Forecasting Geo-sensor data with participatory sensing based on dropout neural network

Jyun Yu Jiang, Cheng Te Li

研究成果: Conference contribution

摘要

Nowadays, geosensor data, such as air quality and traffic flow, have become more and more essential in people's daily life. However, installing geosensors or hiring volunteers at every location and every time is so expensive. Some organizations may have only few facilities or limited budget to sense these data. Moreover, people usually tend to know the forecast instead of ongoing observations, but the number of sensors (or volunteers) will be a hurdle to make precise prediction. In this paper, we propose a novel concept to forecast geosensor data with participatory sensing. Given a limited number of sensors or volunteers, participatory sensing assumes each of them can observe and collect data at different locations and at different time. By aggregating these sparse data observations in the past time, we propose a neural network based approach to forecast the future geosensor data in any location of an urban area. The extensive experiments have been conducted with large-scale datasets of the air quality in three cities and the traffic of bike sharing systems in two cities. Experimental results show that our predictive model can precisely forecast the air quality and the bike rentle traffic as geosensor data.

原文English
主出版物標題CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management
發行者Association for Computing Machinery
頁面2033-2036
頁數4
ISBN(電子)9781450340731
DOIs
出版狀態Published - 2016 十月 24
事件25th ACM International Conference on Information and Knowledge Management, CIKM 2016 - Indianapolis, United States
持續時間: 2016 十月 242016 十月 28

出版系列

名字International Conference on Information and Knowledge Management, Proceedings
24-28-October-2016

Other

Other25th ACM International Conference on Information and Knowledge Management, CIKM 2016
國家United States
城市Indianapolis
期間16-10-2416-10-28

指紋

Neural networks
Drop out
Sensor
Volunteers
Air quality
Experiment
Prediction
Traffic flow
Hiring
Urban areas

All Science Journal Classification (ASJC) codes

  • Business, Management and Accounting(all)
  • Decision Sciences(all)

引用此文

Jiang, J. Y., & Li, C. T. (2016). Forecasting Geo-sensor data with participatory sensing based on dropout neural network. 於 CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management (頁 2033-2036). (International Conference on Information and Knowledge Management, Proceedings; 卷 24-28-October-2016). Association for Computing Machinery. https://doi.org/10.1145/2983323.2983902
Jiang, Jyun Yu ; Li, Cheng Te. / Forecasting Geo-sensor data with participatory sensing based on dropout neural network. CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery, 2016. 頁 2033-2036 (International Conference on Information and Knowledge Management, Proceedings).
@inproceedings{cfde05f3c8244069b6b3a68a5fa1cb45,
title = "Forecasting Geo-sensor data with participatory sensing based on dropout neural network",
abstract = "Nowadays, geosensor data, such as air quality and traffic flow, have become more and more essential in people's daily life. However, installing geosensors or hiring volunteers at every location and every time is so expensive. Some organizations may have only few facilities or limited budget to sense these data. Moreover, people usually tend to know the forecast instead of ongoing observations, but the number of sensors (or volunteers) will be a hurdle to make precise prediction. In this paper, we propose a novel concept to forecast geosensor data with participatory sensing. Given a limited number of sensors or volunteers, participatory sensing assumes each of them can observe and collect data at different locations and at different time. By aggregating these sparse data observations in the past time, we propose a neural network based approach to forecast the future geosensor data in any location of an urban area. The extensive experiments have been conducted with large-scale datasets of the air quality in three cities and the traffic of bike sharing systems in two cities. Experimental results show that our predictive model can precisely forecast the air quality and the bike rentle traffic as geosensor data.",
author = "Jiang, {Jyun Yu} and Li, {Cheng Te}",
year = "2016",
month = "10",
day = "24",
doi = "10.1145/2983323.2983902",
language = "English",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "2033--2036",
booktitle = "CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management",

}

Jiang, JY & Li, CT 2016, Forecasting Geo-sensor data with participatory sensing based on dropout neural network. 於 CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, 卷 24-28-October-2016, Association for Computing Machinery, 頁 2033-2036, 25th ACM International Conference on Information and Knowledge Management, CIKM 2016, Indianapolis, United States, 16-10-24. https://doi.org/10.1145/2983323.2983902

Forecasting Geo-sensor data with participatory sensing based on dropout neural network. / Jiang, Jyun Yu; Li, Cheng Te.

CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery, 2016. p. 2033-2036 (International Conference on Information and Knowledge Management, Proceedings; 卷 24-28-October-2016).

研究成果: Conference contribution

TY - GEN

T1 - Forecasting Geo-sensor data with participatory sensing based on dropout neural network

AU - Jiang, Jyun Yu

AU - Li, Cheng Te

PY - 2016/10/24

Y1 - 2016/10/24

N2 - Nowadays, geosensor data, such as air quality and traffic flow, have become more and more essential in people's daily life. However, installing geosensors or hiring volunteers at every location and every time is so expensive. Some organizations may have only few facilities or limited budget to sense these data. Moreover, people usually tend to know the forecast instead of ongoing observations, but the number of sensors (or volunteers) will be a hurdle to make precise prediction. In this paper, we propose a novel concept to forecast geosensor data with participatory sensing. Given a limited number of sensors or volunteers, participatory sensing assumes each of them can observe and collect data at different locations and at different time. By aggregating these sparse data observations in the past time, we propose a neural network based approach to forecast the future geosensor data in any location of an urban area. The extensive experiments have been conducted with large-scale datasets of the air quality in three cities and the traffic of bike sharing systems in two cities. Experimental results show that our predictive model can precisely forecast the air quality and the bike rentle traffic as geosensor data.

AB - Nowadays, geosensor data, such as air quality and traffic flow, have become more and more essential in people's daily life. However, installing geosensors or hiring volunteers at every location and every time is so expensive. Some organizations may have only few facilities or limited budget to sense these data. Moreover, people usually tend to know the forecast instead of ongoing observations, but the number of sensors (or volunteers) will be a hurdle to make precise prediction. In this paper, we propose a novel concept to forecast geosensor data with participatory sensing. Given a limited number of sensors or volunteers, participatory sensing assumes each of them can observe and collect data at different locations and at different time. By aggregating these sparse data observations in the past time, we propose a neural network based approach to forecast the future geosensor data in any location of an urban area. The extensive experiments have been conducted with large-scale datasets of the air quality in three cities and the traffic of bike sharing systems in two cities. Experimental results show that our predictive model can precisely forecast the air quality and the bike rentle traffic as geosensor data.

UR - http://www.scopus.com/inward/record.url?scp=84996593736&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996593736&partnerID=8YFLogxK

U2 - 10.1145/2983323.2983902

DO - 10.1145/2983323.2983902

M3 - Conference contribution

AN - SCOPUS:84996593736

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 2033

EP - 2036

BT - CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery

ER -

Jiang JY, Li CT. Forecasting Geo-sensor data with participatory sensing based on dropout neural network. 於 CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Association for Computing Machinery. 2016. p. 2033-2036. (International Conference on Information and Knowledge Management, Proceedings). https://doi.org/10.1145/2983323.2983902