Contiguous temporal withholding for hemispheric analysis in frontal EEG during cycling

Area of Science:

• Neuroscience
• Biomedical Engineering
• Exercise Physiology

Background:

• Evaluating temporal sensitivity in electroencephalography (EEG) is crucial for understanding dynamic brain processes.
• Traditional methods like randomized train-test splits can disrupt the physiological time-series data.
• Frontal EEG during cycling offers insights into motor control and cortical adaptation.

Purpose of the Study:

• To present a novel methodological framework for assessing temporal sensitivity in frontal EEG recordings during cycling.
• To introduce contiguous temporal withholding and class-wise recall as key metrics.
• To evaluate hemispheric differentiation and cortical reorganization during sustained exercise.

Main Methods:

• Implemented contiguous temporal withholding, preserving physiological ordering by excluding sequential data segments.
• Utilized class-wise recall as a time-indexed indicator of hemispheric recognizability.
• Segmented EEG signals into contraction-aligned epochs and organized them into within-subject temporal sequences for analysis.

Main Results:

• The framework successfully captured evolving hemispheric recognizability across the pedaling sequence.
• Block-dependent modulation in recall consistently exceeded repetition-related variability.
• Results indicate the detection of structured temporal shifts in EEG signals, not stochastic training effects.

Conclusions:

• The proposed framework offers a robust method for evaluating temporal sensitivity in EEG data.
• It enables the assessment of hemispheric differentiation during gradual cortical reorganization.
• This approach moves beyond maximal classification accuracy to understand dynamic brain activity.