Analisa Perbandingan Model Machine Learning Untuk Prediksi Dampak Kesehatan Dari Kualitas Udara
DOI:
https://doi.org/10.22441/jitkom.v10i1.007Keywords:
air quality prediction, health impact classification, machine learning, Random Forest, Extreme Gradient Boosting, SMOTE, public health analyticsAbstract
Polusi udara masih menjadi salah satu permasalahan kesehatan masyarakat yang paling serius di tingkat global, karena paparan jangka panjang terhadap polutan berbahaya dapat meningkatkan risiko penyakit pernapasan, gangguan kardiovaskular, serta angka rawat inap. Penelitian ini bertujuan untuk membandingkan kinerja prediktif dua model machine learning berbasis ensemble, yaitu Random Forest dan Extreme Gradient Boosting (XGBoost), dalam mengklasifikasikan tingkat dampak kesehatan berdasarkan indikator kualitas udara. Penelitian ini menggunakan Air Quality and Health Impact Dataset yang diperoleh dari Kaggle dan menerapkan tahapan metodologi yang sistematis, meliputi analisis data eksploratif, prapemrosesan data, penskalaan fitur, penanganan ketidakseimbangan kelas menggunakan stratified sampling dan metode Synthetic Minority Over-sampling Technique (SMOTE), pembangunan model baseline, serta optimasi hiperparameter menggunakan RandomizedSearchCV. Dataset mencakup konsentrasi polutan udara (PM2.5, PM10, NO₂, SO₂, dan O₃), variabel meteorologi, serta indikator kesehatan harian. Hasil eksperimen menunjukkan bahwa kedua model mampu mempelajari pola hubungan antara paparan polusi udara dan risiko kesehatan masyarakat, namun XGBoost secara konsisten menunjukkan performa yang lebih unggul dibandingkan Random Forest. Setelah proses tuning, model XGBoost mencapai tingkat akurasi sebesar 0,9003 dengan nilai F1-score tertimbang sebesar 0,8902. Analisis feature importance menunjukkan bahwa indeks kualitas udara, partikulat PM2.5 dan PM10, konsentrasi ozon, serta jumlah rawat inap merupakan faktor yang paling berpengaruh dalam proses klasifikasi. Secara keseluruhan, hasil penelitian ini menegaskan bahwa Extreme Gradient Boosting merupakan pendekatan yang andal dan efektif untuk memprediksi dampak kesehatan akibat kualitas udara, serta memiliki potensi besar untuk mendukung pengembangan sistem peringatan dini dan kebijakan kesehatan lingkungan berbasis data.References
[1] Y. Chen et al., “Examining the importance of built and natural environment factors in predicting self-rated health in older adults: An extreme gradient boosting (XGBoost) approach,” Journal of Cleaner Production, vol. 413, p. 137432, Aug. 2023, doi: 10.1016/j.jclepro.2023.137432.
[2] M. Zamani Joharestani, C. Cao, X. Ni, B. Bashir, and S. Talebiesfandarani, “PM2.5 Prediction Based on Random Forest, XGBoost, and Deep Learning Using Multisource Remote Sensing Data,” Atmosphere, vol. 10, no. 7, p. 373, July 2019, doi: 10.3390/atmos10070373.
[3] A. M. Sapari, A. I. Hadiana, F. R. Umbara, “Air quality classification using extreme gradient boosting (XGBOOST) algorithm,” Innovation in Research of Informatics and Computing, 2023.
[4] S. Tırınk, “Machine learning-based forecasting of air quality index under long-term environmental patterns: A comparative approach with XGBoost, LightGBM, and SVM,” PLOS One, vol. 20, no. 10, p. e0334252, Oct. 2025, doi: 10.1371/journal.pone.0334252.
[5] F. P. Arifianti and A. Salam, “XGBoost and Random Forest Optimization using SMOTE to Classify Air Quality,” Advance Sustainable Science, Engineering and Technology, vol. 6, no. 1, p. 02401025, Jan. 2024, doi: 10.26877/asset.v6i1.18136.
[6] B. Liu, X. Tan, Y. Jin, W. Yu, and C. Li, “Application of RR-XGBoost combined model in data calibration of micro air quality detector,” Scientific Reports, vol. 11, no. 1, Aug. 2021, doi: 10.1038/s41598-021-95027-1.
[7] J. Yang, Y. Tian, and C. H. Wu, “Air Quality Prediction and Ranking Assessment Based on Bootstrap-XGBoost Algorithm and Ordinal Classification Models,” Atmosphere, vol. 15, no. 8, p. 925, Aug. 2024, doi: 10.3390/atmos15080925.
[8] W. Ni et al., “Classification and Concentration Predictions of Volatile Organic Compounds Using an Electronic Nose Based on XGBoost-Random Forest Algorithms,” IEEE Sensors Journal, vol. 24, no. 1, pp. 671–678, Jan. 2024, doi: 10.1109/jsen.2023.3304355.
[9] S. Poupry, C. Béler, and K. Medjaher, “Development of a reliable measurement station for air quality monitoring based on low-cost sensors and active redundancy,” IFAC-PapersOnLine, vol. 55, no. 5, pp. 7–12, 2022, doi: 10.1016/j.ifacol.2022.07.631.
[10] Z. Jiang et al., “Characteristics of ambient air quality and its air quality index (AQI) model in Shanghai, China,” Science of The Total Environment, vol. 896, p. 165284, Oct. 2023, doi: 10.1016/j.scitotenv.2023.165284
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jurnal Ilmu Teknik dan Komputer
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International 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.
