Perbandingan Performa Algoritma Machine Learning untuk Prediksi Risiko Kesehatan dari Polusi Udara
Abstract
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.
Keywords
Full Text:
PDFReferences
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.
DOI: http://dx.doi.org/10.22441/fifo.2025.v17i2.002
Refbacks
- There are currently no refbacks.
Jurnal Ilmiah FIFO
Fakultas Ilmu Komputer Universitas Mercu Buana
Jl. Raya Meruya Selatan, Kembangan, Jakarta 11650
Tlp./Fax: +62215871335
p-ISSN: 2085-4315
e-ISSN: 2502-8332
http://publikasi.mercubuana.ac.id/index.php/fifo
e-mail:[email protected]
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
