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

Stratum-specific serum metabolic reprogramming in Saanen goats with graded Brucella serological reactivity under natural exposure.

Frontiers in veterinary science·2026
Same author

Propofol and Salvianolic Acid a Synergistically Attenuate LPS-Induced Myocardial Pyroptosis in Diabetic Mice via the SIRT1/HMGB1 Pathway.

Mediators of inflammation·2026
Same author

Serum copper and high-risk plaque: a promising finding that still requires clinical validation. Authors' reply.

Polish archives of internal medicine·2026
Same author

Decoding brandy flavor complexity: A multivariate analysis of grapes, origins, distillation techniques, and aging methods through flavoromics and chemometrics.

Food chemistry·2026
Same author

Sequential inoculation with indigenous non-Saccharomyces yeasts drives multi-dimensional quality improvement of cabernet Gernischt wine: Mechanisms for greenness masking, color stabilization, and phenolic modulation.

Food research international (Ottawa, Ont.)·2026
Same author

Strategic ultrasonic regulation of Saccharomyces cerevisiae fermentation for enhanced anthocyanin production and wine quality.

Food research international (Ottawa, Ont.)·2026

Related Experiment Video

Updated: Aug 3, 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

675

Upper Limb Movement Decoding Scheme Based on Surface Electromyography Using Attention-Based Kalman Filter Scheme.

Anyuan Zhang, Qi Li, Zhenlan Li

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |April 8, 2023
    PubMed
    Summary

    This study introduces an attention-based Kalman filter scheme (AKFS) to improve human movement decoding using surface electromyography. The AKFS enhances decoding accuracy by better extracting temporal information and incorporating system prior knowledge, outperforming traditional models.

    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

    43.4K
    Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction
    09:14

    Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction

    Published on: September 28, 2019

    11.5K

    Related Experiment Videos

    Last Updated: Aug 3, 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

    675
    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

    43.4K
    Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction
    09:14

    Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction

    Published on: September 28, 2019

    11.5K

    Area of Science:

    • Biomedical Engineering
    • Machine Learning
    • Neuroscience

    Background:

    • Convolutional neural networks (CNNs) are prevalent for human movement decoding from surface electromyography (sEMG).
    • Existing CNN models primarily capture spatial information, neglecting temporal dynamics and system prior knowledge, leading to suboptimal decoding accuracy.
    • Challenges include insufficient data for new subjects and limited transferability of models.

    Purpose of the Study:

    • To propose an attention-based Kalman filter scheme (AKFS) for enhanced human movement decoding from sEMG.
    • To improve the extraction of temporal information and integrate system prior knowledge into the decoding process.
    • To address data scarcity for new subjects via transfer learning and fine-tuning.

    Main Methods:

    • An attention-based CNN model was developed to extract richer temporal features from sEMG signals.
    • A Kalman filter (KF) was integrated to incorporate prior knowledge of the system dynamics.
    • Transfer learning with a fine-tuning strategy was employed to adapt the model for new subjects with limited data.
    • The AKFS was evaluated across intra-session, long-term intra-session, inter-subject, and fine-tuned inter-subject scenarios.

    Main Results:

    • The attention-based CNN model demonstrated superior performance over vanilla CNN and CNN-LSTM models in intra-session and long-term intra-session tasks.
    • After fine-tuning, the attention-based CNN model achieved higher decoding accuracy and lower response time compared to baseline models for new subjects.
    • The inclusion of the Kalman filter consistently improved decoding accuracy across all tested scenarios.
    • The proposed scheme effectively enhanced decoding accuracy by capturing temporal sEMG information and system priors.

    Conclusions:

    • The attention-based Kalman filter scheme significantly improves human movement decoding accuracy from sEMG.
    • The AKFS enhances temporal information extraction and incorporates valuable system prior knowledge.
    • Transfer learning enables efficient adaptation of the model to new subjects with minimal data, broadening its practical applicability.