Analisis Ramalan Indeks Kualiti Udara berasaskan Pembelajaran Mesin melalui Aplikasi SEGAR
Keywords:
Indeks Kualiti Udara, Ramalan Kualiti Udara, Pembelajaran Mesin, Sistem Amaran AwalAbstract
Kajian ini membentangkan pembangunan aplikasi SEGAR, sebuah platform berteraskan pembelajaran mesin yang direka khusus untuk menganalisis dan meramal Indeks Kualiti Udara (AQI) di Shah Alam dan Cheras. Menggunakan set data 2018-2022, pembangunan model dimulakan dengan prosedur pembersihan data dan pengisian nilai hilang menggunakan teknik KNN-Imputer. Analisis perbandingan antara model MLR, SVR, dan RF membuktikan keupayaan prediktif algoritma RF yang paling jitu dalam mengenal pasti dinamik corak pencemaran yang kompleks dan tidak linear. Model RF tersebut kemudiannya diintegrasikan ke dalam aplikasi web SEGAR yang dilengkapi fungsi muat naik fail CSV, visualisasi data interaktif, dan mekanisme amaran awal. Rumusannya, SEGAR berpotensi bertindak sebagai sistem sokongan keputusan yang berwibawa bagi pihak berkuasa dalam memitigasi risiko kesihatan awam secara proaktif berasaskan data.
References
Abdul Rahman, A. S., Idris, A. Y., & Abdul Rahman, S. (2023). Evaluation of machine learning in predicting air quality index. Mathematical Sciences and Informatics Journal (MIJ), 4(1), 1-10.
Epa, U. (2018). Technical assistance document for the reporting of daily air quality–The Air Quality Index (AQI). Environmental Protection Agency.
Karimi, B., & Samadi, S. (2024). Long-term exposure to air pollution on cardio-respiratory, and lung cancer mortality: a systematic review and meta-analysis. Journal of Environmental Health Science and Engineering, 22(1), 75-95.
Latif, S. D., Almalayih, M., Yafouz, A., Ahmed, A. N., Zaini, N. a., Irwan, D., AlDahoul, N., Sherif, M., & El-Shafie, A. (2023). Prediction of atmospheric carbon monoxide concentration utilizing different machine learning algorithms: A case study in Kuala Lumpur, Malaysia. Environmental Technology & Innovation, 32, 103387.
Li, Z.-H., Wang, X.-M., Liao, D.-Q., Zhang, Q., Chen, Z.-T., Qiu, C.-S., Tang, X.-L., Li, H.-M., Du, L.-Y., & Zhang, P.-D. (2024). Long-term air pollutants exposure and respiratory mortality: A large prospective cohort study. Ecotoxicology and Environmental Safety, 274, 116176.
Méndez, M., Merayo, M. G., & Núñez, M. (2023). Machine learning algorithms to forecast air quality: a survey. Artificial intelligence review, 1.
Neo, E. X., Hasikin, K., Mokhtar, M. I., Lai, K. W., Azizan, M. M., Razak, S. A., & Hizaddin, H. F. (2022). Towards integrated air pollution monitoring and health impact assessment using federated learning: a systematic review. Frontiers in public health, 10, 851553.
Orellano, P., Kasdagli, M.-I., Velasco, R. P., & Samoli, E. (2024). Long-term exposure to particulate matter and mortality: an update of the WHO global air quality guidelines systematic review and meta-analysis. International journal of public health, 69, 1607683.
U.S. EPA. Communicating Air Quality Conditions: The Air Quality Index. Available online at: https://www.epa.gov/wildfire-smoke-course/communicating-air-quality-conditions-air-quality-index (accessed Disember 13, 2025).
Wang, B., Wang, B., Lv, B., & Wang, R. (2022). Impact of motor vehicle exhaust on the air quality of an urban city. Aerosol and Air Quality Research, 22(8), 220213.
Yohanna, E., & San, L. H. (2026). Comparative analysis of machine learning models for predicting PM₁₀ and PM2. 5 Concentrations in Pulau Pinang, Malaysia. Air Quality, Atmosphere & Health, 19(2), 21.
Zaini, N. a. (2025). Air quality forecasting and mapping in Malaysian urban areas: A hybrid deep learning approach
Zaini, N. a., Ean, L. W., Malek, M. A., Ahmed, A. N., & Chow, M. F. (2025). Forecasting of CO and O3 concentrations using optimized deep learning: A case study for Kuala Lumpur, Malaysia. AIP Conference Proceedings,
Zhang, X., Han, L., Wei, H., Tan, X., Zhou, W., Li, W., & Qian, Y. (2022). Linking urbanization and air quality together: A review and a perspective on the future sustainable urban development. Journal of Cleaner Production, 346, 130988.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Azizuddin Hanif, Zuraini Zainol, Ummul Fahri Abdul Rauf, Siti Hasliza Ahmad Rusmili, Yuhanim Hani Yahya, Puteri NE Nohuddin
This work is licensed under a Creative Commons Attribution 4.0 International License.
The authors of MJII retain copyright to the content of the articles.
The content is published under the Creative Commons Attribution (CC BY) 4.0 which allows content to be copied, adapted, displayed, distributed, republished, or otherwise re-used for any purpose, including for adaptation and commercial use provided the content is attributed without any restriction.
Authors Rights
The Journal grants you the following non-exclusive rights, subject to giving propoer acknowledgement to the original journal. The authors may:
(i) to reprint or reproduce the contribution, in whole or in part, in any publication of your interest.
(ii) to use material for teaching purposes; including availability of the matarial in academic course.
(iii) to post a copy of the contribution on your personal or institutional web server, provided that the server is non-commercial and there are no charges for access, and
(iv) to deposit a copy of the contribution in a non-commercial data repository maintained by an institution of which you are a member.
Author's Agreement
Author(s) guarantee the journal the following:
(i) that the contribution is their original work;
(ii) that it contains, no matter what, content that is defamatory or is otherwise unlawful or which invades rights of privacy or publicity or infringes any proprietary rights (including copyright);
(iii) that the contribution has not been published elsewhere in whole or in part and that no agreement to publish is outstanding other than this agreement. Author(s) agree to be responsible and hold the journal, its editors, staff and affiliate organizations harmless against any claims arising from or related to the breach or inaccuracy of any of the guarantees listed above.
Disclaimer
The editorial team of the MJII and the publication team of Academica Press Solutions share no responsibility regarding the views and opinions expressed by the authors.
The content published in MJII is Open Access and can be shared, adapted, reproduced, reprinted, after appropriate acknowledgment and giving due credit to the author(s) work.
