Please use this identifier to cite or link to this item:
Title: LGGNet: learning from local-global-graph representations for brain-computer interface
Authors: Ding, Yi
Robinson, Neethu
Tong, Chengxuan
Zeng, Qiuhao
Guan, Cuntai
Keywords: Engineering::Computer science and engineering
Issue Date: 2023
Source: Ding, Y., Robinson, N., Tong, C., Zeng, Q. & Guan, C. (2023). LGGNet: learning from local-global-graph representations for brain-computer interface. IEEE Transactions On Neural Networks and Learning Systems.
Project: A20G8b0102 
Journal: IEEE Transactions on Neural Networks and Learning Systems 
Abstract: Neuropsychological studies suggest that co-operative activities among different brain functional areas drive high-level cognitive processes. To learn the brain activities within and among different functional areas of the brain, we propose local-global-graph network (LGGNet), a novel neurologically inspired graph neural network (GNN), to learn local-global-graph (LGG) representations of electroencephalography (EEG) for brain-computer interface (BCI). The input layer of LGGNet comprises a series of temporal convolutions with multiscale 1-D convolutional kernels and kernel-level attentive fusion. It captures temporal dynamics of EEG which then serves as input to the proposed local-and global-graph-filtering layers. Using a defined neurophysiologically meaningful set of local and global graphs, LGGNet models the complex relations within and among functional areas of the brain. Under the robust nested cross-validation settings, the proposed method is evaluated on three publicly available datasets for four types of cognitive classification tasks, namely the attention, fatigue, emotion, and preference classification tasks. LGGNet is compared with state-of-the-art (SOTA) methods, such as DeepConvNet, EEGNet, R2G-STNN, TSception, regularized graph neural network (RGNN), attention-based multiscale convolutional neural network-dynamical graph convolutional network (AMCNN-DGCN), hierarchical recurrent neural network (HRNN), and GraphNet. The results show that LGGNet outperforms these methods, and the improvements are statistically significant ( ) in most cases. The results show that bringing neuroscience prior knowledge into neural network design yields an improvement of classification performance. The source code can be found at
ISSN: 2162-237X
DOI: 10.1109/TNNLS.2023.3236635
Schools: School of Computer Science and Engineering 
Rights: © 2023 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
LGGNet_ Learning From Local-Global-Graph Representations for Brain–Computer Interface.pdf3.05 MBAdobe PDFThumbnail

Citations 50

Updated on Dec 8, 2023

Page view(s)

Updated on Dec 10, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.