EEG-based brain-computer interfaces are systems aiming to integrate disabled people into their environments. Nevertheless, their control could not be intuitive or depend on an active external stimulator to generate the responses for interacting with it. Targeting the second issue, a novel paradigm is explored in this paper, which depends on a passive stimulus by measuring the EEG responses of a subject to the primary colors (red, green, and blue). Particularly, we assess if a compact and feature-extraction-independent deep learning method (EEGNet) can effectively learn from these EEG responses. Our outcomes outperformed previous works focused on a dataset composed of EEG signals belonging to 7 subjects while seeing and imagining three primary colors. The method reaches an accuracy of 45% for exposed colors, 43% for imagined colors, and 35% for the six classes. Last, the experiments suggest that EEGNet learned to discover patterns in the EEG signals recorded for imagined and exposed colors, and for the six classes, too.
Autorzy
- Alejandro A. Torres-García,
- dr Jesus Garcia Salinas link otwiera się w nowej karcie ,
- Luis Villaseñor-Pineda
Informacje dodatkowe
- DOI
- Cyfrowy identyfikator dokumentu elektronicznego link otwiera się w nowej karcie 10.1007/978-3-031-19493-1_12
- Kategoria
- Publikacja monograficzna
- Typ
- rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
- Język
- angielski
- Rok wydania
- 2022
