Spatio-Temporal Prediction of Noise Pollution Using Participatory Sensing

Abstract

The physiological and psychological well-being of humans depends on an extensive set of factors, of which pollution is the most ubiquitous. Its effects are often latent but extremely detrimental, especially in the case of noise pollution. In pollution monitoring and smart city systems, predicting noise from urban road traffic is of utmost significance. It is a difficult task due to the complexity of spatial correlations among the locations and temporal correlations among the timestamps, coupled with the diverse nature of these spatio-temporal correlations which are also dependent on the type of area in which the locations are situated. As a solution, we propose a participatory sensing-based solution to assess the road traffic noise by attaining a high level of granularity. We subsequently predict the noise values with a hybrid predictor that uses a regression model and ordinary kriging. Our solution outperforms the baseline regression and kriging methods and thus provides a novel method to gain a deeper insight into the levels of road traffic noise pollution. The effectiveness and strength of the proposed method are validated by extensive experiments with a real-world participatory sensing-based road traffic noise dataset.