Deep Fusion Feature Learning Network for MI-EEG Classification

Brain-computer interfaces (BCIs) are used to provide a direct communication between the human brain and the external devices, such as wheelchairs and intelligent apparatus, by interpreting the electroencephalograph (EEG) signals. Recently, motor imagery EEG (MI-EEG) has become an active research field where a subject's active intent can be detected. The accurate decoding of MI-EEG signals is essential for effective BCI systems but also very challenging due to the lack of informative correlation between the signals and the brain activities. To improve the precision performance of a BCI system, accurate feature discrimination from input signals and proper classification are necessary. However, the traditional deep learning scheme is failed to generate spatio-temporal representation simultaneously and capture the dynamic correlation for an MI-EEG sequence. To address this problem, we propose a long short-term memory network combined with a spatial convolutional network that concurrently learns spatial information and temporal correlations from raw MI-EEG signals. In addition, spectral representations of EEG signals are obtained via a discrete wavelet transformation decomposition. In order to achieve even higher learning rates and less demanding initialization, we employ a batch normalization method before training and recognition. Various experiments have been performed to evaluate the performance of the proposed deep learning architectures. Results indicate a high level of accuracy over both the public data set and the local data set. Our method can also serve as a useful and robust model for multi-task classification and subject-independent movement class decoder across many different methods.