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

Steady-state visual evoked potentials (SSVEPs) based brain-computer interface(BCI) has received considerable attention due to its high information transferrate (ITR) and available quantity of targets. However, the performance offrequency identification methods heavily hinges on the amount of usercalibration data and data length, which hinders the deployment in real-worldapplications. Recently, generative adversarial networks (GANs)-based datageneration methods have been widely adopted to create syntheticelectroencephalography (EEG) data, holds promise to address these issues. Inthis paper, we proposed a GAN-based end-to-end signal transformation networkfor Time-window length Extension, termed as TEGAN. TEGAN transformsshort-length SSVEP signals into long-length artificial SSVEP signals. Byincorporating a novel U-Net generator architecture and an auxiliary classifierinto the network architecture, the TEGAN could produce conditioned features inthe synthetic data. Additionally, we introduced a two-stage training strategyand the LeCam-divergence regularization term to regularize the training processof GAN during the network implementation. The proposed TEGAN was evaluated ontwo public SSVEP datasets (a 4-class dataset and a 12-class dataset). With theassistance of TEGAN, the performance of traditional frequency recognitionmethods and deep learning-based methods have been significantly improved underlimited calibration data. And the classification performance gap of variousfrequency recognition methods has been narrowed. This study substantiates thefeasibility of the proposed method to extend the data length for short-timeSSVEP signals for developing a high-performance BCI system. The proposedGAN-based methods have the great potential of shortening the calibration timeand cutting down the budget for various real-world BCI-based applications.

Short-length SSVEP data extension by a novel generative adversarial networks based framework