| Issue |
E3S Web Conf.
Volume 680, 2025
The 4th International Conference on Energy and Green Computing (ICEGC’2025)
|
|
|---|---|---|
| Article Number | 00119 | |
| Number of page(s) | 14 | |
| DOI | https://doi.org/10.1051/e3sconf/202568000119 | |
| Published online | 19 December 2025 | |
Comparison of Ordinal Logistic Regression, XGBoost, and TabNet Models for Air Quality Classification in Jakarta City
1 Statistics Department, School of Computer Science, Bina Nusantara University Jakarta, Indonesia 11480
2 Computer Science Department, School of Computer Science, Bina Nusantara University Jakarta, Indonesia 11480
* Corresponding author: theophilus.tanudjaja@binus.ac.id, syarifah.permai@binus.ac.id
This study aims to compare the performance of statistical, machine learning, and deep learning models in solving the air quality classification problem in Jakarta province over the period from 2018 to 2024. The dataset used in this research was obtained from the ‘Satu Data Indonesia’ website, specifically the daily air quality data ISPU (Indeks Standar Pencemar Udara). Specifically, the models evaluated in this study include Ordinal Logistic Regression, XGBoost, and TabNet, and their performance is assessed using several evaluation metrics, such as precision, recall, F1-score, and accuracy. The research process is divided into several stages, including hyperparameter tuning, to enhance model performance. The dataset consists of daily air quality data, with variables such as PM₁₀, SO₂, CO, O₃, and NO₂. The results indicate that the XGBoost model outperforms the other models.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.