Motor Imagery EEG Dataset for BCI-based Neurorehabilitation

This dataset was collected as part of a Master's thesis focused on developing a modular brain-computer interface (BCI) system for neurorehabilitation. It consists of EEG recordings acquired from 8 participants performing motor imagery tasks under a structured rehabilitation scenario using the OpenBCI Cyton board (8-channel configuration). The data acquisition was synchronized with a custom Unity-based 3D environment and the FourMotors robotic software to simulate realistic rehabilitation conditions. In total. 24 trials were performed alternating between rest and motor imagery of upper-limb movement, with clearly defined cues (S1–S6 event markers). The EEG signals were recorded at 1000 Hz sampling frequency and annotated with precise time stamps and event labels indicating cue presentation, movement onset, and resting phases.