English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neuropsychological studies suggest that co-operative activities amongdifferent brain functional areas drive high-level cognitive processes. To learnthe brain activities within and among different functional areas of the brain,we propose LGGNet, a novel neurologically inspired graph neural network, tolearn local-global-graph representations of electroencephalography (EEG) forBrain-Computer Interface (BCI). The input layer of LGGNet comprises a series oftemporal convolutions with multi-scale 1D convolutional kernels andkernel-level attentive fusion. It captures temporal dynamics of EEG which thenserves as input to the proposed local and global graph-filtering layers. Usinga defined neurophysiologically meaningful set of local and global graphs,LGGNet models the complex relations within and among functional areas of thebrain. Under the robust nested cross-validation settings, the proposed methodis evaluated on three publicly available datasets for four types of cognitiveclassification tasks, namely, the attention, fatigue, emotion, and preferenceclassification tasks. LGGNet is compared with state-of-the-art methods, such asDeepConvNet, EEGNet, R2G-STNN, TSception, RGNN, AMCNN-DGCN, HRNN and GraphNet.The results show that LGGNet outperforms these methods, and the improvementsare statistically significant (p<0.05) in most cases. The results show thatbringing neuroscience prior knowledge into neural network design yields animprovement of classification performance. The source code can be found athttps://github.com/yi-ding-cs/LGG

LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface