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

Walking-assistive devices require adaptive control methods to ensure smoothtransitions between various modes of locomotion. For this purpose, detectinghuman locomotion modes (e.g., level walking or stair ascent) in advance iscrucial for improving the intelligence and transparency of such roboticsystems. This study proposes Deep-STF, a unified end-to-end deep learning modeldesigned for integrated feature extraction in spatial, temporal, and frequencydimensions from surface electromyography (sEMG) signals. Our model enablesaccurate and robust continuous prediction of nine locomotion modes and 15transitions at varying prediction time intervals, ranging from 100 to 500 ms.In addition, we introduced the concept of 'stable prediction time' as adistinct metric to quantify prediction efficiency. This term refers to theduration during which consistent and accurate predictions of mode transitionsare made, measured from the time of the fifth correct prediction to theoccurrence of the critical event leading to the task transition. Thisdistinction between stable prediction time and prediction time is vital as itunderscores our focus on the precision and reliability of mode transitionpredictions. Experimental results showcased Deep-STP's cutting-edge predictionperformance across diverse locomotion modes and transitions, relying solely onsEMG data. When forecasting 100 ms ahead, Deep-STF surpassed CNN and othermachine learning techniques, achieving an outstanding average predictionaccuracy of 96.48%. Even with an extended 500 ms prediction horizon, accuracyonly marginally decreased to 93.00%. The averaged stable prediction times fordetecting next upcoming transitions spanned from 28.15 to 372.21 ms across the100-500 ms time advances.

Predicting Continuous Locomotion Modes via Multidimensional Feature Learning from sEMG