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

You might also read

Related Articles

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

Sort by
Same author

[Model establishment of liver fibrosis in oral arsenic solution exposed mice].

Zhonghua yi xue za zhi·2009
Same author

Effect of human cytomegalovirus infection on nerve growth factor expression in human glioma U251 cells.

Biomedical and environmental sciences : BES·2009
Same author

[Study on the mechanism of arsenic trioxide inhibiting NB4 cells proliferation].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2009
Same author

Reversal of P-glycoprotein-mediated multidrug resistance by guggulsterone in doxorubicin-resistant human myelogenous leukemia (K562/DOX) cells.

Die Pharmazie·2009
Same author

Structures of discoidal high density lipoproteins: a combined computational-experimental approach.

The Journal of biological chemistry·2009
Same author

Dynamic regulation of GSH synthesis and uptake pathways in the rat lens epithelium.

Experimental eye research·2009

Related Experiment Video

Updated: Oct 7, 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

818

Reliability Analysis for Finger Movement Recognition With Raw Electromyographic Signal by Evidential Convolutional

Yuzhou Lin, Ramaswamy Palaniappan, Philippe De Wilde

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |January 7, 2022
    PubMed
    Summary

    This study introduces a new reliability metric for surface electromyography (sEMG) hand gesture recognition. An evidential convolutional neural network (ECNN) classifier demonstrates improved reliability and accuracy over traditional methods.

    More Related Videos

    Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
    11:25

    Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

    Published on: July 26, 2013

    43.6K
    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
    06:37

    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

    Published on: July 14, 2023

    1.0K

    Related Experiment Videos

    Last Updated: Oct 7, 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

    818
    Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
    11:25

    Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

    Published on: July 26, 2013

    43.6K
    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
    06:37

    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

    Published on: July 14, 2023

    1.0K

    Area of Science:

    • Biomedical Engineering
    • Machine Learning
    • Human-Computer Interaction

    Background:

    • Surface electromyography (sEMG) is crucial for muscle-gesture-computer interfaces, but reliability of gesture recognition models is understudied.
    • Existing research primarily focuses on accuracy and robustness, neglecting model reliability and uncertainty estimation.

    Purpose of the Study:

    • To define and quantify model reliability in sEMG-based hand gesture recognition.
    • To propose a novel uncertainty-aware classifier, the evidential convolutional neural network (ECNN), to enhance model reliability.
    • To evaluate the performance and reliability of ECNN against traditional Convolutional Neural Networks (CNNs).

    Main Methods:

    • Developed an offline framework to quantify model reliability based on uncertainty estimation quality.
    • Proposed and implemented an end-to-end evidential convolutional neural network (ECNN) for finger movement classification.
    • Conducted comparative analysis of CNN and ECNN variants on NinaPro Database 5, exercise A, for 12 finger movements across 10 subjects.

    Main Results:

    • The proposed ECNN achieved a mean accuracy of 76.34%, surpassing state-of-the-art performance.
    • ECNN variants demonstrated significantly improved reliability compared to standard CNN, with a highest reliability improvement of 19.33%.
    • Multidimensional uncertainties (vacuity, dissonance) of ECNN were shown to be advantageous for reliability analysis.

    Conclusions:

    • The evidential convolutional neural network (ECNN) offers enhanced reliability and competitive accuracy for sEMG-based hand gesture recognition.
    • The proposed reliability analysis framework provides a valuable supplementary measure for evaluating sEMG classifiers.
    • This work highlights the potential of uncertainty-aware models for more dependable human-computer interfaces.