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

Cistanoside A decreases Tau hyperphosphorylation and neuronal apoptosis through the AKT/GSK3β pathway in okadaic acid-induced in vivo and in vitro models of Alzheimer's disease.

Molecular biology reports·2026
Same author

Integrative profiling of glymphatic dysfunction in adolescent subthreshold depression.

Journal of affective disorders·2026
Same author

Identification of shared diagnostic biomarkers and molecular pathways between chronic kidney disease and renal cell carcinoma using transcriptomics and machine learning.

Translational cancer research·2026
Same author

Cold-stimulated browning graft fat enhances burn wound recovery through accelerating DAMP-ADSC activation.

Journal of tissue engineering·2026
Same author

Janus nanomotors for topical treatment of radiation-induced dermatitis.

Nature communications·2026
Same author

TCF-CBM: a three-stage collaborative poisoned sample filtering method based on composite backdoor mechanism.

Scientific reports·2026

Related Experiment Video

Updated: Jun 27, 2025

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets
08:45

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

9.2K

Attention-ProNet: A Prototype Network with Hybrid Attention Mechanisms Applied to Zero Calibration in Rapid Serial

Baiwen Zhang1, Meng Xu2, Yueqi Zhang2

  • 1Institute of Information and Artificial Intelligence Technology, Beijing Academy of Science and Technology, Beijing 100089, China.

Bioengineering (Basel, Switzerland)
|April 27, 2024
PubMed
Summary

This study introduces Attention-ProNet, a novel zero-calibration method for rapid serial visual presentation-based brain-computer interfaces (RSVP-BCI). It enables efficient and accurate decoding of new subjects without retraining, significantly reducing calibration time.

Keywords:
Attention-ProNethybrid attention mechanismprototype networksrapid serial visual presentation (RSVP)zero-calibration (ZC)

More Related Videos

Methods to Test Visual Attention Online
09:44

Methods to Test Visual Attention Online

Published on: February 19, 2015

11.9K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K

Related Experiment Videos

Last Updated: Jun 27, 2025

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets
08:45

A Dual Task Procedure Combined with Rapid Serial Visual Presentation to Test Attentional Blink for Nontargets

Published on: December 5, 2014

9.2K
Methods to Test Visual Attention Online
09:44

Methods to Test Visual Attention Online

Published on: February 19, 2015

11.9K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K

Area of Science:

  • Neuroscience
  • Computer Science
  • Biomedical Engineering

Background:

  • Rapid serial visual presentation-based brain-computer interfaces (RSVP-BCI) rely on electroencephalogram (EEG) signal analysis for target image recognition.
  • Reducing training and calibration time for RSVP-BCI classification models across diverse subjects is a critical challenge for practical applications.

Purpose of the Study:

  • To develop an innovative and high-performance zero-calibration (ZC) RSVP-BCI decoding model algorithm.
  • To address the issue of lengthy training and calibration times in current RSVP-BCI systems.

Main Methods:

  • Proposed Attention-ProNet, a ZC method utilizing meta-learning with a prototype network and multiple attention mechanisms.
  • Employed multiscale attention for efficient EEG feature extraction and a hybrid attention mechanism for enhanced model generalization.
  • Incorporated data augmentation and channel selection techniques to optimize the decoding model.

Main Results:

  • Attention-ProNet achieved a balance accuracy (BA) of 86.33% in decoding tasks for new subjects.
  • The integration of channel selection and data augmentation further improved network performance, increasing BA by an additional 2.3%.
  • The developed model demonstrated efficient and accurate decoding without the need for recalibration or retraining for new users.

Conclusions:

  • Attention-ProNet effectively reduces training and calibration time for RSVP-BCI systems.
  • The meta-learning prototype network with integrated attention mechanisms offers a promising solution for practical BCI applications.
  • Optimized channel selection and data augmentation strategies are crucial for maximizing the performance of ZC RSVP-BCI models.