Classification of EEG signal using convolutional neural networks

Abstract

Electroencephalography (EEG) signal recorded during motor imagery (MI) has been widely applied in noninvasive brain-computer interfaces (BCIs) as a communication approach. As an important issue in BCI systems, signal classification has been attached to increasingly attention. This paper presents a new classification method based on the deep convolutional neural network (CNN) for MI-EEG. Compared with other three classification methods (LDA, SVM, MLP), the results demonstrate that CNN can provide better classification performance. The present study shows that the proposed method is effective to classify MI and have potential to be a proper choice for BCI applications. The proposed paradigm could be further implemented by optimizing the network structure.