Characterization of Sustainable Mobility Models Using Machine Learning Architectures Applied to PID Signals Obtained via OBD II for the Study of Pollutant Emissions in the City of Cuenca

This research project addresses the issue of air pollution generated by the vehicle fleet in the city of Cuenca, Ecuador. Given the lack of accurate local models that account for vehicular technological diversity and driving styles, the research proposes a methodology based on the acquisition of on-board diagnostic (OBD II) data and the use of Machine Learning architectures. The technical approach consists of extracting and processing PID (Parameter Identification) signals to characterize engine behavior under different driving modes (Sport, Normal, Eco). Using tools such as Matlab and multivariate statistical analysis techniques, the project seeks to develop a robust model capable of estimating pollutant emissions and fuel consumption under real driving conditions. Expected results include the creation of an efficient driving manual and the publication of high-impact scientific articles. The project's impact extends to improving air quality, optimizing vehicle performance, and providing technical tools for the management of sustainable mobility in the city.<br/><br/><b>Goal</b>: <br/>Characterize sustainable mobility models by applying Machine Learning architectures to PID signals obtained via OBD II to study pollutant emissions in the city of Cuenca. The project aims to develop strategies to reduce the environmental impact of the local vehicle fleet.<br/><br/><b>Research lines</b>: <br/>Energy efficiency and environmental pollution