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

Designing efficient and labor-saving prosthetic hands requires powerful handgesture recognition algorithms that can achieve high accuracy with limitedcomplexity and latency. In this context, the paper proposes a compact deeplearning framework referred to as the CT-HGR, which employs a visiontransformer network to conduct hand gesture recognition using highdensity sEMG(HD-sEMG) signals. The attention mechanism in the proposed model identifiessimilarities among different data segments with a greater capacity for parallelcomputations and addresses the memory limitation problems while dealing withinputs of large sequence lengths. CT-HGR can be trained from scratch withoutany need for transfer learning and can simultaneously extract both temporal andspatial features of HD-sEMG data. Additionally, the CT-HGR framework canperform instantaneous recognition using sEMG image spatially composed fromHD-sEMG signals. A variant of the CT-HGR is also designed to incorporatemicroscopic neural drive information in the form of Motor Unit Spike Trains(MUSTs) extracted from HD-sEMG signals using Blind Source Separation (BSS).This variant is combined with its baseline version via a hybrid architecture toevaluate potentials of fusing macroscopic and microscopic neural driveinformation. The utilized HD-sEMG dataset involves 128 electrodes that collectthe signals related to 65 isometric hand gestures of 20 subjects. The proposedCT-HGR framework is applied to 31.25, 62.5, 125, 250 ms window sizes of theabove-mentioned dataset utilizing 32, 64, 128 electrode channels. The averageaccuracy over all the participants using 32 electrodes and a window size of31.25 ms is 86.23%, which gradually increases till reaching 91.98% for 128electrodes and a window size of 250 ms. The CT-HGR achieves accuracy of 89.13%for instantaneous recognition based on a single frame of HD-sEMG image.

Transformer-based Hand Gesture Recognition via High-Density EMG Signals: From Instantaneous Recognition to Fusion of Motor Unit Spike Trains