Cross-user gesture recognition method for robust myoelectricity control

Abstract

The invention discloses a cross-user gesture recognition method for robust electromyographic control. The method comprises the following steps: 1, collecting surface electromyographic signals and extracting features to construct a source domain data set; 2, constructing a student teacher deep network model; and 3, training a student model by using the source domain data set, obtaining network parameters, and obtaining teacher model parameters through index moving averaging. 4, new user electromyographic signals are collected, and features are extracted to construct target domain data; and classifying and generating pseudo labels through the student model and the teacher model. And 5, optimizing a pseudo tag generated by the teacher model through an optimal transmission algorithm. And 6, continuously giving classification results for newly input target domain data by using the student model, carrying out parameter updating, and then updating the teacher model. And 7, executing the step 4 for subsequent new users. According to the method, model migration from the source domain to the target domain can be realized, so that high-precision cross-user gesture recognition is realized.

Description

technical field [0001] The invention belongs to the technical field of electromyography signal processing, in particular to a domain adaptation method based on a student teacher model, which realizes universal gesture recognition across users, and is mainly applied to robust electromyography control. Background technique [0002] EMG control directly decodes human muscle activity into a series of instructions that can reflect its movement intention, realizes the control and information input of peripheral electronic equipment, and is widely used in human-machine interface, neurorehabilitation and prosthetic control. Distinguishing different gesture action patterns from electromyography (EMG) is a key technology in realizing multi-degree-of-freedom EMG control. Surface electromyography (sEMG) has attracted extensive attention due to its advantages of non-invasiveness, convenience, and ability to reflect information related to neuromuscular system activities. The time domain,...

AI Technical Summary

Problems solved by technology

However, there is a problem with these methods, that is, for each new user, they need to train the classifier with as much target domain data as possible and a large amount of training data, which is inefficient and time-consuming

Moreover, the target domain data used for training needs to contain all gesture samples, which limits the convenience of using the myoelectric control system

Images