SSVEP-gated EMG-based decoding of elbow angle during goal-directed reaching movement

Abstract

IntroductionEstimation of reaching movement commands for controlling human–machine interfaces (HMIs) based on electromyogram (EMG) signals, such as prostheses or robotic assistive devices, for the disabled is challenging due to the absence of healthy and synergistic muscle activations. MethodsIn this study, to improve the kinematic estimation of an EMG-based decoder during goal-directed reaching movements, steady-state visual evoked potentials (SSVEP) were considered to identify the motion target. The EMG signal of the shoulder and arm muscles was mapped to the elbow angle with a model selected by SSVEP signals during the reaching movement to a flashing target on display. ResultsThe accuracy of decoding based on the combination of EMG and EEG was significantly different (RMSE = 3.7° and R2 = 92.13%) from the counterpart EMG-based decoder (RMSE = 4.26° and R2 = 91.02%). Indeed, the proposed dual-modality structure outperformed the single-modality structure when the EMG signals altered in permanent conditions, such as spinal cord injury or stroke. Especially in simulated muscle weakness situations where the signal-to-noise ratio declines, the dual-modality framework was more robust than the single-modality, and the determinant coefficient of the decoder was stable above 80%. ConclusionBecause of the additional EEG information to recognize the target of reaching, the performance of the EMG-based decoding improved and could be more robust during EMG signal alterations. The outcomes of this study can be applied to control HMIs or evaluate real-time rehabilitation trials, particularly for severe motor injury patients.