EEG Classification Based on Sparse Representation and Deep Learning

Abstract

For brain computer interfaces (BCIs) research, the classification of motor imagery brain signals is a major and challenging step. Based on the traditional sparse representation classification, a classification algorithm of electroencephalogram (EEG) based on sparse representation and convolution neural network is proposed by this paper. For the EEG signal, firstly, the features of the signal are obtained through the common spatial pattern (CSP) algorithm, and then the redundant dictionary with sparse representation is constructed based on these features. The sparse representation of the EEG signal is completed and the sparse features can be obtained. Finally, the sparse features are transformed into two dimensional signals, and the convolution neural network is used to complete the classification of EEG signals. Using the dataset downloaded from the website of BCI competition III (dataset IVa), for two types of EEG signals, the experiments show that the recognition accuracy of the method is over 80, and the recognition accuracy is better than that of the traditional SRC algorithm.