EEG Alpha Neurofeedback and Strength Adaptation – Judokas (2024)

This dataset is associated with the study entitled "Machine Learning Identification of EEG Predictors of Load-Specific Strength Gains Following Alpha Neurofeedback in Elite Judokas." The objective of the study was to investigate whether baseline prefrontal EEG activity—specifically alpha-band oscillations (8–13 Hz) measured at electrode sites F3 and F4—can serve as reliable predictors of neuromuscular adaptation following a structured 15-session alpha neurofeedback training protocol. The repository contains de-identified raw and processed EEG data (F3, F4, and Frontal Alpha Asymmetry Index [FAI]), lower-body strength performance metrics assessed across five relative loads (35%, 55%, 70%, 85%, and 100% of 1RM), responder classification labels, training group allocation (advanced vs. moderately trained), delta indices, and the full set of R scripts used for statistical and machine learning analyses (PCA, multivariate regression, Random Forest, Multi-Layer Perceptron). The data support a two-stage analytical framework: (1) identification of EEG-based predictors of load-specific strength improvements, and (2) supervised classification of responder status based on baseline neurophysiological profiles. All analyses conform to the FAIR principles and were preregistered prior to statistical processing to ensure transparency and reproducibility. This open-access dataset facilitates replication and further development of precision neurofeedback models in sports neuroscience and strength training domains.