Citation

Majumder, Tahmida and Goh, Michael Kah Ong and Abdul Aziz, Nor Hidayati (2025) Air Quality Prediction with Bi-Directional Gated Recurrent Unit (Bi-GRU). In: 11th International Conference on Engineering and Emerging Technologies, ICEET 2025, 22 October 2025 - 23 October 2025, Kuala Lumpur.

Text IEEE Xplore Full-Text PDF_13.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

Air pollution is a global health concern due to the higher concentration levels of pollutants (PM₂.₅, PM₁₀, SO₂, NO₂, CO, O₃) found in the air. Accurate prediction of the concentration levels plays a crucial part in mitigating public health concerns. To resolve this problem, we propose a Bi-GRU-based deep learning model to aid in forecasting PM₂.₅ concentration levels. The proposed method utilizes a sliding window to retain past information to forecast for the future. The Bidirectional Gated Recurrent Unit (Bi-GRU) model was developed using a multistation dataset from Beijing. The model achieved an R² score of 0.95, MSE of 185.51, MAE of 9.7, and RMSE of 13.62. Compared to baseline models our model has shown significant improvement, suggesting its effectiveness in real-time air pollution monitoring and forecasting. Future studies ca

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Bidirectional Gated Recurrent Unit
Subjects:	T Technology > TD Environmental technology. Sanitary engineering > TD878-894 Special types of environment Including soil pollution, air pollution, noise pollution
Divisions:	Faculty of Engineering and Technology (FET) Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	20 Apr 2026 03:35
Last Modified:	20 Apr 2026 03:35
URII:	http://shdl.mmu.edu.my/id/eprint/15772

Downloads

Edit (login required)