3D ground reaction force (GRF) estimation during walking is important for gait and inverse dynamics analyses. Recent studies have estimated 3D GRF based on kinematics measured from optical or inertial motion capture systems without force plate measurement. A neural network (NN) could be used to estimate ground reaction forces. The NN network approach based on segment kinematics requires the selection of optimal inputs, including kinematics type and segments. This study aimed to select optimal input kinematics for implementing an NN for each foot’s GRF estimation. A two-stage NN consisting of a temporal convolution network for gait phase detection and a gated recurrent unit network was developed for GRF estimation. To implement the NN, we conducted level/inclined walking and level running on a force-sensing treadmill, collecting datasets from seven male participants across eight experimental conditions. Results of the input selection process indicated that the center of mass acceleration among six kinematics types and trunk, pelvis, thighs, and shanks among 15 individual segments showed the highest correlations with GRFs. Among four segment combinations, the combination of trunk, thighs, and shanks demonstrated the best performance (root mean squared errors: 0.28, 0.16, and 1.15 N/kg for anterior-posterior, medial-lateral, and vertical components, respectively).

The purpose of this study was to examine the effect of gender and foot landing type (forefoot vs. rearfoot landing) on kinematics, kinetics, and energy absorption of lower extremity joint. Twenty males and twenty females performed single-leg landing with two different foot landing types: forefoot landing and rearfoot landing. Three-dimensional kinematic and kinetic parameters were measured using motion capture system. Greater knee valgus angle at peak vertical ground reaction force (p = 0.034) during rearfoot landing increased the risk of anterior cruciate ligament (ACL) injury in females as increasing valgus positioning from neutral alignment could increase the load on ACL. Greater contribution of ankle joint and less contribution of hip joint in energy dissipation were found in females during both forefoot (p = 0.029 and p = 0.016, respectively) and rearfoot landing (p = 0.003 and p = 0.016, respectively). These results suggest that increasing muscular activity of ankle plantarflexor could reduce shock transmission to the proximal joint in females. In addition, greater hip joint’s contribution to total negative work in males induced lower hip flexion angle found in both forefoot and rearfoot landing by elevated activation of the hip extensor. In conclusion, landing strategy differs between genders in both forefoot and rearfoot landing.