A DYNAMIC NEURAL-NETWORK IDENTIFICATION OF ELECTROMYOGRAPHY AND ARM TRAJECTORY RELATIONSHIP DURING COMPLEX MOVEMENTS

We propose a new approach based on dynamic recurrent neural networks ( DRNN) to identify, in human, the relationship between the muscle elect romyographic (EMG) activity and the arm kinematics during the drawing of the figure eight using an extended arm, After learning, the DRNN si mulations showed the efficiency of the model. We demonstrated its gene ralization ability to draw unlearned movements. We developed a test of its physiological plausibility by computing the error velocity vector s when small artificial lesions in the EMG signals were created, These lesion experiments demonstrated that the DRNN has identified the pref erential direction of the physiological action of the studied muscles. The network also identified neural constraints such as the covariatio n between geometrical and kinematics parameters of the movement, This suggests that the information of raw EMG signals is largely representa tive of the kinematics stored in the central motor pattern. Moreover, the DRNN approach will allow one to dissociate the feedforward command (central motor pattern) and the feedback effects from muscles, skin a nd joints.