Indoor Air Quality Monitoring with IoT: Predicting PM10 for Enhanced Decision Support

Indoor air pollution is one of the major environmental hazards. Breathing in poor air can cause several serious health issues. Air quality is critical for building occupant's health and well-being. Hence, a reliable system to monitor indoor air quality (IAQ) is required. Advances in the prediction of pollutant conditions in the building environment can help occupants to take preventive actions. These interventions can avoid poisonous situations in useful time. This paper describes the functionality of the IAQ monitoring systems based on Internet of Things for measuring PM
₁₀
, PM
_2.5
, CO
₂
, VOC, Temperature, and Humidity parameters. The main contribution of this study is to propose an automated prediction system for PM
₁₀
. The XGBoost Regressor is applied to predict PM
₁₀
levels for enhanced decision support. The prediction system performance is measured in terms of six relevant regression parameters. The obtained values are RMSE=0.48, R2 Score=0.99, MSE=0.234, MAE=0.284, MAPE=3.24% and Prediction Accuracy = 98.15%. The results show the efficiency of the proposed system to support building managers and occupants to prevent critical consequences associated with poor air quality.