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/

Zendy Plus

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

Zendy Tools

Zendy Open

Brain--computer interfaces are groundbreaking technology whereby brainsignals are used to control external devices. Despite some advances in recentyears, electroencephalogram (EEG)-based motor-imagery tasks face challenges,such as amplitude and phase variability and complex spatial correlations, witha need for smaller models and faster inference. In this study, we develop aprototype, called the Lightweight Geometric Learning Brain--Computer Interface(LGL-BCI), which uses our customized geometric deep learning architecture forswift model inference without sacrificing accuracy. LGL-BCI contains an EEGchannel selection module via a feature decomposition algorithm to reduce thedimensionality of a symmetric positive definite matrix, providing adaptivenessamong the continuously changing EEG signal. Meanwhile, a built-in losslesstransformation helps boost the inference speed. The performance of our solutionwas evaluated using two real-world EEG devices and two public EEG datasets.LGL-BCI demonstrated significant improvements, achieving an accuracy of 82.54%compared to 62.22% for the state-of-the-art approach. Furthermore, LGL-BCI usesfewer parameters (64.9K vs. 183.7K), highlighting its computational efficiency.These findings underscore both the superior accuracy and computationalefficiency of LGL-BCI, demonstrating the feasibility and robustness ofgeometric deep learning in motor-imagery brain--computer interfaceapplications.

LGL-BCI: A Motor-Imagery-Based Brain-Computer Interface with Geometric Learning