Expanding Semantic BCI for Low-Density EEG via Deep Learning
This study investigates the potential of Semantic Brain-Computer Interfaces (BCIs) using low- density electroencephalography (EEG) systems in conjunction with advanced deep learning models. By analyzing both reflexive and cognitive event-related potentials elicited by visual stimuli, the research a...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Proyecto final de grado |
| Lenguaje: | Español |
| Publicado: |
Bioingeniería
2025
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/20.500.14769/4974 |
| Aporte de: |
| Sumario: | This study investigates the potential of Semantic Brain-Computer Interfaces (BCIs) using low- density electroencephalography (EEG) systems in conjunction with advanced deep learning models.
By analyzing both reflexive and cognitive event-related potentials elicited by visual stimuli, the research aims to develop effective methods for the semantic interpretation of brain signals using minimal electrode setups. Emphasizing the use of low-density EEG systems, this work demonstrates that high classification accuracy can be achieved even with limited equipment. Additionally, the study ensures that the deep learning model used, namely EEGNet, align with established physiological EEG knowledge by following procedures that validate the learned features against known EEG patterns. |
|---|