Enhanced air quality prediction by edge-based spatiotemporal data preprocessing

Particulate matter with a diameter less than 2.5 micrometers (PM2.5) can be considered as the most dangerous air pollutant that affects human health. In addition, technological advances, such as those involving the Internet of Things (IoT) for monitoring air quality, have made it possible to monitor air quality for a lower cost. However, missing values and noisy data make nonlinear data provided by air quality IoT sensors less reliable and more complicated than data provided by air quality monitoring stations. In this study, we propose a mixed edge-based and cloud-based framework with the final goal of PM2.5 value prediction. In order to validate the proposed approach, we evaluate the quality of predictions using both original and preprocessed data on a real-world dataset from air quality sensors distributed in Calgary, Canada. Obtained results show an average improvement of 40.18% of the prediction accuracy on Mean Absolute Percentage Error by using the proposed preprocessing technique.