Address book
Contacts
FEDERICO MASON
Position
Ricercatore a tempo det. art. 24 c. 3 lett. A L. 240/2010
Address
VIA G. GRADENIGO, 6/B - PADOVA
Telephone
Notices
Publications
Pietro Talli, et al. "Pragmatic Communication for Remote Control of Finite-State Markov Processes." in IEEE Journal on Selected Areas in Communications, 2025.
Federica Pondrelli, et al. "EEG as a predictive biomarker of neurotoxicity in anti-CD19 CAR T-cell therapy," in Journal of Neurology, Vol. 272, No. 5, April 2025.
Federico Mason & Jacopo Pegoraro, "Using Deep Reinforcement Learning to Enhance Channel Sampling Patterns in Integrated Sensing and Communication," in IEEE Wireless Communications Letters, Vol. 14, No. 3, March 2025.
Federico Mason, et al. "AI-Ehanced Reconstruction of the 12-Lead Electrocardiogram via 3-Leads with Accurate Clinical Assessment," in npj Digital Medicine, December 2024.
Federico Mason, et al., "Multi-Agent Reinforcement Learning for Pragmatic Communication and Control," in IEEE Transactions on Cognitive Communication and Networking, August 2024.
Seyyd Ahmed Lahmer, et al., "Fast Context Adaptation in Cost-Aware Continual Learning," in IEEE Transactions on Machine Learning in Communications and Networking, vol. 2, pp. 479-494, April 2024.
Federico Mason, et al., "Heart Rate Variability as a Tool for Seizure Prediction: A Scoping Review," in MDPI Journal of Clinical Medicine, vol. 13, no. 3, pp. 747-764, January 2024.
Federico Mason, et al., "Using Distributed Reinforcement Learning for Resource Orchestration in a Network Slicing Scenario," in IEEE/ACM Transactions on Networking, vol. 31, no. 1, pp. 88-102, February 2023.
Federico Mason, et al., "Remote tracking of UAV swarms via 3D mobility models and LoRaWAN communications," in IEEE Transactions on Wireless Communications, vol. 21, no. 5, pp. 2953-2968, October 2021.
Federico Venturini, et al., "Distributed Reinforcement Learning for Flexible and Efficient UAV Swarm Control," in IEEE Transactions on Cognitive Communications and Networking, vol. 7, no. 3, pp. 955-969, September 2021.
Federico Mason, et al., “An Adaptive Broadcasting Strategy for Efficient Dynamic Mapping in Vehicular Networks," in IEEE Transactions on Wireless Communications, vol. 19, no. 8, pp. 5605-5620, May 2020.
Massimo Dalla Cia, et al., "Using Smart City Data in 5G Self-Organizing Networks," in IEEE Internet of Things Journal, vol. 5, no. 2, pp. 645-654, April 2018.
Thesis proposals
Identifying the Epileptogenic Zone in Stereo-EEG
Stereo-Electroenceèhalography (SEEG) is a minimally invasive surgical procedure that allows the recording of intracranial electrical activity in patients with drug-resistant epilepsy. The goal of such a procedure is to identify the Epileptogenic Zone (EZ), i.e., the minimum portion of the brain to be resected to provide seizure freedom after epilepsy surgery. The goal of the project is to design new computational techniques to analyze SEEG signals and potentially identify new biomarkers of the EZ, enhancing the success probability of epilepsy surgery.
The cost of learning dilemma
Artificial Intelligence (AI) has become an increasingly central actor in our lives, enabling technology to adapt to user needs. The shift to a continuously evolving technology presents a critical cost in terms of communication and computational resources, as telecommunication networks must support both user and training data flows. This project aims to define new strategies for combining the optimization of cognitive networks, analyzing how the training of learning agents implies a performance reduction in user applications.
Predicting extubation outcomes in intensive care
In intensive care units (ICUs), ventilator machines support breathing functions in patients under critical conditions. The readiness of a patient to breathe autonomously is verified via the Spontaneous Breathing Trial (SBT) procedure. If SBT concludes successfully, the patient is extubated, and the ventilator machine can be allocated to a new user. In the other case, the patient is subjected to a hazardous physical effort. This project aims to analyze the data series collected in ICUs and predict the outcome of SBT procedures.
Predicting VNS efficacy in epilepsy
Vagus Nerve Stimulation (VNS) is a treatment for people with epilepsy that involves the implantation of a neurostimulator connected to the left vagus nerve. This device periodically generates electric pulses in the brain, a procedure that, in specific cases, strongly reduces the impact of seizures. However, there are no clear practices for selecting the right candidates for the VNS therapy. This project aims to analyze EEG and EKG signals before and after VNS implantation, and identify new features to predict the outcome of VNS treatment.
Lightweight EEG acquisition
Remote EEG monitoring requires the implementation of lightweight setups that mitigate energy consumption and computational complexity for EEG recording. This project aims to design new algorithms for processing EEG signals and obtain an acquisition setup with a limited number of electrodes. To evaluate the final performance, we will consider both the mathematical difference between the original and the reconstructed signals and the clinical performance, assessed in terms of the probability of detecting relevant clinical features.
UAV networks for remote health monitoring
Body sensor networks offer a non-intrusive means of monitoring health by enabling the continuous tracking of vital signs without causing discomfort in daily life. However, there are still vast regions where establishing a stable internet connection is a significant challenge. This project aims to design a dynamic telecommunication system, integrating wearable sensors and Unmanned Aerial Vehicles (UAVs), for health data collection. The goal is to adapt the system components to maximize performance in terms of clinical assessment.
