Staff View: A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)

A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)

Presence of particulate matters with aerodynamic diameter of less than 2.5 mu m (PM2.5) in the atmosphere is fast increasing in Malaysia due to industrialization and urbanization. Prolonged exposure of PM2.5 can cause serious health effects to human. This research is aimed to identify the most relia...

Full description

Saved in:

Bibliographic Details
Main Authors:	Chinatamby, Pavithra, Jewaratnam, Jegalakshimi
Format:	Article
Published:	Pergamon-Elsevier Science Ltd 2023
Subjects:	GE Environmental Sciences TP Chemical technology
Online Access:	http://eprints.um.edu.my/38780/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.38780
record_format	eprints
spelling	my.um.eprints.387802023-12-01T01:15:52Z http://eprints.um.edu.my/38780/ A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN) Chinatamby, Pavithra Jewaratnam, Jegalakshimi GE Environmental Sciences TP Chemical technology Presence of particulate matters with aerodynamic diameter of less than 2.5 mu m (PM2.5) in the atmosphere is fast increasing in Malaysia due to industrialization and urbanization. Prolonged exposure of PM2.5 can cause serious health effects to human. This research is aimed to identify the most reliable model to predict the PM2.5 pollution using multi-layered feedforward-backpropagation neural network (FBNN). Air quality and meteorological data were collected from Department of Environment (DOE) Malaysia. Six different training algorithms consisting of thirteen various training functions were trained and compared. FBNN model with the highest coefficient cor-relation (R2) and lowest root mean square error (RMSE), mean absolute error (MAE) and mean absolute per-centage error (MAPE) were selected as the best performing model. Levenberg Marquardt (trainlm) is the best performing algorithms compared to other algorithms with R2 value of 0.9834 and the lowest error values for RMSE (2.3981), MAE (1.7843) and MAPE (0.1063). Pergamon-Elsevier Science Ltd 2023-03 Article PeerReviewed Chinatamby, Pavithra and Jewaratnam, Jegalakshimi (2023) A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN). Chemosphere, 317. ISSN 0045-6535, DOI https://doi.org/10.1016/j.chemosphere.2023.137788 <https://doi.org/10.1016/j.chemosphere.2023.137788>. 10.1016/j.chemosphere.2023.137788
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	GE Environmental Sciences TP Chemical technology
spellingShingle	GE Environmental Sciences TP Chemical technology Chinatamby, Pavithra Jewaratnam, Jegalakshimi A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)
description	Presence of particulate matters with aerodynamic diameter of less than 2.5 mu m (PM2.5) in the atmosphere is fast increasing in Malaysia due to industrialization and urbanization. Prolonged exposure of PM2.5 can cause serious health effects to human. This research is aimed to identify the most reliable model to predict the PM2.5 pollution using multi-layered feedforward-backpropagation neural network (FBNN). Air quality and meteorological data were collected from Department of Environment (DOE) Malaysia. Six different training algorithms consisting of thirteen various training functions were trained and compared. FBNN model with the highest coefficient cor-relation (R2) and lowest root mean square error (RMSE), mean absolute error (MAE) and mean absolute per-centage error (MAPE) were selected as the best performing model. Levenberg Marquardt (trainlm) is the best performing algorithms compared to other algorithms with R2 value of 0.9834 and the lowest error values for RMSE (2.3981), MAE (1.7843) and MAPE (0.1063).
format	Article
author	Chinatamby, Pavithra Jewaratnam, Jegalakshimi
author_facet	Chinatamby, Pavithra Jewaratnam, Jegalakshimi
author_sort	Chinatamby, Pavithra
title	A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)
title_short	A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)
title_full	A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)
title_fullStr	A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)
title_full_unstemmed	A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)
title_sort	performance comparison study on pm2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (fbnn)
publisher	Pergamon-Elsevier Science Ltd
publishDate	2023
url	http://eprints.um.edu.my/38780/
_version_	1784511851369857024
score	13.211869

A performance comparison study on PM2.5 prediction at industrial areas using different training algorithms of feedforward-backpropagation neural network (FBNN)

Similar Items