To solve the problem of long training time and over-fitting of small sample EEG signal processing

this paper proposes a DBN based on random retreat algorithm

which can classify and identify the left and right hand motion imaginary EEG signals. Firstly

the original EEG data were processed by dimension reduction

and the random DBN model was used to train the reduced EEG data

then the optimal parameter values for classification and recognition were obtained. The experimental results show that compared with CSP

PCA and single DBN network

the DBN algorithm based on random retreat can maintain the high recognition rate and reduces the training time

which proves the effectiveness of the method. Finally

the feasibility of the algorithm was verified on the intelligent wheelchair platform.