Fine Dust Forecast Based on Recurrent Neural Networks

被引：0

作者：

Kang, Sunwon ^{[1
]}

Kim, Namgi ^{[1
]}

Lee, Byoung-Dai ^{[1
]}

机构：

[1] Kyonggi Univ, Div Comp Sci & Engn, Kyonggi, South Korea

来源：

2019 21ST INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY (ICACT): ICT FOR 4TH INDUSTRIAL REVOLUTION | 2019年

关键词：

Deep learning; RNN; TensorFlow (2 (sic));

D O I：

10.23919/icact.2019.8701978

中图分类号：

TN [电子技术、通信技术];

学科分类号：

0809 ;

摘要：

In this paper, we propose a fine dust forecast model based on deep neural networks. The proposed model uses five kinds of air quality-related information as input variables and presents fine dust levels on an hourly basis. For training, we built training datasets by crawling air quality open data provided by the Korea Meteorological Administration and Seoul City. According to the experimental results, the proposed method achieved an RMSE of 8.966 for the prediction of fine dust levels after one hour.

引用

页码：456 / 459

页数：4