Surface EMG data aggregation processing for intelligent prosthetic action recognition

Abstract

In the current development and design of sports rehabilitation equipment or biomimetic prostheses, in addition to pay attention to the development and design of the structure, the more core is how to realize the accurate and effective control of the rehabilitation equipment or intelligent prosthesis, and the current research is based on data process and pattern recognition. This paper designs 9 kinds of actions that can react effectively to the function of the hand and extracts the original EMG signals, which are based on the sEMG of the forearm muscles of human hand movement, and uses the 20 order comb filter and wavelet threshold to preprocess the signal, and uses the root mean square, wavelength and nonlinear characteristics sample entropy in time domain as three eigenvalues to construct the input feature vectors of the subsequent action classifier. Finally, the recognition of the hand movements is realized successfully through GRNN and SVM. The recognition rate is 98.64% in SVM classifier and 96.27% in GRNN classifier. Experimental results show that the SVM classifier is better than the GRNN classifier.

Numerical simulation of thermal insulation and longevity performance in new lightweight ladle

“…The advantage of this method is that on the one hand, it can save the workload and reduce the time spent on mesh drawing, on the other hand, it will not lead to too sparse mesh drawing, resulting in inaccurate results. 50,51 In the place where the physical quantity changes greatly, the number of grids can be appropriately increased, and the grid density can be appropriately reduced when the physical quantity changes steadily. 52,53 When a material changes in an object, a new grid cell should be divided at the material change.…”

“…Using ANSYS finite element software to mesh model requires hand‐animated meshes, subdividing the parts at the joints, and sparsely dividing the other parts. The advantage of this method is that on the one hand, it can save the workload and reduce the time spent on mesh drawing, on the other hand, it will not lead to too sparse mesh drawing, resulting in inaccurate results 50,51 . In the place where the physical quantity changes greatly, the number of grids can be appropriately increased, and the grid density can be appropriately reduced when the physical quantity changes steadily 52,53 .…”

Gesture recognition based on surface electromyography‐featureimage

“…However, the recognition accuracy of the hand movements will be greatly affected by the quality difference of the dataset, the quality of sEMG feature selection and the rationality of the intelligent classification model design. 15,16 In addition, the dependence of traditional machine learning on the quality of sEMG features greatly limits the development of sEMG gesture recognition research, resulting in researchers usually focusing only on the development of sEMG features with higher recognition performance. 17,18 It is difficult to identify the similar hand movements if combining the extracted sEMG feature with the conventional machine learning model, so that the gesture accuracy needs further improve.…”

Force Estimation Based on sEMG using Wavelet Analysis and Neural Network

“…Based on sEMG, it is widely studied to identify the movement intentions of human hands [5], namely the type of motion [6], the magnitude of motion [7], the speed of motion [8], and the output force. It has gradually developed into a wider field of gesture recognition and human-computer interaction [9]. The main work of sEMG-based human hand motion pattern recognition is to study the action pattern of identifying the hand from the surface EMG signal, that is, the feature extraction and motion pattern recognition of sEMG [10], [11].…”