File Download
  Links for fulltext
     (May Require Subscription)

Conference Paper: A Gaussian Bayesian model to identify spatio-temporal causalities for air pollution based on urban big data

TitleA Gaussian Bayesian model to identify spatio-temporal causalities for air pollution based on urban big data
Authors
KeywordsAir pollution
Bayesian network (BN)
Causality analysis
Spatio-temporal (ST)
Urban big data
Issue Date2016
PublisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000359
Citation
The 35th IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS 2016): The 2nd IEEE INFOCOM Workshop on Smart Cities and Urban Computing (SmartCity 2016), San Francisco, CA., 11 April 2016. In 2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2016, p. 3-8 How to Cite?
AbstractIdentifying the causalities for air pollutants and answering questions, such as, where do Beijing's air pollutants come from, are crucial to inform government decision-making. In this paper, we identify the spatio-temporal (ST) causalities among air pollutants at different locations by mining the urban big data. This is challenging for two reasons: 1) since air pollutants can be generated locally or dispersed from the neighborhood, we need to discover the causes in the ST space from many candidate locations with time efficiency; 2) the cause-and-effect relations between air pollutants are further affected by confounding variables like meteorology. To tackle these problems, we propose a coupled Gaussian Bayesian model with two components: 1) a Gaussian Bayesian Network (GBN) to represent the cause-and-effect relations among air pollutants, with an entropy-based algorithm to efficiently locate the causes in the ST space; 2) a coupled model that combines cause-and-effect relations with meteorology to better learn the parameters while eliminating the impact of confounding. The proposed model is verified using air quality and meteorological data from 52 cities over the period Jun 1st 2013 to May 1st 2015. Results show superiority of our model beyond baseline causality learning methods, in both time efficiency and prediction accuracy. © 2016 IEEE.
DescriptionSession - Smart Cities and Urban Computing I
Persistent Identifierhttp://hdl.handle.net/10722/235847
ISBN
ISSN

 

DC FieldValueLanguage
dc.contributor.authorZhu, JY-
dc.contributor.authorZheng, Y-
dc.contributor.authorYi, X-
dc.contributor.authorLi, VOK-
dc.date.accessioned2016-11-03T04:32:01Z-
dc.date.available2016-11-03T04:32:01Z-
dc.date.issued2016-
dc.identifier.citationThe 35th IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS 2016): The 2nd IEEE INFOCOM Workshop on Smart Cities and Urban Computing (SmartCity 2016), San Francisco, CA., 11 April 2016. In 2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2016, p. 3-8-
dc.identifier.isbn978-146739955-5-
dc.identifier.issn0743-166X-
dc.identifier.urihttp://hdl.handle.net/10722/235847-
dc.descriptionSession - Smart Cities and Urban Computing I-
dc.description.abstractIdentifying the causalities for air pollutants and answering questions, such as, where do Beijing's air pollutants come from, are crucial to inform government decision-making. In this paper, we identify the spatio-temporal (ST) causalities among air pollutants at different locations by mining the urban big data. This is challenging for two reasons: 1) since air pollutants can be generated locally or dispersed from the neighborhood, we need to discover the causes in the ST space from many candidate locations with time efficiency; 2) the cause-and-effect relations between air pollutants are further affected by confounding variables like meteorology. To tackle these problems, we propose a coupled Gaussian Bayesian model with two components: 1) a Gaussian Bayesian Network (GBN) to represent the cause-and-effect relations among air pollutants, with an entropy-based algorithm to efficiently locate the causes in the ST space; 2) a coupled model that combines cause-and-effect relations with meteorology to better learn the parameters while eliminating the impact of confounding. The proposed model is verified using air quality and meteorological data from 52 cities over the period Jun 1st 2013 to May 1st 2015. Results show superiority of our model beyond baseline causality learning methods, in both time efficiency and prediction accuracy. © 2016 IEEE.-
dc.languageeng-
dc.publisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000359-
dc.relation.ispartof2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)-
dc.rights©2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectAir pollution-
dc.subjectBayesian network (BN)-
dc.subjectCausality analysis-
dc.subjectSpatio-temporal (ST)-
dc.subjectUrban big data-
dc.titleA Gaussian Bayesian model to identify spatio-temporal causalities for air pollution based on urban big data-
dc.typeConference_Paper-
dc.identifier.emailZheng, Y: zhy9639@hku.hk-
dc.identifier.emailLi, VOK: vli@eee.hku.hk-
dc.identifier.authorityLi, VOK=rp00150-
dc.description.naturepostprint-
dc.identifier.doi10.1109/INFCOMW.2016.7562036-
dc.identifier.scopuseid_2-s2.0-84988857295-
dc.identifier.hkuros265247-
dc.identifier.spage3-
dc.identifier.epage8-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 161103-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats