HANDLINK: A Dexterous Robotic Hand Exoskeleton controlled by Motor Imagery (MI)
Journal of Advances in Medicine and Medical Research · pp. 427–436 · Published 1 Dec 2022
10.9734/jammr/2022/v34i234879Abstract
Introduction: Over 5.6 million stroke survivors in the United States experience hemiparesis of the upper limb. Assistive devices are used to help regain upper limb functionality for affected individuals; however, existing devices are bulky, costly, and lack adaptability. The objective of this pilot study was to test the performance of a newly developed hand exoskeleton on a sample of individuals with hand impairment. Methods: A hand exoskeleton was developed comprising of a novel linkage system with three four-bar linkages structures set up in a series and a novel algorithm that finds optimal Electroencephalogram (EEG) channels, through Common Spatial Pattern (CSP) Recognition, and classifies them with a stacked Linear Discriminant Analysis-Support Vector Machine (LDA-SVM) classifier. The functionality of the novel hand exoskeleton was tested by examining performance across a battery of hand mobility assessments among individuals in the experimental group with hand impairment (n=10) compared to controls (n=10). Results: A paired-t test was used to show better performance for the experimental group with the exoskeleton compared to those without the exoskeleton across function, grip force, and range of motion measures. An unpaired-t test was used to show that there was no statistical difference in the mean performance of the experimental group with the exoskeleton compared to the control group for most measures, indicating that functionality with the exoskeleton is comparable to a healthy hand. The LDA-SVM classifier resulted in an 88% accuracy in classifying which finger the user intends to move with minimal latency as a result of its computational efficiency. Conclusions: Findings suggest HANDLINK was effective in improving function, grip force, and range of motion among hand-impaired individuals. The HANDLINK, and its complementary stacked SVM-LDA classification algorithm, work as a viable solution for a fully adaptable and cost-effective assistive hand aide for individuals with paraplegia.
Cited by 4
Aibek Niyetkaliyev, Azamat Turganbayev, Madina Karasheva · Journal of Mechanical Design · 2025
Bogdan Gherman, Ionut Zima, Calin Vaida · Technologies · 2025
Saad Abdullah, Abdelakram Hafid, Hira Shahid · 2023 IEEE 4th International Multidisciplinary Conference on Engineering Technology (IMCET) · 2023
Ana Carretero, Alvaro Araujo · Sensors · 2024
Article metrics
Real usage data collected on this platform.
3
Page views
0
PDF downloads
0
Outbound clicks
4
Citations
Views over time
Views by country
Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".
Traffic sources
Referring site, by host.
Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.