基于协调注意力模块的运动想象脑电识别方法OA

To solve the problem of low recognition rate due to the small number of channels and low signal-to-noise ratio of motor imagery EEG,this paper introduces coordinate attention(CA)into convolutional neural networks and proposes a method of motor imagery EEG recognition based on coordinated attention module.Firstly,the two-dimension time-frequency graph obtained from the pre-processed EEG signal is used as the input of the model,and the motion image intention recognition model is obtained by training the convolutional neural network model.Finally,the method is applied to the data set and a series of comparative experi-ments are carried out with the excellent deep learning methods in recent years.The experimental results show that CA module can be flexibly used in convolutional neural networks,and can improve the accuracy of model recognition without increasing the calculation cost of the model,which indicates that the proposed method is effective in classification recognition.