Cargando…

Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks

To prevent severe air pollution, it is important to analyze time-series air quality data, but this is often challenging as the time-series data is usually partially missing, especially when it is collected from multiple locations simultaneously. To solve this problem, various deep-learning-based mis...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Taesung, Kim, Jinhee, Yang, Wonho, Lee, Hunjoo, Choo, Jaegul
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8618081/
https://www.ncbi.nlm.nih.gov/pubmed/34831969
http://dx.doi.org/10.3390/ijerph182212213
_version_ 1784604661880193024
author Kim, Taesung
Kim, Jinhee
Yang, Wonho
Lee, Hunjoo
Choo, Jaegul
author_facet Kim, Taesung
Kim, Jinhee
Yang, Wonho
Lee, Hunjoo
Choo, Jaegul
author_sort Kim, Taesung
collection PubMed
description To prevent severe air pollution, it is important to analyze time-series air quality data, but this is often challenging as the time-series data is usually partially missing, especially when it is collected from multiple locations simultaneously. To solve this problem, various deep-learning-based missing value imputation models have been proposed. However, often they are barely interpretable, which makes it difficult to analyze the imputed data. Thus, we propose a novel deep learning-based imputation model that achieves high interpretability as well as shows great performance in missing value imputation for spatio-temporal data. We verify the effectiveness of our method through quantitative and qualitative results on a publicly available air-quality dataset.
format Online
Article
Text
id pubmed-8618081
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86180812021-11-27 Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks Kim, Taesung Kim, Jinhee Yang, Wonho Lee, Hunjoo Choo, Jaegul Int J Environ Res Public Health Article To prevent severe air pollution, it is important to analyze time-series air quality data, but this is often challenging as the time-series data is usually partially missing, especially when it is collected from multiple locations simultaneously. To solve this problem, various deep-learning-based missing value imputation models have been proposed. However, often they are barely interpretable, which makes it difficult to analyze the imputed data. Thus, we propose a novel deep learning-based imputation model that achieves high interpretability as well as shows great performance in missing value imputation for spatio-temporal data. We verify the effectiveness of our method through quantitative and qualitative results on a publicly available air-quality dataset. MDPI 2021-11-20 /pmc/articles/PMC8618081/ /pubmed/34831969 http://dx.doi.org/10.3390/ijerph182212213 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kim, Taesung
Kim, Jinhee
Yang, Wonho
Lee, Hunjoo
Choo, Jaegul
Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks
title Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks
title_full Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks
title_fullStr Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks
title_full_unstemmed Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks
title_short Missing Value Imputation of Time-Series Air-Quality Data via Deep Neural Networks
title_sort missing value imputation of time-series air-quality data via deep neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8618081/
https://www.ncbi.nlm.nih.gov/pubmed/34831969
http://dx.doi.org/10.3390/ijerph182212213
work_keys_str_mv AT kimtaesung missingvalueimputationoftimeseriesairqualitydataviadeepneuralnetworks
AT kimjinhee missingvalueimputationoftimeseriesairqualitydataviadeepneuralnetworks
AT yangwonho missingvalueimputationoftimeseriesairqualitydataviadeepneuralnetworks
AT leehunjoo missingvalueimputationoftimeseriesairqualitydataviadeepneuralnetworks
AT choojaegul missingvalueimputationoftimeseriesairqualitydataviadeepneuralnetworks