Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Prosopagnosia01:24

Prosopagnosia

156
Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...
156

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Structures of the Crimean-Congo hemorrhagic fever virus RNA-dependent RNA polymerase.

Cell discovery·2026
Same author

Lytic polysaccharide monooxygenases (LPMOs): A double-edged sword in biomass polysaccharide degradation.

Biotechnology advances·2026
Same author

Pathology-Informed Augmentation Improves Cross-Cohort IMU-to-vGRF Estimation Between Healthy Adults and Adults With Osteoarthritis.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026
Same author

Organizational culture, social capital, and emergency capacity in primary healthcare institutions: A cross-sectional structural equation modeling study comparing ordinary and older communities.

PloS one·2026
Same author

Efficacy of Pharyngeal Balloon Muscle Resistance Treatment in Post-Stroke Dysphagia: A Randomized Controlled Trial.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same author

Prismatic treatment combined with binocular visual training for intermittent exotropia: impact on visual function and quality of life.

Expert review of medical devices·2026

Related Experiment Video

Updated: Jun 24, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

441

Post-stroke hand gesture recognition via one-shot transfer learning using prototypical networks.

Hussein Sarwat1, Amr Alkhashab2, Xinyu Song1

  • 1School of Mechanical Engineering, Shanghai Jiao Tong University, Dongchuan Road, Shanghai, 200240, China.

Journal of Neuroengineering and Rehabilitation
|June 12, 2024
PubMed
Summary

This study introduces an advanced model for stroke survivor rehabilitation, achieving 82.2% hand-gesture recognition accuracy. This improves upon existing methods, enabling more reliable in-home therapy systems.

Keywords:
Few-shot learningHand gesture recognitionMachine learningPost-strokePrototypical networks

More Related Videos

Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another
05:12

Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another

Published on: September 18, 2017

545.9K
Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment
06:25

Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment

Published on: December 23, 2020

2.6K

Related Experiment Videos

Last Updated: Jun 24, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

441
Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another
05:12

Using Virtual Reality to Transfer Motor Skill Knowledge from One Hand to Another

Published on: September 18, 2017

545.9K
Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment
06:25

Capturing Representative Hand Use at Home Using Egocentric Video in Individuals with Upper Limb Impairment

Published on: December 23, 2020

2.6K

Area of Science:

  • Biomedical Engineering
  • Rehabilitation Technology
  • Machine Learning in Healthcare

Background:

  • In-home rehabilitation offers a promising alternative to conventional therapy for stroke survivors.
  • Wearable sensor inaccuracies due to physiological differences and sensor displacement challenge classifier performance, especially for stroke patients.
  • Developing reliable in-home systems for accurate gesture classification remains a significant hurdle.

Purpose of the Study:

  • To develop and evaluate an improved machine learning model for accurate hand-gesture recognition in stroke survivors using wearable sensors.
  • To address the challenges of physiological variability and sensor displacement in developing subject-independent classifiers.
  • To enhance the accuracy and reliability of in-home rehabilitation systems for post-stroke recovery.

Main Methods:

  • Twenty stroke survivors performed seven distinct gestures while wearing EMG, FMG, and IMU sensors.
  • A novel model incorporating prototypical networks for one-shot transfer learning, K-Best feature selection, and increased window size was developed.
  • The proposed model's performance was benchmarked against conventional transfer learning and various subject-dependent/independent classifiers (neural networks, LGBM, LDA, SVM).

Main Results:

  • The proposed model achieved a hand-gesture classification accuracy of 82.2%, significantly outperforming conventional methods (e.g., one-shot transfer learning with neural networks at 63.17%).
  • Performance was comparable to subject-dependent classifiers, surpassing other subject-independent models.
  • K-Best feature selection improved accuracy in 3 out of 6 classifiers, while increasing window size enhanced accuracy across all classifiers by an average of 4.28%.

Conclusions:

  • The developed model demonstrates significant improvements in hand-gesture recognition for stroke survivors compared to existing approaches.
  • Feature selection and window size optimization further enhance classification accuracy.
  • This approach holds potential for creating robust, subject-independent wearable sensor models, mitigating physiological differences and improving stroke rehabilitation outcomes.