The purpose of this study was to develop and train neural networks (NN) to predict barbell motion and velocity from hip, knee, and ankle joint torques during a weightlifting exercise. Seven weightlifters performed two repetitions of the clean exercise at 85% of maximum while reaction forces and 3-D motion data of the lifter and barbell were acquired. An inverse dynamics procedure was then used to calculate torques at the hip, knee, and ankle joints. The joint torque time-series data were used as inputs to two seperate NN to predict 1) the horizontal and vertical barbell trajectories and 2) the vertical barbell velocities. Both NN demonstrated low mean square errors and good agreement with experimental data, which suggests NN could be used to inform weightlifters and their coaches about the relationships between joint kinetics and barbell kinematics.
"NEURAL NETWORK PREDICTION OF BARBELL KINEMATICS FROM JOINT KINETICS IN WEIGHTLIFTING,"
ISBS Proceedings Archive: Vol. 35
, Article 237.
Available at: https://commons.nmu.edu/isbs/vol35/iss1/237