The Internet of Things (IoT) is a rising communication paradigm, allowing the interconnection of microcontroller-integrated devices via the Internet. In an urban context, the adoption of IoT technologies can lead to a better use of public urban resources, offering high-quality services to citizens while reducing the administrative operational cost. In Smart Cities, a plethora of useful ICT-enabled services can be provided to citizens -including waste management, noise monitoring, smart lighting and air quality monitoring. So far, air quality has been monitored in many cities, mostly by deploying fixed stations. Given the high cost of necessary equipment, the number of the fixed stations is limited; this results in low spatial resolution of air quality data. Low-cost sensing technologies overcome this challenge by providing higher spatial monitoring resolution at a lower cost. By deploying air quality sensors on moving vehicles, the spatial monitoring resolution improves without the need of deploying hundreds of fixed sensors. However, the collected air quality measurements often have low temporal resolution at specific locations because of the movement of the vehicles. Furthermore, there are still many locations that are not covered by the vehicles, leaving room for improving the spatial resolution. In this paper, we present an air quality monitoring system capable of real-time collection of air quality measurements from static reference stations and mobile sensors. To address the problem of spatiotemporal resolution, we introduce a method for processing and interpolating air quality data based on deep learning. Experiments with promising results conducted on data collected from the City-of-Things in Antwerp, Belgium show the effectiveness of the proposed method in comparison with state-of-the-art methods.
Do Huu, T, Rodrigo Bonet, E, Qin, X, Hofman, J, Nikolaou, M, Panzica La Manna, V, Philips, W & Deligiannis, N 2020, Deep-Learning-based Hyperlocal Air Quality Monitoring for Smart Cities. in International Environmental Modelling and Software Society (iEMSs 2020). 10th International Congress on Environmental Modelling and Software (iEMSs 2020), Brussels, Belgium, 14/09/20.
Do Huu, T., Rodrigo Bonet, E., Qin, X., Hofman, J., Nikolaou, M., Panzica La Manna, V., Philips, W., & Deligiannis, N. (Accepted/In press). Deep-Learning-based Hyperlocal Air Quality Monitoring for Smart Cities. In International Environmental Modelling and Software Society (iEMSs 2020)
@inproceedings{43f1b068d9cc4842953a72c66564b877,
title = "Deep-Learning-based Hyperlocal Air Quality Monitoring for Smart Cities",
abstract = "The Internet of Things (IoT) is a rising communication paradigm, allowing the interconnection of microcontroller-integrated devices via the Internet. In an urban context, the adoption of IoT technologies can lead to a better use of public urban resources, offering high-quality services to citizens while reducing the administrative operational cost. In Smart Cities, a plethora of useful ICT-enabled services can be provided to citizens -including waste management, noise monitoring, smart lighting and air quality monitoring. So far, air quality has been monitored in many cities, mostly by deploying fixed stations. Given the high cost of necessary equipment, the number of the fixed stations is limited; this results in low spatial resolution of air quality data. Low-cost sensing technologies overcome this challenge by providing higher spatial monitoring resolution at a lower cost. By deploying air quality sensors on moving vehicles, the spatial monitoring resolution improves without the need of deploying hundreds of fixed sensors. However, the collected air quality measurements often have low temporal resolution at specific locations because of the movement of the vehicles. Furthermore, there are still many locations that are not covered by the vehicles, leaving room for improving the spatial resolution. In this paper, we present an air quality monitoring system capable of real-time collection of air quality measurements from static reference stations and mobile sensors. To address the problem of spatiotemporal resolution, we introduce a method for processing and interpolating air quality data based on deep learning. Experiments with promising results conducted on data collected from the City-of-Things in Antwerp, Belgium show the effectiveness of the proposed method in comparison with state-of-the-art methods.",
keywords = "air quality interpolation, deep learning, IoT, smart city",
author = "{Do Huu}, Tien and {Rodrigo Bonet}, Esther and Xuening Qin and Jelle Hofman and Mania Nikolaou and {Panzica La Manna}, Valerio and Wilfried Philips and Nikolaos Deligiannis",
year = "2020",
month = sep,
day = "14",
language = "English",
booktitle = "International Environmental Modelling and Software Society (iEMSs 2020)",
note = "10th International Congress on Environmental Modelling and Software (iEMSs 2020), iEMSs ; Conference date: 14-09-2020 Through 18-09-2020",
url = "https://iemss2020.com/",
}