IoT and ML for Air Pollution Monitoring with Real Time Data and Prediction of Health Advisory

Air pollution is a major environmental and health concern, especially in urban areas where high pollution levels can severely impact individuals with respiratory conditions. This paper presents an IoT and ML-based Air Pollution Monitoring System designed to provide real-time air quality monitoring, predictive analytics, and intelligent route optimization. The system utilizes an IoT module installed at traffic signals, equipped with air quality sensors to monitor CO, CO₂, and smoke levels. The collected data is displayed on an LCD screen, informing commuters of pollution levels and health advisories. A mobile application integrates real-time pollution data and ML-based predictions to assess outdoor safety, particularly for individuals with respiratory conditions. The system employs a Decision Tree Classifier to generate personalized health advisories based on pollution levels and user-reported symptoms. Additionally, the system offers intelligent route optimization, suggesting alternative routes with lower pollution exposure using real-time sensor data and historical trends. For seamless operation, Firebase is used for real-time data synchronization, ensuring accurate and timely updates. The integration of IoT and ML enables continuous air quality monitoring and proactive health measures. This research aims to enhance public awareness, encourage healthier urban mobility, and support smart city initiatives by providing data-driven insights and reducing pollution exposure risks.