep-16.2017.64
DO  - 10.2991/bep-16.2017.64
ID  - LI2016/12
ER  -