Elderly people often use a cane to walk; it is an important part of their daily life. The cane must be made of a light weight material of high stiffness. In addition, stress relaxation on impact is required to make the cane easy to grasp. All these factors are affected by the shape design. Therefore, an effective shape design considering the stress relaxation on impact load and the weight of the cane is important. Traditionally, straight-type canes are widely used in the market. In this study, a bioinspired shape design methodology is proposed to produce canes. The basis vector method is used, and a multi-objective design optimization for minimizing the total volume and the maximum stress is performed. A sequential approximate optimization is then adopted to determine the Pareto optimal solutions. The superiority of the proposed method over the straight-type cane is confirmed through numerical results. The optimal cane shapes have more than 90% lower impact stress than the straight-type canes. Finally, a prototype of the optimized cane is produced using the braiding technology. Carbon fiber reinforced plastic is the selected cane material owing to its light weight and high stiffness.

Keywords

Biology, Cane design, Shape optimization, Multi-objective design optimization, Breading technology

Paper information

[Advance Publication] (Proper information for citation will be announced after formal publication)

Several training methods have been developed to acquire motion information during real-time walking; these methods also feed the information back to the trainee. Trainees adjust their gait to ensure that the measured value approaches the target value, which may not always be suitable for each trainee. Therefore, we aim to develop a gait feedback training system that considers individual differences, classifies the gait of the trainee, and identifies adjustments for body parts and timing. A convolutional neural network (CNN) has a feature extraction function and is robust in terms of each feature position; therefore, it can be used to classify a gait as ideal or non-ideal. Additionally, when the gradient-weighted class activation mapping (Grad-CAM) is applied to the gait classification model, the output measures the influence degree contributed by the trainee's each body part to the classification results. Thus, the trainee can visually determine the body parts that need to be adjusted through the use of the output. In this study, we focused on gaits related to stumbling. We measured the kinematics and kinetics data for participants and generated multivariate gait data, which were labeled as "gait rarely associated with stumbling" class or "gait frequently associated with stumbling" class using clustering with dynamic time warping. Next, the multichannel deep CNN (MC-DCNN) was used to learn the gait using the multivariate gait data and the corresponding classes. Finally, the data for verification were input into the MC-DCNN model, and we visualized the influence degrees of each place of the multivariate gait data for classification using Grad-CAM. The MC-DCNN model classified gaits with a high accuracy of 97.64±0.40%, and it learned the features that determine the thumb-to-ground distance. The output of the Grad-CAM indicated body parts, timing, and the relative strength of features that have an important effect on the thumb-to-ground distance.

Keywords

Healthcare, Gait training, Motion analysis, Walking factor, Neural network, Grad-CAM

Paper information

[Advance Publication] (Proper information for citation will be announced after formal publication)