Data-driven Optimization of Public Transportation in Smart Cities
Reference persons LUCA VASSIO
External reference persons Skip to content
INDACO BIAZZO - Research Assistant - DISAT
Description Modern cities face new challenges for making an efficient and sustainable management of services and resources. The challenge for smart cities, and smart mobility in particular is to provide mobility to all the citizens in this context of rising population concentration and to make the city a more sustainable urban ecosystem.
Public Transportation plays a key role in this scenario, with a common challenge: limited resources to be optimized. Using tools to compute key metrics for assessing the quality of service of public transportation (see http://www.citychrone.org), the work of the thesis will be focused on optimizing the choice of new infrastructure. For example, the student will study the impact of a new line of metro within a city, optimizing its size and location.
Most of the problems arising in this field have a great computational complexity. Special attention will be paid to data-driven optimization algorithms and techniques, like for example Swarm Intelligence.
See also http://www.citychrone.org/world
Required skills Good programming languages knowledge (high level languages like Python)
Knowledge of optimization/operational research
Knowledge on statistics (regressions, probability estimations, etc.)
Deadline 20/03/2022 PROPONI LA TUA CANDIDATURA