Antonio Ferramosca

Autoimmune atrophic gastritis (AAG) is a chronic autoimmune disease affecting the stomach. Its diagnosis is based on serologic profiles, histological evaluations and esophagogastroduodenoscopies (EGDSs). AAG is characterized by a progressively increasing mucosal damage that can lead to several complications, however the specific temporal dynamics of this disease have not been fully characterized yet. This paper presents an exploratory study of the application of a graph representation learning method to model the AAG progression by identifying temporal phenotypes. We employed a procedure that combines Topological Data Analysis (TDA) and Minimum Spanning Tree filters, on a longitudinal dataset of patients that underwent multiple EGDSs, obtained from a multicentric Italian cohort. The dataset includes histological evaluations and clinical observations derived from text notes that were annotated in a previous study, with a total of 236 patients, 836 EGDSs performed, and 18 variables. Using our algorithm, we obtained a graph with weights representing the temporal progression. Five possible disease trajectories were identified through a Minimum Spanning Tree. Statistical tests and Cox Hazard Analysis demonstrated the existence of significant differences in the development of complications timing within these trajectories, proving that our approach is able to characterize the AAG evolution even in a relatively small dataset.

This paper proposes a new controller that takes advantage of the properties of the recurrent neural network of the long short-term memory (RNN-LSTM) to imitate the behavior of an economic model predictive control (economic MPC). The approach introduces specific knowledge of the benchmark controller optimization problem and modifies the loss function during the training stage of the RNN-LSTM. This method is easy to implement, and its effectiveness demonstrates itself in a practical application: the energy management system of a microgrid on a university campus. The results show that the modification of the loss function improves the accuracy of the proposed controller compared to the traditional training method.

This paper presents a novel robust predictive controller for constrained nonlinear systems that is able to track piece-wise constant setpoint signals. The tracking model predictive controller presented in this paper extends the nonlinear MPC for tracking to the more complex case of nonlinear systems subject to bounded and not necessarily additive perturbations. The optimal control problem that is solved at each step penalizes the deviation of the predicted nominal system trajectory from an artificial reference, which is added as a decision variable, as well as the distance between the artificial reference and the setpoint. Robust feasibility is ensured by imposing conservative constraints that take into account the effect of uncertainties and convergence to a neighborhood of any feasible setpoint is guaranteed by means of an appropriate terminal cost and an extended stabilizing terminal constraint. In the case of unreachable setpoints, convergence to a neighborhood of the optimal reachable steady output is also proved.