Pre-movement neural population activity in human motor cortex reflects the subsequent outcome of futsal free kicks
Hirose, S.; Ushiba, J.; Iwama, S.
Show abstract
Recent sports science studies suggest that optimizing neural activity can enhance motor performance, but practical applications have been hindered by large-scale electroencephalography (EEG) setups and controlled laboratory protocols. In our study, we demonstrate that a portable 3-channel EEG device can predict trial-by-trial success in a futsal-based kicking task under conditions mimicking real-world sports. We employed a model that used a transformer-based encoder and multilayer perceptron decoder, with evaluations performed separately on all electrodes. The model achieved a mean score of approximately 0.68 under cross-validation. We found that significantly higher alpha- and beta-band power contributed to the classification. Our findings indicate that performance prediction is feasible using low-density EEG in a real-world sports scenario. This research provides practical insights that could lead to the development of new training methods to improve performance through the control of brain states.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Cortical sensorimotor activity in the execution and suppression of discrete and rhythmic movements 96%
- Sound perception in realistic surgery scenarios: Towards EEG-based auditory work strain measures for medical personnel. 95%
- Discrimination of finger movements by magnetomyography with optically pumped magnetometers 95%
Similar papers in this journal
- Data leakage in deep learning studies of translational EEG 95%
- Decoding Neural Activity in Sulcal and White Matter Areas of the Brain to Accurately Predict Individual Finger Movement and Tactile Stimuli of the Human Hand 94%
- Modulation of gamma spectral amplitude and connectivity during reaching predicts peak velocity and movement duration 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.