Thematic Session 20

THEMATIC SESSION #20

Enrico Mattei

University of L'Aquila

• enrico.mattei@univaq.it

Alessandro Di Matteo

University of L'Aquila

• alessandro.dimatteo1@graduate.univaq.it

Lorenzo Nazzicone

University of Pavia

• lorenzo.nazzicone01@universitadipavia.it

Daniele Lozzi

University of L'Aquila

• daniele.lozzi@univaq.it

This thematic session will explore the latest developments in portable Brain–Computer Interfaces (BCIs), focusing on both passive and active applications that leverage artificial intelligence (AI) for enhanced functionality. A central theme will be the integration of EEG-based AI techniques for real-time signal processing and embedding, facilitating more efficient and adaptive BCI systems. In particular, the session will examine lightweight AI models designed for motor imagery and execution decoding, optimizing computational efficiency while maintaining high classification accuracy.

Multimodal AI techniques for BCI control will be another key area of discussion, highlighting approaches that combine EEG with additional physiological or behavioral inputs to improve system robustness and user experience. Furthermore, the role of wearable sensors and actuators in portable BCIs will be addressed, emphasizing their potential for seamless interaction in real-world applications.

Given the increasing adoption of wearable BCI technologies, security and privacy concerns remain paramount. This session will explore contemporary strategies for protecting neural data, ensuring secure signal transmission, and mitigating potential vulnerabilities associated with portable BCIs. By bringing together advancements in AI-driven signal processing, multimodal interaction, and cybersecurity, this session aims to foster interdisciplinary discussions on the future of portable BCIs and their practical implications in neuroscience, assistive technologies, and human-computer interaction.

We welcome original contributions on topics including but not limited to:

• New portable passive and active BCI applications;
• EEG-Artificial Intelligence technique for embedding;
• Multimodal AI techniques for controlling BCI;
• Digital Twin Modelling for BCI Applications;
• Motor imagery/execution decoding with light AI model;
• Security and privacy for portable BCIs;
• Wearable sensors and actuators for portable BCI.

Enrico Mattei is a Research Fellow in the University of L'Aquila medical department. He holds a Bachelor's Degree In Information Engineering and a Master's Degree In Computer And Systems Engineering from the Department of Information Engineering, Computer Science, and Mathematics at the University of L'Aquila, Italy. He is pursuing a PhD in Information and Communication Technology in the Department of Information Engineering, Computer Science, and Mathematics at the University of L'Aquila. His primary focus lies in the field of Robotics, Human-Robot Interaction (HRI), Deep Learning, Emotional Intelligence for HRI, BCI and EEG signal analysis using advanced deep learning techniques.

Alessandro Di Matteo received his master's degree in Computer Science from the University of L'Aquila, Italy, in 2022. He is currently pursuing a Ph.D. in Computer Science and Engineering at the same university.
He is currently spending four months at the INRIA, Empenn LAB, Rennes, France.
His research focuses on computer vision, machine learning and deep learning applications in medical imaging.

Lorenzo Nazzicone is a Ph.D. student in Micro and Nano Electronics at the University of Pavia. He obtained his Master's degree in Electronic Engineering from the University of L'Aquila, Department of Industrial and Information Engineering and Economics, in 2024. Previously, he obtained a Bachelor's degree in Information Engineering in 2021 from the same University, within the Department of Information Engineering, Computer Science and Mathematics. His research focuses on the development of systems for under-sampled MRI acquisition and reconstruction using advanced deep-learning techniques, with the aim of implementing the final solution on FPGA platforms.

Daniele Lozzi is a Research Fellow at the University of L'Aquila Medical Department. He holds a Bachelor's degree in Psychology and a Master's in Cognitive Neuroscience from the Department of Biotechnological and Applied Clinical Sciences at the University of L'Aquila, Italy. In 2021, he worked as a research assistant in Developmental Psychology at the University of Florence in the FORLILPSI Department. He is pursuing a PhD in Information and Communication Technology in the Department of Information Engineering, Computer Science, and Mathematics at the University of L'Aquila. He spent five months at the Institute of Neural Engineering at Graz University of Technology. His primary focus lies in the field of Neuroinformatics, BCI and EEG signal analysis using advanced deep learning techniques.