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

Low-channel EEG devices are crucial for portable and entertainmentapplications. However, the low spatial resolution of EEG presents challenges indecoding low-channel motor imagery. This study introduces TSFF-Net, a novelnetwork architecture that integrates time-space-frequency features, effectivelycompensating for the limitations of single-mode feature extraction networksbased on time-series or time-frequency modalities. TSFF-Net comprises four maincomponents: time-frequency representation, time-frequency feature extraction,time-space feature extraction, and feature fusion and classification.Time-frequency representation and feature extraction transform raw EEG signalsinto time-frequency spectrograms and extract relevant features. The time-spacenetwork processes time-series EEG trials as input and extracts temporal-spatialfeatures. Feature fusion employs MMD loss to constrain the distribution oftime-frequency and time-space features in the Reproducing Kernel Hilbert Space,subsequently combining these features using a weighted fusion approach toobtain effective time-space-frequency features. Moreover, few studies haveexplored the decoding of three-channel motor imagery based on time-frequencyspectrograms. This study proposes a shallow, lightweight decoding architecture(TSFF-img) based on time-frequency spectrograms and compares its classificationperformance in low-channel motor imagery with other methods using two publiclyavailable datasets. Experimental results demonstrate that TSFF-Net not onlycompensates for the shortcomings of single-mode feature extraction networks inEEG decoding, but also outperforms other state-of-the-art methods. Overall,TSFF-Net offers considerable advantages in decoding low-channel motor imageryand provides valuable insights for algorithmically enhancing low-channel EEGdecoding.

Time-space-frequency feature Fusion for 3-channel motor imagery classification