Real-time Haze Monitoring Based on Social Sensors

DOI

10.2991/amms-17.2017.89How to use a DOI?

Keywords

event detection; hazing monitoring; classifier; temporal model; social sensor

Abstract

Traditional environmental monitoring systems require distributed sensors to collect data, which is restricted by equipment deployment. In contrast, social sensor, oriented by Social Network users, offers real-time, widely-distributed and low-cost sensory information gathered and processed through vision, hearing, touch et al. As described in this paper, we present a real-time monitoring system based on Weibo streams to deal with the prediction problem of Haze. The system is composed of two core modules: one is a classifier-based sensor signal indicator to select timely haze data, and the other is a temporal prediction model to forecast haze. The experimental results on the Weibo stream of October, 2016, illustrate high consistency with the corresponding AQI record, and imply that the proposed system is sensitive to the air quality change trend even in user inactive period.

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  - Dandan Zhu
AU  - Chenchen Wang
AU  - Dong Chen
AU  - Zhihui Ye
AU  - Yuanfeng Lian
PY  - 2017/11
DA  - 2017/11
TI  - Real-time Haze Monitoring Based on Social Sensors
BT  - Proceedings of the 2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS 2017)
PB  - Atlantis Press
SP  - 402
EP  - 405
SN  - 1951-6851
UR  - https://doi.org/10.2991/amms-17.2017.89
DO  - 10.2991/amms-17.2017.89
ID  - Zhu2017/11
ER  -