Abstract
This paper conducts an evaluative study on the rehabilitation of limb motor function by using a microsensor information flow gain algorithm and investigates the surface electromyography (EMG) signals of the upper limb during rehabilitation training. The surface EMG signals contain a large amount of limb movement information. By analysing and processing the surface EMG signals, we can grasp the human muscle movement state and identify the human upper limb movement intention. The EMG signals were processed by the trap and filter combination denoising method and wavelet denoising method, respectively, the signal-to-noise ratio was used to evaluate the noise reduction effect, and finally, the wavelet denoising method with a better noise reduction effect was selected to process all the EMG signals. After the noise is removed, the signal is extracted in the time domain and frequency domain, and the root mean square (RMS), absolute mean, median frequency in the time domain, and average power frequency in the frequency domain are selected and input to the classifier for pattern recognition. The support vector machine is used to classify the myoelectric signals and optimize the parameters in the support vector machine using the grid search method and particle swarm optimization algorithm and classify the test samples using the trained support vector machine. Compared with the classification results of the grid search optimized support vector machine, the optimized vector machine has a 7% higher recognition rate, reaching 85%. The action recognition classification method of myoelectric signals is combined with an upper limb rehabilitation training platform to verify the feasibility of using myoelectric signals for rehabilitation training. After the classifier recognizes the upper limb movements, the upper computer sends movement commands to the controller to make the rehabilitation platform move according to the recognition results, and finally, the movement execution accuracy of the rehabilitation platform reaches 80% on average.
Highlights
Traditional rehabilitation training is usually a long and repetitive process, mainly performed manually by a therapist or with the help of simple equipment to drive the affected limb, this training method is usually assisted by medical personnel, and the physical exertion of medical personnel in the rehabilitation process is very high, so it is difficult to ensure the intensity and durability of the rehabilitation training, limiting the optimization of the rehabilitation training and rehabilitation effect [1]
Every action of the Complexity human body is realized by the central nervous system controlling muscle contraction, and in the process of muscle contraction, there will be myoelectric signals generated, which are bioelectric signals generated by muscle contraction in the process of action realization, and the action information contained in the myoelectric signals is ahead of the actual muscle action and can reflect the body’s action intention earlier, so it can be used to predict body movements [5]. e sEMG can reflect the activity level of specific muscle groups, allowing for more detailed monitoring and control of limb movements [6]
All the data in this paper were obtained by analysing and processing the surface EMG signals of the upper limbs of 10 subjects, each of whom performed four movements, elbow flexion, elbow extension, shoulder abduction, and shoulder dorsiflexion, and each of whom repeated each movement for five sets. e root mean square (RMS), mean absolute value, median frequency, and mean power frequency of each action are used to form a feature vector to characterize the EMG signal category, so that each action has
Summary
Traditional rehabilitation training is usually a long and repetitive process, mainly performed manually by a therapist or with the help of simple equipment to drive the affected limb, this training method is usually assisted by medical personnel, and the physical exertion of medical personnel in the rehabilitation process is very high, so it is difficult to ensure the intensity and durability of the rehabilitation training, limiting the optimization of the rehabilitation training and rehabilitation effect [1]. E sEMG can reflect the activity level of specific muscle groups, allowing for more detailed monitoring and control of limb movements [6] It can be collected by surface electrodes, eliminating the need for complex mechanical structures and avoiding the pain and cross-infection that can be caused by needle electrodes piercing the muscle [7]. A surface electromyography (EMG) signal is collected from the human upper limb during rehabilitation training, and the EMG signal is analysed and processed by a classifier to identify the human movement intention. E extracted eigenvalues are used to train the support vector machine model, optimize the parameters using the grid search method and particle swarm algorithm, and verify the recognition rate using the test data set to select the optimization method with a good classification effect. Assuming that the left upper limb is the healthy side and the right upper limb is the affected side, we verify the feasibility of using myoelectric signals from the healthy side to drive the affected limb on the upper limb rehabilitation training platform
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
