Multidimensional EEG Representations and Classification of Grip- Force-Level Motor Imagery
This study demonstrates that motor imagery at varying grip-force levels produces distinct neural representations across slow cortical potentials, sensorimotor rhythms, and directional functional networks, which can be effectively decoded by the EEGSym model to achieve classification accuracies significantly above chance, thereby enabling the development of force-graded control systems for rehabilitation and prosthetics.