Motor Imagery Classification Emphasizing Corresponding Frequency Domain Method based on Deep Learning Framework

The electroencephalogram, a type of non-invasive-based brain signal that has a user intention-related feature using in brain-computer interface (BCI) provides an efficient bidirectional pathway between user and computer. In this work, we proposed a deep learning framework based on the corresponding frequency emphasize method to decode the motor imagery (MI) data from the 2020 International BCI competition dataset. The MI dataset consists of 3-class, namely `Cylindrical', `Spherical', and `Lumbrical'. We utilized power spectral density as an emphasize method and a convolutional neural network to classify the modified MI data. The results showed that the MI-related frequency range was activated during the MI task, and provide neurophysiological evidence to design the proposed method. When using the proposed method, the average classification performance in the intra-session condition was 69.68% and the average classification performance in the inter-session condition was 52.76%. Our results provided the possibility of developing a BCI-based device control system for practical applications.