Adaptive graph convolutional imputation network for environmental sensor data recovery

Simple item page
dc.contributor.authorChen, Fanglanen
dc.contributor.authorWang, Dongjieen
dc.contributor.authorLei, Shuoen
dc.contributor.authorHe, Jianfengen
dc.contributor.authorFu, Yanjieen
dc.contributor.authorLu, Chang-Tienen
dc.date.accessioned2023-04-20T13:11:36Zen
dc.date.available2023-04-20T13:11:36Zen
dc.date.issued2022-11en
dc.description.abstractEnvironmental sensors are essential for tracking weather conditions and changing trends, thus preventing adverse effects on species and environment. Missing values are inevitable in sensor recordings due to equipment malfunctions and measurement errors. Recent representation learning methods attempt to reconstruct missing values by capturing the temporal dependencies of sensor signals as handling time series data. However, existing approaches fall short of simultaneously capturing spatio-temporal dependencies in the network and fail to explicitly model sensor relations in a data-driven manner. In this work, we propose a novel Adaptive Graph Convolutional Imputation Network for missing value imputation in environmental sensor networks. A bidirectional graph convolutional gated recurrent unit module is introduced to extract spatio-temporal features which takes full advantage of the available observations from the target sensor and its neighboring sensors to recover the missing values. In addition, we design an adaptive graph learning layer that learns a sensor network topology in an end-to-end framework, in which no prior network information is needed for capturing spatial dependencies. Extensive experiments on three real-world environmental sensor datasets (solar radiation, air quality, relative humidity) in both in-sample and out-of-sample settings demonstrate the superior performance of the proposed framework for completing missing values in the environmental sensor network, which could potentially support environmental monitoring and assessment.en
dc.description.notesFunding This research was partially supported by Virginia Tech's Open Access Subvention Fund, and the National Science Foundation (NSF) via the grant numbers: IIS-2045567, IIS-2006889, IIS-2040950, IIS-1755946.en
dc.description.sponsorshipVirginia Tech's Open Access Subvention Fund; National Science Foundation (NSF); [IIS-2045567]; [IIS-2006889]; [IIS-2040950]; [IIS-1755946]en
dc.description.versionPublished versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.3389/fenvs.2022.1025268en
dc.identifier.eissn2296-665Xen
dc.identifier.other1025268en
dc.identifier.urihttp://hdl.handle.net/10919/114592en
dc.identifier.volume10en
dc.language.isoenen
dc.publisherFrontiersen
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectmissing data imputationen
dc.subjectadaptive graph learningen
dc.subjectspatio-temporal deep learningen
dc.subjectgraph neural networken
dc.subjectenvironmental sensor networken
dc.titleAdaptive graph convolutional imputation network for environmental sensor data recoveryen
dc.title.serialFrontiers in Environmental Scienceen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
fenvs-10-1025268.pdf
Size:
1.43 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Scholarly Works, Computer Science