Feature recognition of motor imaging EEG signals based on deep learning

The brain-computer interface technology interprets the EEG signals displayed by the human brain's neurological thinking activities through computers and instruments, and directly uses the interpreted information to manipulate the outside world, thereby abandoning the human peripheral nerves and muscle systems. The emergence of brain-computer interface technology has brought practical value to many fields. Based on the mechanism and characteristics of motion imaging EEG signals, this paper designs the acquisition experiment of EEG signals. After removing the anomalous samples, the wavelet-reconstruction method is used to extract the specific frequency band of the motion imaging EEG signal. According to the characteristics of motor imagery EEG signals, the feature recognition algorithm of convolutional neural networks is discussed. After an in-depth analysis of the reasons for choosing this algorithm, a variety of different network structures were designed and trained. The optimal network structure is selected by analyzing the experimental results, and the reasons why the structure effect is superior to other structures are analyzed. The results show that the method has a high accuracy rate for the recognition of motor imagery EEG, and it has good robustness.