| Title:
|
Decoding of Voluntary Motor Decisions from Prefrontal EEG Oscillatory Dynamics Using Ensemble Learning
|
| Author(s):
|
1
|
| Subject:
|
Artificial Intelligence and Brain Mapping
|
|
|
|
Presenter Author:
|
|
| Name:
|
کوثر فتاحی
|
|
|
|
Author:
|
|
| Name 1:
|
کوثر فتاحی - Corresponding - Presenter
|
| Affiliation 1:
|
National Institute of Genetic Engineering and Biotechnology
|
|
|
| Name 2:
|
Mobin Fattahi
|
| Affiliation 2:
|
|
|
|
| Name 3:
|
|
| Affiliation 3:
|
|
|
|
| Name 4:
|
|
| Affiliation 4:
|
|
|
|
| Name 5:
|
|
| Affiliation 5:
|
|
|
|
| Name 6:
|
|
| Affiliation 6:
|
|
|
|
| Name 7:
|
|
| Affiliation 7:
|
|
|
|
| Name 8:
|
|
| Affiliation 8:
|
|
|
|
| Name 9:
|
|
| Affiliation 9:
|
|
|
|
| Name 10:
|
|
| Affiliation 10:
|
|
|
|
Abstract
|
Original Research
|
|
introduction :
|
Decoding the neural basis of voluntary human decision-making is a cardinal goal in cognitive neuroscience and brain mapping research. Volitional motor choices self-arise from interlinked executive control, cognitive evaluation, and motor preparation processes, for which the Prefrontal Cortex (PFC) acts as the main coordination area. Recent developments in wearable EEG systems provide the opportunity to explore these neural dynamics with improved ecological validity, reaching beyond the conventional borders of laboratory-based research. This study tests the hypothesis that oscillatory EEG signatures recorded from prefrontal areas can reliably predict voluntary motor choices before the execution of overt actions.
|
|
Methods:
|
Eighteen healthy participants performed a self-paced binary decision-making task, choosing between two motor responses ('p' or 'q' keys). Neural activity was captured via a wearable Muse EEG device across four electrodes: AF7, AF8, TP9, and TP10. Signals were preprocessed using band-pass filtering and ocular artifact attenuation. Power Spectral Density (PSD) features were extracted across five canonical frequency bands (Delta, Theta, Alpha, Beta, and Gamma), resulting in 20 spectral features per decision epoch. A Random Forest ensemble classifier was employed for decoding, and model performance was evaluated using cross-validation to ensure generalizability.
|
|
Results:
|
The proposed decoding framework achieved a mean classification accuracy of 72.22%, significantly above the 50% chance level for binary prediction. Feature importance analysis identified Theta-band oscillations at AF8 (right PFC) and Beta-band activity at AF7 (left PFC) as the most pertinent predictors. Increased Theta power at AF8 is indicative of heightened cognitive control and uncertainty resolution, while increased Beta activity at AF7 relates to neural mechanisms of motor planning and action preparation, suggesting asymmetrical prefrontal contributions to volition.
|
|
Conclusion:
|
This study demonstrates that voluntary motor choices can be decoded from prefrontal oscillatory dynamics well in advance of behavioral execution using a non-invasive, wearable system. The above-chance prediction underlines the real-world feasibility of brain mapping and encourages the development of portable Brain-Computer Interface (BCI) applications. This work offers a scalable framework for future neurotechnological interventions and contributes to a deeper understanding of the neural architecture underlying human volition.
|
| Attachment:
|
|
| Keywords:
|
EEG Decoding, Prefrontal Cortex, Brain-Computer Interface (BCI), Oscillatory Dynamics, Random Forest, Voluntary Decision-Making
|
| Key message:
|
|
| Do you want your abstract to be indexed, if this is selected as one of the top 100
articles?
|
