OBJECTIVE: Proportional and simultaneous est-imation of finger kinematics from surface EMG based on the assumption that there exists a correlation between muscle activations and finger kinematics in low dimensional space. METHODS: We employ Manifold Relevance Determination (MRD), a multi-view learning model with a nonparametric Bayesian approach, to extract the nonlinear muscle and kinematics synergies and the relationship between them by studying muscle activations (input-space) together with the finger kinematics (output-space). RESULTS: This study finds that there exist muscle synergies which are associated with kinematic synergies. The acquired nonlinear synergies and the association between them has further been utilized for the estimation of finger kinematics from muscle activation inputs, and the proposed approach has outperformed other commonly used linear and nonlinear regression approaches with an average correlation coefficient of 0.91±0.03. CONCLUSION: There exists an association between muscle and kinematic synergies which can be used for the proportional and simultaneous estimation of finger kinematics from the muscle activation inputs. SIGNIFICANCE: The findings of this study not only presents a viable approach for accurate and intuitive myoelectric control but also provides a new perspective on the muscle synergies in the motor control community.
OBJECTIVE: Proportional and simultaneous est-imation of finger kinematics from surface EMG based on the assumption that there exists a correlation between muscle activations and finger kinematics in low dimensional space. METHODS: We employ Manifold Relevance Determination (MRD), a multi-view learning model with a nonparametric Bayesian approach, to extract the nonlinear muscle and kinematics synergies and the relationship between them by studying muscle activations (input-space) together with the finger kinematics (output-space). RESULTS: This study finds that there exist muscle synergies which are associated with kinematic synergies. The acquired nonlinear synergies and the association between them has further been utilized for the estimation of finger kinematics from muscle activation inputs, and the proposed approach has outperformed other commonly used linear and nonlinear regression approaches with an average correlation coefficient of 0.91±0.03. CONCLUSION: There exists an association between muscle and kinematic synergies which can be used for the proportional and simultaneous estimation of finger kinematics from the muscle activation inputs. SIGNIFICANCE: The findings of this study not only presents a viable approach for accurate and intuitive myoelectric control but also provides a new perspective on the muscle synergies in the motor control community.