With the aid of an artificial neural network technique, we investigated relationships between the torque and extending velocity of an elbow at constant muscle activation in healthy volunteers. Each subject sat on a chair and was able to move his upper- and forearm on a shoulder-high horizontal plane. First, with the gravitational force of a weight hanging from a pulley, the subject's wrist was pulled to flex the elbow. Next, the subject was instructed to extend his elbow joint at a constant velocity. Integrated electromyograms (IEMGs), elbow joint angle and torque were measured while the elbow was being extending. Then the relationships among these three variables were modeled using an artificial neural network where IEMGs, joint angle and velocity were the inputs, and torque was the output. After back propagation learning, we presented various combinations of IEMGs, elbow joint angle and velocity to the model, and estimated the elbow joint torque to obtain the torque-velocity relationship for constant muscle activation. The torque decreased in a nearly linear manner as the velocity increased. This was caused by slow extending velocity and was explained by Hill's equation at slow velocity.
|Number of pages||9|
|Journal||Frontiers of medical and biological engineering : the international journal of the Japan Society of Medical Electronics and Biological Engineering|
|Publication status||Published - 1999|
ASJC Scopus subject areas