no code implementations • 19 Jun 2024 • Mirko Fiacchini, Martina Mammarella, Fabrizio Dabbene
First, motivated by the difficulty of guaranteeing recursive feasibility in this framework, due to the nonzero probability of violating chance-constraints in the case of unbounded noise, we introduce the novel definition of measured-state conditioned recursive feasibility in expectation.
no code implementations • 11 Jun 2024 • Valentina Breschi, Chiara Ravazzi, Paolo Frasca, Fabrizio Dabbene, Mara Tanelli
This paper focuses on devising strategies for control-oriented decision-making scenarios, in the presence of social and external influences, e. g. within recommending systems in social contexts.
no code implementations • 28 May 2024 • Cesare Donati, Martina Mammarella, Fabrizio Dabbene, Carlo Novara, Constantino Lagoa
In this paper, we propose a unified framework for identifying interpretable nonlinear dynamical models that preserve physical properties.
no code implementations • 23 Apr 2024 • Pierluigi Francesco De Paola, Alessandro Borri, Fabrizio Dabbene, Karim Keshavjee, Pasquale Palumbo, Alessia Paglialonga
Despite the well-acknowledged benefits of physical activity for type 2 diabetes (T2D) prevention, the literature surprisingly lacks validated models able to predict the long-term benefits of exercise on T2D progression and support personalized risk prediction and prevention.
no code implementations • 15 Mar 2024 • Alberto Carlevaro, Teodoro Alamo Cantarero, Fabrizio Dabbene, Maurizio Mongelli
Conformal predictions make it possible to define reliable and robust learning algorithms.
no code implementations • 31 Oct 2023 • Cesare Donati, Martina Mammarella, Fabrizio Dabbene, Carlo Novara, Constantino Lagoa
The aim of this paper is to present a novel physics-based framework for the identification of dynamical systems, in which the physical and structural insights are reflected directly into a backpropagation-based learning algorithm.
no code implementations • 8 Sep 2023 • Alberto Carlevaro, Teodoro Alamo, Fabrizio Dabbene, Maurizio Mongelli
The notion of scalable classifiers is then exploited to link the tuning of machine learning with error control.
no code implementations • 4 Sep 2023 • Sara Narteni, Alberto Carlevaro, Fabrizio Dabbene, Marco Muselli, Maurizio Mongelli
Everyday life is increasingly influenced by artificial intelligence, and there is no question that machine learning algorithms must be designed to be reliable and trustworthy for everyone.
no code implementations • 6 Feb 2022 • Martina Mammarella, Cesare Donati, Takumi Shimizu, Masaya Suenaga, Lorenzo Comba, Alessandro Biglia, Kuniaki Uto, Takeshi Hatanaka, Paolo Gay, Fabrizio Dabbene
In this paper, we present an innovative approach where a fleet of unmanned aerial vehicles is exploited to perform remote sensing tasks over an apple orchard for reconstructing a 3D map of the field, formulating the covering control problem to combine the position of a monitoring target and the viewing angle.
no code implementations • 15 Jan 2021 • Martina Mammarella, Victor Mirasierra, Matthias Lorenzen, Teodoro Alamo, Fabrizio Dabbene
In this paper, a sample-based procedure for obtaining simple and computable approximations of chance-constrained sets is proposed.