NEURAL NETWORK USED FOR THE PREDICTION OF JOINT TORQUE FROM GROUND REACTION FORCE DURING COUNTER·MOVEMENT JUMP AND SQUAT JUMP
Keywords: artificial neural network, joint torque, GRF, CMJ, SJ
AbstractThe purpose of this study was to develop an artificial neural network (ANN) for predicting the joint torque of lower limb using solely the ground reaction force (GRF) parameters for counter-movement jump (CMJ) and squat jump (SJ). Ten sport students performed CMJ and SJ on force plate, meanwhile the kinematic data were recorded and the joint torque were calculated as experimental data by inverse dynamics. We used a fully-connected, feed-forward network comprised of one input layer, one hidden layer and one output layer trained by back propagation using Steepest Descent Method. The input parameters of ANN were relevant time variables of GRF measurement and the output parameters were joint torque. The results revealed that the ANN model fitted the experimental data well indicating that the model developed in this study is feasible in the assessment of joint torque for CMJ and SJ.
Modelling / Simulation
Authors can retain copyright, while granting the International Society of Biomechanics in Sports (ISBS) the right of first publication.