Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JOMLAI: Journal of Machine Learning and Artificial Intelligence
Arfany Dhimas Muftareza
Unknown Affiliation
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : JOMLAI: Journal of Machine Learning and Artificial Intelligence

 1 
Comparative Evaluation of MLR and SVM Algorithms for DKI Jakarta Air Quality Prediction Arfany Dhimas Muftareza
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 4 No. 2 (2025): Juni 2025
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v4i2.5369

Abstract

This research explores the application of Machine Learning using Multiple Linear Regression (MLR) and Support Vector Machine (SVM) algorithms to predict air quality categories in Jakarta based on key pollutant parameters, such as PM10, PM2.5, NO2, CO, SO2, and O3. The dataset used comes from ISPU data measured from five Air quality monitoring stations in DKI Jakarta Province in 2021. The research process includes data collection, data cleaning, model implementation using the scikit-learn library, and model performance evaluation using Accuracy, R-Squared, RMSE, and MAE metrics. The results of model performance evaluation show that SVM performs better than MLR, as evidenced by higher accuracy value (91.78% vs. 90.41%), higher R-squared value (69.63% vs. 64.56%), lower RMSE value (0.2867 vs. 0.3097), and lower MAE value (0.0822 vs. 0.0959), indicating that the error in SVM model is smaller than MLR. This study proves the effectiveness of machine learning-based models in providing accurate air quality category predictions, although there are still challenges in predicting the “Good” category that require further development, such as balancing data and advanced feature engineering to improve the prediction accuracy of all categories.
Co-Authors