Project BCI4ALL aims to research and develop effective EEG-based BCIs for individuals in locked-in state (LIS) and completely LIS (CLIS). The focus is on machine learning methods to improve BCI usability, the use of tDCS for neuromodulation, and LLM-driven communication. It is also expected that researched techniques have the potential to be used for assessing patients with disorders of consciousness (DoC).
MAIN TASKS:
TASK1: Machine learning for highly non-stationary EEG signal with cross-session transfer-learning
TASK2: Transcranial direct current stimulation (TDCS) to enhance EEG discrimination
TASK3: Multilevel and multimodal interfaces for BCI and patient assessment: reflexive, perceptual and cognitive dimensions
TASK4: Using large language models for text and speech generation from BCI outputs and hybrid interfaces
Funding Information:
FCT: 2023.17977.ICDT ; SGO2023: 17094 ; COMPETE: COMPETE2030-FEDER-00842800We had three papers accepted for publication at the IEEE ENBENG2025 Conference! Congrats to all the teams!
Our paper "Generalization of Machine and Deep Learning Models for Brain-Computer Interfaces Across Sessions and Paradigms in a Completely Locked-In Patient" has been accepted for publication at ROMAN2025! Congrats to the team, specially to Luis Garrote!
Official Project Kick-off meeting, 12 june, 2025! The meeting was attended by all BCI4ALL project members from the three institutions.
Portuguese meeting: Encontro Prospetivo: Tecnologias de Apoio em Portugal, May, 9, 2025, Polytechnic Institute of Tomar, https://sites.google.com/view/tapep2025 Registration ends May, 2 !