Real-Time Air Quality Monitoring Using Artificial Intelligence (AI) and Internet of Things (IoT)

Air pollution remains a significant global challenge, posing severe risks to public health and the environment. The integration of Artificial Intelligence (AI) and the Internet of Things (IoT) has revolutionized real-time air quality monitoring, enabling proactive pollution control measures. This study presents a novel AI and IoT-enabled system for real-time air quality assessment, focusing on carbon monoxide (CO) emissions. The IoT network comprises sensors that continuously collect air quality data, transmitting it to a cloud-based server for real-time analysis. Four AI models Linear Regression, Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), and K-Nearest Neighbors (KNN) - are employed to predict air pollution levels. Model performance is evaluated using mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and R-squared R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> metrics. Results demonstrate that all models effectively predict PM2.5 levels, with LSTM outperforming others (MAE: 3.29573, RMSE: 5.44488, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>:0.952). The findings highlight the system's potential for real-time air quality monitoring, enabling informed decision-making and prompt intervention strategies. Future work will extend monitoring to additional pollutants, leveraging advanced AI techniques for enhanced predictive accuracy.