Developing a robust machine-learning algorithm to detect hand motion is one of the most challenging aspects of prosthetic hands and exoskeleton design. Machine-learning methods that considered sex differences were used to identify and describe hand movement patterns in healthy individuals. To this purpose, surface Electromyographic (sEMG) signals have been acquired from muscles in the forearm and hand. The results of statistical analysis indicated that most of the same muscle pairs in the right hand (females and males) showed significant differences during the six hand movements. Time features were used an as input to machine-learning algorithms for the recognition of six gestures. Specifically, two types of hand-gesture recognition methods that considered sex differences(differentiating sex datasets and adding a sex label)were proposed and applied to the k-nearest neighbor (k-NN), support vector machine (SVM) and artificial neural network (ANN) algorithms for comparison. In addition, a t-test statistical analysis approach and 5-fold cross validation were used as complements to verify whether considering sex differences could significantly improve classification performance. It was demonstrated that considering sex differences can significantly improve classification performance. The ANN algorithm with the addition of a sex label performed best in movement classification (98.4% accuracy). In the future, hand movement recognition algorithms considering sex differences could be applied to control systems for prosthetic hands or exoskeletons.

Background: Because of osteoporosis, traffic accidents, falling from high places, and other reasons, the vertebral body can be compressed and even collapse. Vertebral implants can be used for clinical treatment. Because of the advantages of honeycomb sandwich structures, such as low cost, less material, light weight, high strength, and good cushioning performance. In this paper, the honeycomb sandwich structure was used as the basic structure of vertebral implants. Methods: The orthogonal experiment method is applied to analyse the size effect of honeycomb sandwich structures by the finite element method. Based on the minimum requirements of three indexes of peak stress, axial deformation, and anterior–posterior deformation, the optimal structure size was determined. Furthermore, through local optimization of the overall structure of the implant, a better honeycomb sandwich structure vertebral implant was designed. Results: The optimal structure size combination was determined as a panel thickness of 1 mm, wall thickness if 0.49 mm, cell side length of 1 mm, and height of 6 mm. Through local optimization, the peak stress was further reduced, the overall stress distribution was uniform, and the deformation was reduced. The optimized peak stress decreased to 1.041 MPa, the axial deformation was 0.1110%, and the anterior–posterior deformation was 0.0145%. A vertebral implant with good mechanical performance was designed. Conclusions: This paper is the first to investigate vertebral implants with honeycomb sandwich structures. The design and analysis of the vertebral implant with a honeycomb sandwich structure were processed by the finite element method. This research can provide a feasible way to analyse and design clinical implants based on biomechanical principles.

Background: Because of osteoporosis, traffic accidents, falling from high places and other reasons, the vertebral body could be compressed injury, even collapse. Vertebral implant can be used for clinical treatment. Because of the advantages of honeycomb sandwich structure, such as low cost, less material, light weight, high strength, and good cushioning performance, honeycomb sandwich structure was used as the basic structure of vertebral implant.Methods: In this paper, we applied the orthogonal experiment method to analyze the size effect of honeycomb sandwich structure by finite element method. Based on the minimum requirements of three indexes of peak stress, axial displacement, and anterior-posterior displacement, the optimal structure size was determined. Further, through local optimization of the overall structure of the implant, we designed better honeycomb sandwich structure vertebral implant.Results: The optimal structure size combination is determined as the face sheets thickness 1mm, wall thickness 0.49mm, cell side length 1mm, height 6mm. Than through local optimization, the peak stress is further reduced, the overall stress distribution is uniform, and the deformation is reduced. The optimized peak stress decreases to 1.041MPa, the axial deformation is 0.111%, and the anterior-posterior deformation is 0.014%. The honeycomb sandwich structure vertebral implant with stable structure and good mechanical performance was designed.Conclusions: The research result provides a method for the optimal design of vertebral body implant structures, as well as provides a new idea and biomechanical basis for clinical treatment after vertebral body injury.