MODAL@UNINA

The M.O.D.A.L. research group at the University Naples Federico II conducts research and teaches a wide range of AI related topics, often cross-disciplinary. We collaborate internationally and locally with academics, businesses and public stakeholders, working at the frontiers of knowledge on solving real-world problems. The M.O.D.A.L. research group is dynamic and community-oriented, providing many research collaboration and innovation opportunities. M.O.D.A.L. is committed to advancing knowledge and fostering learning in an atmosphere of discovery and creativity. People-oriented values such as transparency, trust, creativity and autonomy are central. Head and Scientific Coordinator: Prof. Francesco Piccialli

Research Activities

M.O.D.A.L. research interests fall within the following main areas:

Machine and Deep Learning

Machine learning means computers learning from data using algorithms to perform a task without being explicitly programmed. Deep learning uses a complex structure of algorithms modeled on the human brain. This enables the processing of unstructured data such as documents, images and text.

Scientific Machine Learning (SciML)

Nowadays, combining physics law and domain knowledge into Machine Learning models can be considered a new frontier; the goal is to provide some “informative priors” such as theoretical constraints on top of observational ones. Therefore, Physics-Informed Machine Learning aims to introduce a novel paradigm to improve the performance of the learning algorithms.

Federated Learning

Federated Learning is a distributed machine learning approach that enables the training of models across decentralized data sources while maintaining data privacy. Federated Learning allows multiple devices or servers to collaboratively learn a shared model without exchanging raw data, combining computational techniques and privacy-preserving methods to produce robust global models without compromising sensitive information.

Real-World Applications

Healthcare, Precision Medicine, Industry 4.0, Smart City, Smart Mobility, Agritech, Biochemistry, Cultural Heritage, Energy Efficiency, Geosciences, Seismology.

Last Research Projects

TUAI – Marie Curie Doctoral Network

The TUAI Project (Towards an Understanding of Artificial Intelligence) is a Marie Skłodowska-Curie Doctoral Network under the Horizon Europe program. This project focuses on training a new generation of researchers in sustainable AI solutions, addressing challenges in smart manufacturing, smart cities, healthcare, and mobility.

Deep-Learning-aided GPC-IR fingerprinting of complex polyolefin mixtures

By combining deep learning with GPC-IR fingerprinting, we hope to unlock new possibilities for analyzing and characterizing these materials, and to provide valuable insights into their properties and behavior. This research is being carried out in partnership with the Department of Chemical Sciences of the University of Naples Federico II.

PRIN - GANDALF – Gan Approaches for Non-iid Aiding Learning in Federations

The GANDALF focuses on addressing one of the key challenges in Federated Learning—non-IID data. By leveraging Generative Adversarial Networks (GANs) and edge computing, the project aims to improve learning across decentralized nodes. This approach has significant potential in healthcare, where privacy-preserving and decentralized learning can enhance diagnosis without the need for data sharing, thus overcoming privacy and security issues. Our research group plays a crucial role in designing methodologies to tackle these challenges, enabling more efficient learning models.

Last News

Last News @ M.O.D.A.L.

Blockchain-based Secure Internet of Medical Things Framework for Stress Detection

We are thrilled to announce that our paper “A Blockchain-based Secure Internet of Medical Things Framework for Stress Detection” has been pu

Leggi tutto

Highly Cited Paper in 2022

We're thrilled to share that our article on "From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0" has been recog

Leggi tutto

Welcome to a new member of MODAL!

We are excited to welcome Marzia Canzaniello as new researcher to our MODAL laboratory! With her expertise and skills, we're looking forward to

Leggi tutto