Skip to main navigation Skip to search Skip to main content

A Dual-Fatigue Speed Guidance Model for Isokinetic Training: Cognitive and sEMG-Based Physiological Fatigue Approach

  • Harbin Institute of Technology Shenzhen
  • Pengcheng Laboratory
  • Huazhong University of Science and Technology
  • Shanghai Jiao Tong University

Research output: Contribution to journalArticlepeer-review

Abstract

Isokinetic training has been proven to be an effective method in rehabilitative therapy. However, the quantitative relationship between training speed and the biophysical condition of the human body is not well established. To address this, a biceps isokinetic training robot implemented the dual-fatigue speed guidance model that integrated cognitive fatigue perception and physiological fatigue index based on sEMG was proposed. The sEMG signals were transformed from time series to a Markov state transition field (MTF) expressed as a state transition network diagram, from which modularity (MD) was extracted as a physiological fatigue index. MD combined with cognitive perceptions by the Borg RPE scale, formed a dual-fatigue speed guidance model for isokinetic training. After one month of training with nine male participants, the proposed model demonstrated improvements in peak torque, muscle dimensions, and cognitive fatigue compared to constant speed training, with a significant absolute peak torque increase (P = 0.0427). The proposed method enables personalized configuration of sports rehabilitation and enhancement, and it can be expected to apply in clinical precision therapy with more participants.

Original languageEnglish
Pages (from-to)2311-2321
Number of pages11
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume33
DOIs
StatePublished - 2025
Externally publishedYes

Keywords

  • Rehabilitation robots
  • fatigue index
  • isokinetic training
  • surface electromyography

Fingerprint

Dive into the research topics of 'A Dual-Fatigue Speed Guidance Model for Isokinetic Training: Cognitive and sEMG-Based Physiological Fatigue Approach'. Together they form a unique fingerprint.

Cite this