Perbandingan Performa Algoritma Machine Learning untuk Prediksi Risiko Kesehatan dari Polusi Udara
DOI:
https://doi.org/10.22441/fifo.2025.v17i2.002Keywords:
Polusi Udara, Kesehatan, Machine Learning, Support Vector Machines, Model PrediktifAbstract
Penelitian ini menggunakan berbagai algoritma pembelajaran mesin untuk menganalisis dan memprediksi hubungan antara polusi udara dan dampak kesehatan masyarakat. Dataset yang digunakan terdiri dari 968 instances dengan 15 fitur yang mencakup indikator kualitas udara (PM2.5, PM10, NO2, SO2, O3) dan data kesehatan (kunjungan rumah sakit, mortalitas, jenis penyakit) yang dikumpulkan dari lima kota besar di Indonesia selama periode Januari-Desember 2023. Lima algoritma pembelajaran mesin dievaluasi secara komprehensif: k-Nearest Neighbors (k-NN), Naive Bayes, Logistic Regression, Support Vector Machines (SVM), dan Neural Network. Kontribusi utama penelitian ini adalah menyediakan analisis komparatif komprehensif dari kelima algoritma tersebut menggunakan evaluasi multi-metrik dan optimasi hyperparameter khusus untuk domain prediksi kesehatan berbasis polusi udara. Hasil evaluasi menunjukkan bahwa algoritma SVM memiliki performa terbaik dengan akurasi 92%, presisi 98%, recall 96%, dan F1-Score 97%. Analisis korelasi mengungkapkan bahwa PM2.5 merupakan prediktor terkuat untuk penyakit respirasi dengan koefisien korelasi 0.78 terhadap kunjungan rumah sakit. Penelitian juga menemukan efek sinergis antara PM2.5 dan NO2 yang meningkatkan risiko kardiovaskular hingga 45%. Di sisi lain, algoritma Neural Network menunjukkan performa terendah dengan akurasi 50% meskipun telah dilakukan hyperparameter tuning ekstensif, mengindikasikan ketidakcocokan arsitektur untuk karakteristik dataset ini. Algoritma Naive Bayes dan Logistic Regression menunjukkan performa moderat dengan akurasi masing-masing 83% dan 88%. Temuan penelitian ini dapat dijadikan acuan untuk pengembangan sistem monitoring kesehatan real-time dan mendukung pengambilan kebijakan kesehatan masyarakat terkait pengendalian polusi udara di wilayah urban.
Downloads
References
M. Bondy, S. Roth, dan L. Sager, “Crime is in the air: The contemporaneous relationship between air pollution and crime,” J Assoc Environ Resour Econ, vol. 7, no. 3, hlm. 555–585, 2020, doi: 10.1086/707127.
N. S. Represa, A. Fernández-Sarría, A. Porta, dan J. Palomar-Vázquez, “Data mining paradigm in the study of air quality,” Environmental Processes, vol. 7, no. 1, hlm. 1–21, 2020, doi: 10.1007/s40710-019-00407-5.
I. Manisalidis, E. Stavropoulou, A. Stavropoulos, dan E. Bezirtzoglou, “Environmental and health impacts of air pollution: a review,” Front Public Health, vol. 8, hlm. 14, 2020, doi: 10.3389/fpubh.2020.00014.
K. K. Lee dkk., “Adverse health effects associated with household air pollution: a systematic review, meta-analysis, and burden estimation study,” Lancet Glob Health, vol. 8, no. 11, hlm. e1427–e1434, 2020, doi: 10.1016/S2214-109X(20)30343-0.
T. M. T. Lei, S. W. I. Siu, J. Monjardino, L. Mendes, dan F. Ferreira, “Using machine learning methods to forecast air quality: A case study in Macao,” Atmosphere (Basel), vol. 13, no. 9, hlm. 1412, 2022, doi: 10.3390/atmos13091412.
V. Calatayud dkk., “Machine learning model to predict vehicle electrification impacts on urban air quality and related human health effects,” Environ Res, vol. 226, hlm. 115835, 2023, doi: 10.1016/j.envres.2023.115835.
N. Temirbekov, M. Temirbekova, D. Tamabay, S. Kasenov, S. Askarov, dan Z. Tukenova, “Assessment of the Negative Impact of Urban Air Pollution on Population Health Using Machine Learning Method,” Int. J. Environ. Res. Public Health, vol. 20, no. 18, hlm. 6770, 2023, doi: 10.3390/ijerph20186770.
M. Castelli, F. M. Clemente, A. Popovič, S. Silva, dan L. Vanneschi, “A Machine Learning Approach to Predict Air Quality in California,” Complexity, vol. 2020, hlm. 1–23, 2020, doi: 10.1155/2020/8049504.
X. Liu, D. Lu, A. Zhang, Q. Liu, dan G. Jiang, “Data-Driven Machine Learning in Environmental Pollution: Gains and Problems,” Environ Sci Technol, vol. 56, no. 4, hlm. 2124–2133, 2022, doi: 10.1021/acs.est.1c06157.
A. Bekkar, B. Hssina, S. Douzi, dan K. Douzi, “Air-pollution prediction in smart city, deep learning approach,” J Big Data, vol. 8, no. 1, hlm. 161, 2021, doi: 10.1186/s40537-021-00548-1.
Y.-C. Liang, Y. Maimury, A. H.-L. Chen, dan J. R. C. Juarez, “Machine Learning-Based Prediction of Air Quality,” Applied Sciences, vol. 10, no. 24, hlm. 9151, 2020, doi: 10.3390/app10249151.
N. S. Pamungkas, Z. P. Putra, H. A. Pratama, dan M. Yusuf, “Supervised machine learning-based categorization and prediction of uranium adsorption capacity on various process parameters,” Journal of Hazardous Materials Advances, vol. 17, hlm. 100523, Feb 2025, doi: 10.1016/j.hazadv.2024.100523.
L. Berrang-Ford dkk., “Systematic mapping of global research on climate and health: a machine learning review,” Lancet Planet Health, vol. 5, no. 7, hlm. e514–e525, 2021, doi: 10.1016/S2542-5196(21)00179-0.
M. A. Cole, R. J. R. Elliott, dan B. Liu, “The Impact of the Wuhan Covid-19 Lockdown on Air Pollution and Health: A Machine Learning and Augmented Synthetic Control Approach,” Environ Resour Econ (Dordr), vol. 76, hlm. 553–580, 2020, doi: 10.1007/s10640-020-00483-4.
X. Zhang, Y. Yang, Y. Zhang, dan Z. Zhang, “Designing tourist experiences amidst air pollution: A spatial analytical approach using social media,” Ann Tour Res, vol. 84, hlm. 102999, 2020, doi: 10.1016/j.annals.2020.102999.
I. A. Rahman dkk., “Integration of machine learning models for enhancing radioactive waste management of disused sealed radioactive sources,” Nuclear Engineering and Design, vol. 442, hlm. 114272, Okt 2025, doi: 10.1016/j.nucengdes.2025.114272.
H. F. D. Supratman dkk., “Sorption and diffusion studies of radiocesium in soil samples from Ibu Kota Nusantara region of Indonesia,” Environmental Chemistry and Ecotoxicology, vol. 7, hlm. 252–262, 2025, doi: 10.1016/j.enceco.2024.12.008.
Y.-S. Chang, H.-T. Chiao, S. Abimannan, Y.-P. Huang, Y.-T. Tsai, dan K.-M. Lin, “An LSTM-based aggregated model for air pollution forecasting,” Atmos Pollut Res, vol. 11, no. 9, hlm. 1451–1463, 2020, doi: 10.1016/j.apr.2020.05.015.
B. Choubin dkk., “Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain,” Science of The Total Environment, vol. 701, hlm. 134474, 2020, doi: 10.1016/j.scitotenv.2019.134474.
N. Ma, D. Aviv, H. Guo, dan W. W. Braham, “Measuring the right factors: A review of variables and models for thermal comfort and indoor air quality,” Renewable and Sustainable Energy Reviews, vol. 135, hlm. 110436, 2021, doi: 10.1016/j.rser.2020.110436.
M. Mele dan C. Magazzino, “A Machine Learning analysis of the relationship among iron and steel industries, air pollution, and economic growth in China,” J Clean Prod, vol. 277, hlm. 123293, 2020, doi: 10.1016/j.jclepro.2020.123293.
P. Rusadi, Z. P. Pratama, H. A. Pratama, R. Sumarbagiono, dan M. Yusuf, “PREDICTING LONG-TERM REUSE UTILIZATION OF DISUSED SEALED RADIOACTIVE SOURCES THROUGH SUPPORT VECTOR MACHINE MODELS,” Journal of Advanced Research in Applied Sciences and Engineering Technology Journal homepage, doi: 10.37934/XXX.17.4.XX.
P. Rusadi dkk., “Synthetic Data for Radioactive Waste Management: A Comparative Study for Disused Sealed Radioactive Sources in Indonesia,” Nuclear Engineering and Technology, hlm. 103524, Feb 2025, doi: 10.1016/j.net.2025.103524.
W. Xing dan Y. Bei, “Medical Health Big Data Classification Based on KNN Classification Algorithm,” IEEE Access, vol. 8, hlm. 28808–28819, 2020, doi: 10.1109/ACCESS.2019.2955754.
O. Llaha, “Crime analysis and prediction using machine learning,” dalam 2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO), 2020, hlm. 496–501. doi: 10.23919/MIPRO48935.2020.9245120.
R. Katuwal, P. N. Suganthan, dan L. Zhang, “Heterogeneous oblique random forest,” Pattern Recognit, vol. 99, hlm. 107078, 2020, doi: 10.1016/j.patcog.2019.107078.
N. Nurajijah, “Sistem Pendukung Persetujuan Pembiayaan Koperasi Syariah,” EVOLUSI: Jurnal Sains dan Manajemen, vol. 11, no. 1, 2023, doi: 10.31289/evolusi.v11i1.9150.
Z. Li, F. Liu, W. Yang, S. Peng, dan J. Zhou, “A survey of convolutional neural networks: analysis, applications, and prospects,” IEEE Trans Neural Netw Learn Syst, vol. 33, no. 12, hlm. 6999–7019, 2021, doi: 10.1109/TNNLS.2021.3084827.
Downloads
Published
How to Cite
Issue
Section
License
The copyright to this article is transferred to Universitas Mercu Buana (UMB) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to UMB. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment.
We declare that this paper has not been published in the same form elsewhere.
Furthermore, I/We hereby transfer the unlimited rights of publication of the above-mentioned paper as a whole to UMB. The copyright transfer covers the right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Retained Rights/Terms and Conditions
Although authors are permitted to re-use all or portions of the Work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
Our Articles are licensed under CC BY-NC
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
