Electromyographic signal gesture recognition method based on double-flow network

Abstract

The invention discloses an electromyographic signal gesture recognition method based on a double-flow network. The electromyographic signal gesture recognition method comprises the following steps: 1)collecting electromyographic signals of various gestures of multiple persons, wherein each gesture action of a subject lasts for 12 seconds by wearing a 16-channel acquisition device, steady-state data of 10 seconds are extracted, data preprocessing is carried out, a 300ms time window is selected, and the size of each frame of electromyogram is 300*16, so that a training set is constructed. 2) constructing a double-flow network model, wherein the model is mainly composed of three parts, the first part is a multi-layer CNN and is responsible for extracting spatial features; the second part isa multi-layer LSTM and is responsible for learning time characteristics; and the last part is a feature merging layer which is responsible for feature fusion. 3) training the double-flow network model, and performing gradient descent optimization by adopting an Adam optimizer until convergence, and 4) performing gesture recognition on the sEMG of the arm by using the trained double-flow network model.

Description

technical field

[0001] The invention relates to the fields of human-computer interaction and artificial intelligence, in particular to a dual-stream network-based myoelectric signal gesture recognition method, which can be applied in industrial control and medical prosthesis. Background technique

[0002] By constructing a deep learning model to classify the surface electromyography signal (sEMG), the electromyography signal is converted into instructions for conveying the user's movement intention, and then transmitted to the machine to form a complete electromyography control system. Gesture recognition based on surface EMG signals is the core of EMG control systems. In the application scenario, sEMG is susceptible to interference from the external environment, such as electrode offset, changes in muscle contraction force, and changes in muscle contraction force. These factors will affect the accuracy of the recognition model. In the application fields of sEMG, such as in...

Images