Thales Firenze presented the results of Pitagora, a project devoted to develop decision support tools for airport management. The University of Florence and KKT, a spinoff from gol, were partners (sub contrctors) of the project. Read the news on the official presentation of
Machine Learning methods for demand and renewable energy production forecasting
In this work, demand and renewable energy production forecasting problems are treated. The main goal of this work is the prediction’s accuracy improvement using machine learning methods and time series analysis too. In the case of demand forecasting problem we
MIDA – Machine Intelligence for diagnosis automation
MIDA – Machine Intelligence for diagnosis automation Oil analysis today is mostly carried out through off-line / off-site procedures and analysed in a laboratory through a standard process. No significant international experience is reported on the use of non
SMARTY – Smart Transport for Sustainable City
Smart Transport for Sustainable City The project aims to develop an ICT platform for the development of innovative mobility, promoting the use of transport systems like flexible bus, car pooling, car and bike sharing integrated with traditional transport systems. A platform
Simulation of equilibrium power allocation strategies in transmission networks
In a network some users, called primary, require connection for their transmission at a specified power, while other, called secondary, compete to share the remaining bandwidth, taking into account signal and noise The thesis developes a simulation model to test
Advanced production planning models
This thesis considers advanced models for production, based on mixed integer linear optimization, when finite capacity constraints are available Advisor: Fabio Schoen Candidate: Andrea Di Muro Date: laurea: Matematica
A Pyomo Particle Swarm model for global optimization
A particle swarm method for has been implemented in pyomo, using local searches in place of function evaluations. Advisor: Fabio Schoen Candidate: Edoardo Belli date: November 2014 Larea: triennale Ingegneria Informatica
Forecasting methods for bike sharing systems based on dynamic ARIMA models
Forecasting for bike sharing systems is carried out on the basis of ARIMA models and regression, based on actual data taken from available bike sharing systems (Paris, Barcelona, Milan); correlation with weather forecast is also analyzed. Advisor: Fabio Schoen Candidate:
Optimization of expensive functions based on surrogate RBF models
Global optimization of expensive, black-box, functions is analyzed in this thesis. A python code has been developed to efficiently identify new evaluation points for expensive objective functions Advisor: Fabio Schoen Candidate: Andrea Fresu Date: November 2014 Laurea: specialistica Ingegneria Informatica
Scheduling in dual-resources constrained manufacturing environment: a case study
A complex production planning model has been implemented and tested for a medium-size company active in the sector of frozen food production. Advisor: Fabio Schoen Candidate: Gianluca Forte Date: October 2014 Laurea: specialistica Ingegneria Meccanica