Knee contact forces and knee stiffness are biomechanical factors worth considering for walking in knee osteoarthritis patients. However, it is challenging to acquire these factors in real time; thus, making it difficult to use them in robotic rehabilitation and assistive systems. This study investigated whether trained deep neural networks (DNNs) can capture the biomechanical factors only using kinematics during gait, which is possible to measure via sensors in real time. A public dataset of walking on the ground was analyzed through biomechanical analysis to train and test DNNs. Using the training dataset, several DNN topologies were explored via Bayesian optimization to tune the hyperparameters. After optimization, DNNs were trained to estimate the biomechanical factors in a supervised manner. The trained DNNs were then evaluated using two new datasets, which were not used in the training process. The trained DNNs estimated the biomechanical factors with a high level of accuracy in both types of test datasets. Results confirmed that DNNs can estimate the biomechanical factors based on only kinematics during gait.

In this paper, we compared the performance of the mechanical inertia and electronic inertia used in the friction coefficient measurement process, as this is the main function of the braking performance tester. The comparative test was carried out 36 times under mechanical inertia and electronic inertia. Stop braking was performed at various braking speeds (120, 160, 200, 220 ㎞/h), and at various contact force conditions (8, 18, 25 kN). We compared the instantaneous coefficient of the friction, the average coefficient of the friction, the braking force, and the braking distance with the mechanical inertia and the electronic inertia, by taking the average of the three tests we performed each for braking velocity and contact force. In addition, the friction coefficient ratio and the energy ratio were calculated. As a result, it was confirmed that the test using the electronic inertia compared to the test using the mechanical inertia appropriately reflects the bearing frictional force and the rotational resistance loss of the tester, and the kinetic energy is consumed as the braking energy without loss.