Staff View: Enhanced air quality index prediction using a hybrid convolutional network

Enhanced air quality index prediction using a hybrid convolutional network

Accurate air quality forecasting is critical for decreasing pollution and protecting public health. A hybrid model combining the Temporal Convolution Network (TCN) and the Graph Convolution Network (GCN) has been developed to predict air pollution with high accuracy and minimise the associated healt...

Full description

Saved in:

Bibliographic Details
Main Authors:	Pei-Chun Lin, Pei-Chun Lin, Arbaiy, Nureize, Yu, Chen-Yu, Mohd Salikon, Mohd Zaki
Format:	Conference or Workshop Item
Language:	English
Published:	2024
Subjects:	TD Environmental technology. Sanitary engineering
Online Access:	http://eprints.uthm.edu.my/11942/1/P17174_dfe5174c6d5badc8744a78af722c8558.pdf http://eprints.uthm.edu.my/11942/ https://doi.org/10.1007/978-3-031-66965-1_29
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uthm.eprints.11942
record_format	eprints
spelling	my.uthm.eprints.119422025-01-09T08:16:44Z http://eprints.uthm.edu.my/11942/ Enhanced air quality index prediction using a hybrid convolutional network Pei-Chun Lin, Pei-Chun Lin Arbaiy, Nureize Yu, Chen-Yu Mohd Salikon, Mohd Zaki TD Environmental technology. Sanitary engineering Accurate air quality forecasting is critical for decreasing pollution and protecting public health. A hybrid model combining the Temporal Convolution Network (TCN) and the Graph Convolution Network (GCN) has been developed to predict air pollution with high accuracy and minimise the associated health risks. Because air quality data has two crucial components: temporal trends and spatial linkages, the combination of TCN and GCN is required. The GCN model learns the complicated architecture of each observatory, whereas the TCN model uses past data to detect deviations. The Graph Temporal Convolution Network (GTCN) model was evaluated using six important variables: station names, Air Quality Index (AQI), data timestamps, longitude, and latitude. Our GTCN outperformed other researchers’ models on real-world data between February and July 2021. The results demonstrated the lowest Mean Absolute Error (MAE) of approximately 4.78 and the lowest Root Mean Square Error (RMSE) of approximately 6.67. Through precise air quality forecasting, people can pre-know how to protect themselves and prepare outdoor dresses well to reduce exposure to air pollution and related health hazards 2024 Conference or Workshop Item PeerReviewed text en http://eprints.uthm.edu.my/11942/1/P17174_dfe5174c6d5badc8744a78af722c8558.pdf Pei-Chun Lin, Pei-Chun Lin and Arbaiy, Nureize and Yu, Chen-Yu and Mohd Salikon, Mohd Zaki (2024) Enhanced air quality index prediction using a hybrid convolutional network. In: Recent Advances on Soft Computing and Data Mining. https://doi.org/10.1007/978-3-031-66965-1_29
institution	Universiti Tun Hussein Onn Malaysia
building	UTHM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Tun Hussein Onn Malaysia
content_source	UTHM Institutional Repository
url_provider	http://eprints.uthm.edu.my/
language	English
topic	TD Environmental technology. Sanitary engineering
spellingShingle	TD Environmental technology. Sanitary engineering Pei-Chun Lin, Pei-Chun Lin Arbaiy, Nureize Yu, Chen-Yu Mohd Salikon, Mohd Zaki Enhanced air quality index prediction using a hybrid convolutional network
description	Accurate air quality forecasting is critical for decreasing pollution and protecting public health. A hybrid model combining the Temporal Convolution Network (TCN) and the Graph Convolution Network (GCN) has been developed to predict air pollution with high accuracy and minimise the associated health risks. Because air quality data has two crucial components: temporal trends and spatial linkages, the combination of TCN and GCN is required. The GCN model learns the complicated architecture of each observatory, whereas the TCN model uses past data to detect deviations. The Graph Temporal Convolution Network (GTCN) model was evaluated using six important variables: station names, Air Quality Index (AQI), data timestamps, longitude, and latitude. Our GTCN outperformed other researchers’ models on real-world data between February and July 2021. The results demonstrated the lowest Mean Absolute Error (MAE) of approximately 4.78 and the lowest Root Mean Square Error (RMSE) of approximately 6.67. Through precise air quality forecasting, people can pre-know how to protect themselves and prepare outdoor dresses well to reduce exposure to air pollution and related health hazards
format	Conference or Workshop Item
author	Pei-Chun Lin, Pei-Chun Lin Arbaiy, Nureize Yu, Chen-Yu Mohd Salikon, Mohd Zaki
author_facet	Pei-Chun Lin, Pei-Chun Lin Arbaiy, Nureize Yu, Chen-Yu Mohd Salikon, Mohd Zaki
author_sort	Pei-Chun Lin, Pei-Chun Lin
title	Enhanced air quality index prediction using a hybrid convolutional network
title_short	Enhanced air quality index prediction using a hybrid convolutional network
title_full	Enhanced air quality index prediction using a hybrid convolutional network
title_fullStr	Enhanced air quality index prediction using a hybrid convolutional network
title_full_unstemmed	Enhanced air quality index prediction using a hybrid convolutional network
title_sort	enhanced air quality index prediction using a hybrid convolutional network
publishDate	2024
url	http://eprints.uthm.edu.my/11942/1/P17174_dfe5174c6d5badc8744a78af722c8558.pdf http://eprints.uthm.edu.my/11942/ https://doi.org/10.1007/978-3-031-66965-1_29
_version_	1821004331625742336
score	13.239859

Enhanced air quality index prediction using a hybrid convolutional network

Similar Items