Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2505.07592 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Tabla de Contenidos:
- Consumer-grade electroencephalography (EEG) devices show promise for Brain-Computer Interface (BCI) applications, but their efficacy in detecting subtle cognitive states remains understudied. We developed a comprehensive study paradigm which incorporates a combination of established cognitive tasks (N-Back, Stroop, and Mental Rotation) and adds a novel ecological Chess puzzles task. We tested our paradigm with the MUSE 2, a low-cost consumer-grade EEG device. Using linear mixed-effects modeling we demonstrate successful distinctions of within-task workload levels and cross-task cognitive states based on the spectral power data derived from the MUSE 2 device. With machine learning we further show reliable predictive power to differentiate between workload levels in the N-Back task, and also achieve effective cross-task classification. These findings demonstrate that consumer-grade EEG devices like the MUSE 2 can be used to effectively differentiate between various levels of cognitive workload as well as among more nuanced task-based cognitive states, and that these tools can be leveraged for real-time adaptive BCI applications in practical settings.