High-Fidelity Reconstruction of 3D Temperature Fields Using Attention-Augmented CNN Autoencoders with Optimized Latent Space

MFI Khan, Z Hossain, A Hossen, MNU Alam… - IEEE …, 2024 - ieeexplore.ieee.org
Understanding and accurately predicting complex three-dimensional (3D) temperature
distributions are critical in diverse domains, including climate science and industrial process …

Machine Learning for the Design and the Simulation of Radiofrequency Magnetic Resonance Coils: Literature Review, Challenges, and Perspectives

G Giovannetti, N Fontana, A Flori, MF Santarelli… - Sensors, 2024 - mdpi.com
Radiofrequency (RF) coils for magnetic resonance imaging (MRI) applications serve to
generate RF fields to excite the nuclei in the sample (transmit coil) and to pick up the RF …

GenAI-Enhanced Federated Multi-Agent DRL for Digital Twin-Assisted IoV Networks

P Singh, B Hazarika, K Singh… - IEEE Internet of …, 2025 - ieeexplore.ieee.org
Achieving real-time decision-making and efficient resource management in dynamic, large-
scale Internet-of-Vehicles (IoV) networks is a significant challenge due to their inherent …

A Novel Hybrid Boundary Element–Physics Informed Neural Network Method for Numerical Solutions in Electromagnetics

S Barmada, S Dodge, M Tucci, A Formisano… - IEEE …, 2024 - ieeexplore.ieee.org
In this contribution the authors propose a hybrid Boundary Element Method–Physics
Informed Neural Networks (BEM–PINN) approach, to be used for the resolution of partial …

Machine Learning Approaches for Inverse Problems and Optimal Design in Electromagnetism

A Formisano, M Tucci - Electronics, 2024 - mdpi.com
The spread of high-performance personal computers, frequently equipped with powerful
Graphic Processing Units (GPUs), has raised interest in a set of techniques that are able to …

A Source Identification Problem in Magnetics Solved by Means of Deep Learning Methods

S Barmada, P Di Barba, N Fontana, ME Mognaschi… - Mathematics, 2024 - mdpi.com
In this study, a deep learning-based approach is used to address inverse problems involving
the inversion of a magnetic field and the identification of the relevant source, given the field …

Synthesis of Boundary Conditions in Polygonal Magnetic Domains Using Deep Neural Networks

S Barmada, P Di Barba, ME Mognaschi - Mathematics, 2024 - search.proquest.com
In this paper, the authors approach the problem of boundary condition synthesis (also
defined as field continuation) in a doubly connected domain by the use of a Neural Network …

Synthesis of Boundary Conditions in Magnetics: a Neural Network Approach

P Di Barba, ME Mognaschi, S Barmada… - 2024 IEEE 21st …, 2024 - ieeexplore.ieee.org
In the paper, the synthesis of boundary conditions in a doubly-connected domain is
accomplished by means of a single-layer neural network. In this way, the classical problem …