Research on Lower Limb Step Speed Recognition Method Based on Electromyography

Abstract

Wearable exoskeletons play an important role in people’s lives, such as helping stroke and amputation patients to carry out rehabilitation training and so on. How to make the exoskeleton accurately judge the human action intention is the basic requirement to ensure that it can complete the corresponding task. Traditional exoskeleton control signals include pressure values, joint angles and acceleration values, which can only reflect the current motion information of the human lower limbs and cannot be used to predict motion. The electromyography (EMG) signal always occurs before a certain movement; it can be used to predict the target’s gait speed and movement as the input signal. In this study, the generalization ability of a BP neural network and the timing property of a hidden Markov chain are used to properly fuse the two, and are finally used in the research of this paper. Experiments show that, using the same training samples, the recognition accuracy of the three-layer BP neural network is only 91%, while the recognition accuracy of the fusion discriminant model proposed in this paper can reach 95.1%. The results show that the fusion of BP neural network and hidden Markov chain has a strong solving ability for the task of wearable exoskeleton recognition of target step speed.

The Realistic Dilemma, Theoretical Logic and Practical Paths of Motivating Knowledge-based Employees

“…Many companies have an "organizational centric" mindset, which assumes that knowledge-based employees work only for the benefit of the company, without considering their inner career pursuits, self-worth, and ideal aspirations. At present, most organizations only focus on material rewards such as salary and annual salary, but neglect the motivation of employees at the spiritual level [2] . As the demand level of knowledge-based employees increases, providing only material incentives cannot effectively motivate them.…”

An Unpowered Knee Exoskeleton for Walking Assistance and Energy Capture

“…D 2 ≈ 0.047 m and D 1 ≈ 0.034 m are calculated by Formulas (25) and (26). The scroll spring is placed in the spring box, and the number of turns n 1 without the torque is…”

“…Tang et al [10] summarized how assist components used by unpowered exoskeleton-assist robots usually implement a tension spring [11][12][13][14], a torsion spring [8,15], pneumatic artificial muscle [16][17][18], a constant force spring [19], a scroll spring [20,21], a single (double) spring [22][23][24], a spring lever and elastic cable. The existing evaluation methods of exoskeletons mainly include metabolic Chen Ben, muscle activation rate [25], joint torque, joint angle, plantar pressure, and joint force. Liu et al [26] studied the influence of weight distribution within knee exoskeleton components on simulated muscle activity during three functional movements.…”

Hardware accelerator for high accuracy sign language recognition with residual network based on FPGAs

“…In recent years, extensive research has been conducted in the field of sign language recognition [1][2][3][4][5][6]. Advances in deep learning (DL) algorithms, particularly convolutional neural networks (CNNs), have played a crucial role in addressing complex tasks such as image recognition [7][8][9][10][11][12] and object detection [13]. These developments have provided excellent neural network models for sign language recognition.…”