Decoding Brain Signals: A Convolutional Neural Network Approach for Motor Imagery Classification

Motor imagery-centered brain-computer interfaces (BCIs) have surfaced as a promising technology with the potential to improve communication and control for people facing motor impairments. Achieving precise classification of motor imagery (MI) tasks from EEG signals is essential for the optimal functioning of BCIs. In this study, we explore the use of convolutional neural networks (CNNs) to achieve robust and precise classification of MI-EEG signals. We utilized well-established EEG datasets, namely BCI Competition IV 2a and BCI Competition IV 2b, to assess our customized CNN architecture. The proposed network achieved an excellent result with an average classification accuracy of 87.3% and 86.29% on the respective datasets. This experiment showcases the network’s capacity to distinguish various motor imagery tasks by utilizing extracted temporal-spatial characteristics from the EEG data. This proposed network creates opportunities for BCIs that can provide enhanced control and communication options for the user.