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.
Full text not available from this repository.Abstract
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).
| Item Type: | Article |
|---|---|
| Funders: | Faculty of Engineering, University of Malaya (Grant No: GPF030A-2019) |
| Uncontrolled Keywords: | Air pollution; Prediction; PM2 5; Artificial neural network; Feedforward-backpropagation; Training algorithms |
| Subjects: | G Geography. Anthropology. Recreation > GE Environmental Sciences T Technology > TP Chemical technology |
| Divisions: | Faculty of Engineering > Department of Chemical Engineering |
| Depositing User: | Ms Zaharah Ramly |
| Date Deposited: | 01 Dec 2023 01:15 |
| Last Modified: | 01 Dec 2023 01:15 |
| URI: | http://eprints.um.edu.my/id/eprint/38780 |
Actions (login required)
 |
View Item |
