Classification Method of Lower Limbs Motor Imagery Based on Functional Connectivity and Graph Convolutional Network

The development of brain-computer interfaces (BCI) based on motor imagery (MI) has greatly improved patients’ quality of life with movement disorders. The classification of upper limb MI has been widely studied and applied in many fields, including rehabilitation. However, the physiological representations of left and right lower limb movements are too close and activated deep in the cerebral cortex, making it difficult to distinguish their features. Therefore, classifying lower limbs motor imagery is more challenging. In this study, we propose a feature extraction method based on functional connectivity, which utilizes phase-locked values to construct a functional connectivity matrix as the features of the left and right legs, which can effectively avoid the problem of physiological representations of the left and right lower limbs being too close to each other during movement. In addition, considering the topology and the temporal characteristics of the electroencephalogram (EEG), we designed a temporal-spatial convolutional network (TSGCN) to capture the spatiotemporal information for classification. Experimental results show that the accuracy of the proposed method is higher than that of existing methods, achieving an average classification accuracy of 73.58% on the internal dataset. Finally, this study explains the network mechanism of left and right foot MI from the perspective of graph theoretic features and demonstrates the feasibility of decoding lower limb MI.