This repository is the result of the BSc. thesis (TFG - Trabajo Fin de Grado) completed by José Ángel Martín Baos in order to finish his Bachelor's Degree in Computer Science in the University of Castilla-La Mancha (Ciudad Real).

Road transportation is often the main source of air pollution in urban areas with detrimental effects on local air quality, ecology, and human health. Therefore, there is an increasing need to estimate precisely the contribution of road transport to air pollution in the cities, so that pollution-reduction policies can be designed and implemented appropriately [SNB10]. These pollution-reduction policies are becoming increasingly relevant due to the continuous growth in vehicle use and the deterioration in driving conditions (congestion). Many authorities find it difficult to meet their environmental targets (e.g. air quality standards or national emission ceilings) and, therefore, reliable emission models are needed in order to predict accurately the impact of road transport on air pollution.

Therefore, intelligent cities are essential to prevent situations of high level contamination and take measures when these situations occur. Cities must be able to predict the pollution peaks and take palliative measures, such as the imposition of restrictions on the circulation of certain vehicles, for example by the license plates, closing traffic in some streets, lowering the speed limits, etc. Moreover, traffic flows must be monitored as they affect the pollution levels in that city. For this reason, these cities must rely on an Internet of Things (IoT) infrastructure connected to a cloud platform that supports those systems as well as sensor-based big data applications [Bib18].

Most common pollution surveillance and control systems are composed of big and expensive devices that are only located in some points in a city, hence, they provide information for vast areas and sometimes these systems are not scalable. However, cities are distributed environments where the events occur in real time and on a massive scale. Therefore, an inexpensive distributed IoT architecture is needed to control pollution levels by zones or streets. These can be combined with a traffic surveillance infrastructure in order to have a complete system that could be used as a Decision Support System (DSS) to help authorities to take decisions about environmental problems caused by pollution before they occur.

The objective in this Bachelor of Science (BSc.) thesis is to design and build a prototype of an integrated low-cost road traffic and air pollution monitoring platform. It only focuses on the design and implementation of the software and hardware architecture that should allow the future implementation of an intelligent system for the prediction of the pollution levels, the recommendation of palliative actions and monitoring those actions. An inexpensive embedded system will be used for designing the architecture in order to obtain a scalable system not only in size but also in cost.

The following diagram shows the system architecture of the complete intelligent system. Nevertheless, in this BSc. thesis only the monitoring infrastructure will be developed.

• [Bib18] Simon Elias Bibri. The IoT for smart sustainable cities of the future: An analytical framework for sensor-based big data applications for environmental sustainability. Sustainable Cities and Society, 38:230–253, 2018.
• [SNB10] Robin Smit, Leonidas Ntziachristos, and Paul Boulter. Validation of road vehicle and traffic emission models – a review and meta-analysis. Atmospheric Environment, 44:2943–2953, August 2010.

• José Ángel Martín Baos (JoseAngel.Martin@uclm.es)

• Dr. Luis Rodríguez Benítez (Luis.Rodriguez@uclm.es)
• Dr. Ricardo García Ródenas (Ricardo.Garcia@uclm.es)