Knee torque estimation in non-pathological gait using dynamics modelling and feed-forward neural network

摘要: This paper presents a knee torque estimation in non-pathological gait cycle at stance phase. Comparative modelling by using dynamics model and neural network is discussed. Dynamics constructed simple two degree of freedom with Newtonian calculation approach more complex four Lagrangian approach. Neural based feed-forward (FNN) structure six different kinematic kinetic input from experiments to provide one output the form joint torque. Six cases combination presented test which give lower complexity data while maintain performance criterion. The available dataset used for simulation was also divided into five speed categories. FNN given normalized root mean squared error (NRMSE). We find that estimating torque, hip angle noticeably insignificant, ankle important than ground reaction force medio-lateral antero-posterior direction combined. Using only kinematics can achieve 2.67% NRMSE.