Motor Imagery Classification based on CNN-GRU Network with Spatio-Temporal Feature Representation
This work addresses EEG-based brain-computer interface classification for motor imagery, which is an incremental improvement in a domain-specific application.
The authors tackled EEG signal classification for motor imagery by developing a CNN-GRU network that extracts spatio-temporal features, achieving an average accuracy of 77.70% on the BCI competition IV_2a dataset and outperforming baseline methods.
Recently, various deep neural networks have been applied to classify electroencephalogram (EEG) signal. EEG is a brain signal that can be acquired in a non-invasive way and has a high temporal resolution. It can be used to decode the intention of users. As the EEG signal has a high dimension of feature space, appropriate feature extraction methods are needed to improve classification performance. In this study, we obtained spatio-temporal feature representation and classified them with the combined convolutional neural networks (CNN)-gated recurrent unit (GRU) model. To this end, we obtained covariance matrices in each different temporal band and then concatenated them on the temporal axis to obtain a final spatio-temporal feature representation. In the classification model, CNN is responsible for spatial feature extraction and GRU is responsible for temporal feature extraction. Classification performance was improved by distinguishing spatial data processing and temporal data processing. The average accuracy of the proposed model was 77.70% for the BCI competition IV_2a data set. The proposed method outperformed all other methods compared as a baseline method.