WIT Press


AIR POLLUTION PREDICTION SYSTEM USING DEEP LEARNING

Price

Free (open access)

Volume

230

Pages

9

Page Range

71 - 79

Published

2018

Paper DOI

10.2495/AIR180071

Copyright

WIT Press

Author(s)

THANONGSAK XAYASOUK, HWAMIN LEE

Abstract

One of the most influential factors on human health is air pollution, such as the concentration of PM10 and PM2.5 is a damage to a human. Despite the growing interest in air pollution in Korea, it is difficult to obtain accurate information due to the lack of air pollution measuring stations at the place where the user is located. Deep learning is a type of machine learning method has drawn a lot of academic and industrial interest. In this paper, we proposed a deep learning approach for the air pollution prediction in South Korea. We use Stacked Autoencoders model for learning and training data. The experiment results show the performance of the air pollution prediction system and model that proposed.

Keywords

fine dust, PM10, PM2.5, air pollution prediction, deep learning