<![CDATA[Air pollution has become a critical environmental and public health concern, particularly in urban areas where industrial activities and transportation contribute significantly to particulate matter emissions. The emergence of Internet of Things (IoT) technologies has enabled continuous and real-time monitoring of environmental conditions through distributed sensor networks. However, raw sensor data alone is insufficient without intelligent analysis for accurate forecasting and decision-making. This study proposes a machine learning-based approach for air quality prediction using IoT-derived environmental data. The Beijing PM2.5 dataset was utilized to simulate real-world IoT sensor measurements, incorporating meteorological and temporal features. Three machine learning models: Linear Regression, Random Forest, and Gradient Boosting were implemented and evaluated using standard performance metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and coefficient of determination (R²). Experimental results indicate that the Random Forest model achieved the best performance, with an RMSE of 47.05, and R² score of 0.75. In comparison, Gradient Boosting produced an RMSE of 66.27 and R² of 0.50, while Linear Regression showed the lowest performance with an RMSE of 80.14 and R² of 0.27. These results demonstrate that tree-based ensemble methods, particularly Random Forest, are more effective in capturing the nonlinear relationships present in environmental data. This work highlights the potential of integrating IoT sensing with machine learning models to support accurate air quality prediction and informed environmental management]]>
Copyrights © 2026
