Abstract
Feature extraction is essential for classifying different motor imagery (MI) tasks in a brain–computer interface (BCI). Although the methods of brain network analysis have been widely studied in the BCI field, these methods are limited by differences in network size, density, and standardization. To address this issue and improve classification accuracy, we propose a novel method, in which the hybrid features of the brain function based on the bilevel network are extracted. Minimum spanning tree (MST) based on electroencephalogram (EEG) signal nodes in different MIs is constructed as the first network layer to solve the global network connectivity problem. In addition, the regional network in different movement patterns is constructed as the second network layer to determine the network characteristics, which is consistent with the correspondence between limb movement patterns and cerebral cortex in neurophysiology. We attempt to apply MST to the classification of the MI EEG signals, and the bilevel network has better interpretability. Thereafter, a vector is formed by combining the MST fundamental features with the directional features of the regional network. Our method is validated using the BCI Competition IV Dataset I. Experimental results verify the feasibility of the bilevel network framework. Furthermore, the average classification performance of the proposed method reaches 89.50%, which is higher than that of other competing methods, thereby indicating that the bilevel network is effective for MI classification.
Highlights
Electroencephalogram (EEG) is a bioelectrical signal formed by the simultaneous synthesis of many postsynaptic potentials, and reflects the state of the brain and the activation of nerve cells [1].we can obtain substantial physiological, psychological, and pathological information through the analysis of EEG signals [2,3]
Notes: sparse Bayesian learning is abbreviated as SBLFB, filter bank common spatial pattern is abbreviated as FBLFB, and channel optimization based on l1 -norm is abbreviated as COL
Regional network is constructed on the basis of Minimum spanning tree (MST) with the functional cortex region corresponding to different movements as the center
Summary
Electroencephalogram (EEG) is a bioelectrical signal formed by the simultaneous synthesis of many postsynaptic potentials, and reflects the state of the brain and the activation of nerve cells [1]. As early as 2006, Lee et al [20] have applied the MST analysis to the EEG signals and demonstrated its effectiveness in the study of epilepsy and in characterizing the network topology of different epilepsies. MST should be applied to the classification of the MI EEG signals in the present brain–computer interface (BCI) research, which provides an effective new idea for classifying the patterns of brain consciousness tasks. The brain network is a small-world network from the perspective of neurophysiology, and the MST clustering coefficient is constantly zero and has no small-world network characteristics To overcome these limitations, we propose a novel method, which is the hybrid features of the brain function based on the bilevel network.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
