Home People Cenedese Research PSC - Padova Smart City

tl_files/utenti/angelocenedese/LOGOS/unipd_logo.jpg     tl_files/utenti/angelocenedese/LOGOS/ComunePD_logo.jpg

Monitoring System Development and Complex Data Analysis for Advanced Integrated Applications

Project summary

Project Responsibles:

Luciano Gamberini, DPG & HIT, University of Padova

Alberto Corò, Comune di Padova

Scientific Coordinator:

A. Cenedese, DEI & HIT, University of Padova

Research Fellow:

Marco Michielan, HIT, University of Padova


Comune di Padova



“Smart Cities pursue sustainability, livability, and social equity through technological and design innovation” (MIT research group): with this aim in mind we believe that urban analytics is a key step to understand our space and to realize smart services.

Specifically designed cyber-physical systems are used in conjunction with standard monitoring stations to sense and provide multilevel, heterogeneous and pervasive information. This information is put in relation through the time and geo-localization of the data and the physical communication and transportation networks of the city, acting like a biological nervous system.

Data-driven analysis highlights the behaviors that emerge from the interplay of human related activities and the natural phenomena.





The Padova Smart City project has received funding from Comune di Padova.


Start Date:

February 2014


15 months

How to turn dumb data into smart services?

To this aim we start from sensors embedded in the environment and heterogeneous measurements to build stochastic and graphical models (e.g. weigthed graphs, Hidden Markov models) to describe phenomena. These are used:
  • in the analysis phase to allow the interpretation of the data, the definition of metrics and the generation of information
  • in the synthesis phase, to ease the decision process that define city policies

Three areas of investigation are considered:

  1. Environmental monitoring (from pollution to public lighting)
  2. Public service control (e.g. bike sharing)
  3. Human related behavior analysis (e.g. traffic monitoring)


Public lighting: fault detection through variance analysis.
Bike sharing: transitional graphical model.

Traffic analysis. Usage of inbound and outbound routes.

The Bike Sharing model

The aim is to build a dynamical model of the bike sharing service based on learning the actual transitions and usage; the model would describe the behavior of the users and include the nonlinear saturations to take into account the real-world scenario and more importantly a control input needed to regulate the Quality of Service (QoS). By using this model it is envisaged:
  • to optimize the initial service condition in order to reduce user discomfort (i.e. maximize QoS)
  • to design efficient control procedures to act continuously and regulate the free dynamics, based on the maximization of the QoS or on the minimization of the control cost


Bike sharing: example of bike occupancy behavior obtained with the synthetic dynamical model.

Contact Us:

If you are interested in the project and you want to be updated on our activities or if you would like to contribute to the workshops to be organized, you can contact us using the form below.