Neural Decoding of Upper Limb Movements Using Electroencephalography

Rationale: The human central nervous system (CNS) effortlessly performs complex hand movements with the control and coordination of multiple degrees of freedom (DoF), but how those mechanisms are encoded in the CNS remains unclear. In order to investigate the neural representations of human upper limb movement, scalp electroencephalography (EEG) was recorded to decode cortical activity in reaching and grasping movements. Methods: Upper limb movements including arm reaching and hand grasping tasks were observed in this study. EEG signals of 15 healthy individuals were recorded (g.USBamp, g.tec, Austria) when performing reaching and grasping tasks. Spectral features of the relevant cortical activities were extracted from EEG signals to decode the relevant reaching direction and hand grasping information. Upper limb motion direction and hand kinematics were captured with sensors worn on the hands. Directional EEG features were classified using stacked autoencoders; hand kinematic synergies were reconstructed to model the relationship of hand movement and EEG activities. Results: An average classification accuracy of three-direction reaching tasks achieved 79 ± 5.5% (best up to 88 ± 6%). As for hand grasp decoding, results showed that EEG features were able to successfully decode synergy-based movements with an average decoding accuracy of 80.1 ± 6.1% (best up to 93.4 ± 2.3%). Conclusion: Upper limb movements, including directional arm reaching and hand grasping expressed as weighted linear combinations of synergies, were decoded successfully using EEG. The proposed decoding and control mechanisms might simplify the complexity of high dimensional motor control and might hold promise toward real-time neural control of synergy-based prostheses and exoskeletons in the near future.