Graph-Based Information Separator and Area Convolutional Network for EEG-Based Intention Decoding

doi:10.1109/TCDS.2023.3260084

Graph-Based Information Separator and Area Convolutional Network for EEG-Based Intention Decoding

2024-02-01

1

PRE

AI

DOI：10.1109/TCDS.2023.3260084

Original

Original request for help

Save

Abstract

En 中文

In the current research on brain-computer interface (BCI), the electroencephalography (EEG) signal is usually only represented by a 2-D matrix, and the installation position of the EEG electrodes and the correlation between them are not considered. Actually, the cerebral cortex is a continuous potential surface and the information collected directly from each electrode is influenced by the other electrodes, so direct use of the raw data results in information redundancy. This article converts the EEG signal into a graph, and then creates an information separator (IS) based on the Laplace matrix of the graph to obtain the independent source information of electrode nodes, and propose an IS-based area convolutional network (IS-ACN). Integrating the proposed IS with some advanced methods, the experimental results show that the incorporation of IS can enhance the performance of these methods. By observing and tracking samples with abnormal noise in the BCI competition IV data set 2a, it is demonstrated that the proposed method can greatly reduce the influence of noise and effectively obtain the source features of EEG signals with low signal-to-noise ratio, and the average accuracy and kappa coefficient of the proposed IS-ACN on this data set are 80.59% and 74.1%, respectively.

Keywords:

Electroencephalography

Electrodes

Feature extraction

Convolutional neural networks

Convolution

Correlation

Symmetric matrices

Area convolutional network (ACN)

electroencephalography (EEG)

graph

information separator (IS)

intention decoding

Graph-Based Information Separator and Area Convolutional Network for EEG-Based Intention Decoding

Abstract

Journal

Organization