Outcomes of the FAIR NAEL project: energy-efficient and sustainable technology AI solution for pattern recognition
Presenting author: Prof. Francesco Carlo Morabito
Other authors: Prof. Nadia Mammone, Prof. Cosimo Ieracitano, Prof. Mario Versaci
Affiliations: University Mediterranea of Reggio Calabria, CNR – ISASI Pozzuoli, Italy
The present speech will show the methodological approaches proposed within the PNRR FAIR NAEL project and the results achieved, specifically in healthcare and BCI. It includes a detailed description of the pre-processing of the data used to reduce the computational cost (and, thus, the energy consumption) in AI applications (i.e., classification, segmentation, and multimodal fusion). In addition, some meta-learning approaches are discussed that improve generalization performance also in different tasks, like in domain adaptation. Although the project is mainly focused in clinical applications, the talk will include some examples of the use of the same methodological approaches for cultural heritage data.
LIP3D project: Digital Tools and Immersive Technologies for the Virtual Reconstruction of Archaeological Heritage
Presenting author: Prof. Massimiliano Pepe
Other authors: Dr. Donato Palumbo, Dr. Ahmed Dewdar
Affiliations: University "G. d'Annunzio" Chieti-Pescara, Italy
The LIP3D project promotes the use of advanced digital tools for the documentation, analysis, and dissemination of archaeological heritage through 3D digitization and virtual reconstruction. The presentation will illustrate the workflow developed within the project for acquiring and processing 3D data using UAV photogrammetry, TLS, and SLAM technologies. Special attention will be given to the creation of open datasets and their reuse for educational, research, and AI-driven reconstruction purposes. Moreover, the talk will explore how immersive technologies—such as virtual reality (VR) and head-mounted displays—can enhance public engagement and accessibility to archaeological sites, offering new ways to experience and interpret cultural heritage in virtual environments.
A live VR demonstration will be organized, allowing participants to explore 3D reconstructions of archaeological sites involved in the LIP3D project using head-mounted displays (VR headsets). The demo will enable attendees to virtually walk through ancient sites, examine reconstructed architectural details, and experience interactive storytelling elements designed to communicate archaeological knowledge in an engaging and immersive way.
MUD-MADE project : MUlti-objective optimization of Digitally MAnufactureD Earth building components supported by neural networks
Presenting authors: Prof. Valentino Sangiorgio, Eng. Naomi Di Marco
Other authors: Prof. Alessia Amelio, Prof. Sergio Montelpare, Prof. Enrico Spacone, Prof. Mariano Pierantozzi
Affiliations: University "G. d'Annunzio" Chieti-Pescara, Italy
The MUD-MADE project explores the integration of artificial intelligence and digital fabrication technologies in the design and production of sustainable raw earth building components. The initiative develops an innovative workflow that combines parametric design, multi-objective optimization, and neural network–based support systems to create high-performance architectural elements that balance structural, thermal, and acoustic properties. The presentation will illustrate the AI-assisted workflow for generating and optimizing 3D-printed clay components, from parametric modeling and multi-performance assessment to prototyping and laboratory validation. Using Triply Periodic Minimal Surface (TPMS) geometries such as Gyroid, Diamond, and Schwarz, the project demonstrates how advanced raw earth-based additive manufacturing can enhance both material efficiency and constructive feasibility.
A live demonstration will showcase the 3D printing process of optimized earthen components using WASP technology, allowing participants to observe in real time how computational design and digital fabrication converge. The session will also feature interactive exploration of digital models and performance simulations, offering insights into how AI-driven methods can support architects and researchers in shaping the future of ecological construction through digitally manufactured raw earth architecture.