Motor Imagery Classification of Single-Arm Tasks Using Convolutional Neural Network based on Feature Refining
This work addresses the problem of improving motor function recovery or rehabilitation through brain-computer interfaces, but it is incremental as it builds on existing methods for EEG signal classification.
The study tackled the challenge of accurately classifying motor imagery EEG signals for single-arm tasks by proposing a band-power feature refining convolutional neural network (BFR-CNN), which outperformed conventional methods in 4-class classification tasks.
Brain-computer interface (BCI) decodes brain signals to understand user intention and status. Because of its simple and safe data acquisition process, electroencephalogram (EEG) is commonly used in non-invasive BCI. One of EEG paradigms, motor imagery (MI) is commonly used for recovery or rehabilitation of motor functions due to its signal origin. However, the EEG signals are an oscillatory and non-stationary signal that makes it difficult to collect and classify MI accurately. In this study, we proposed a band-power feature refining convolutional neural network (BFR-CNN) which is composed of two convolution blocks to achieve high classification accuracy. We collected EEG signals to create MI dataset contained the movement imagination of a single-arm. The proposed model outperforms conventional approaches in 4-class MI tasks classification. Hence, we demonstrate that the decoding of user intention is possible by using only EEG signals with robust performance using BFR-CNN.