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

Targeted Modulation of Eukaryotic Release Factor 1 (OseRF1) by an RNA Aptamer Enhances Drought Adaptation in Rice.

Plant biotechnology journal·2026
Same author

Dietary Coenzyme Q10 Supplementation Enhances Meat Quality, Nutritional Profile, and Antioxidant Status in Meat Rabbits.

Animals : an open access journal from MDPI·2026
Same author

MoS<sub>2</sub>/MoP@Ti<sub>3</sub>C<sub>2</sub>T<sub><i>x</i></sub> ternary heterostructure with dual heterointerfaces for accelerating polysulfide conversion kinetics in lithium-sulfur batteries.

Nanoscale·2026
Same author

Bound States in the Continuum Metasurfaces for Biomolecular Detection: A Review of Advances and Applications.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Functional Nitrile Ether Additives for High-Energy-Density Lithium Metal Batteries: Multiscale Mechanism Study on Cyanide Substitution Regulation.

The journal of physical chemistry. B·2026
Same author

Highly diverse diazotrophs drive high N<sub>2</sub> fixation rates in a shallow submarine hydrothermal system.

Fundamental research·2026

Related Experiment Video

Updated: Jul 3, 2025

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

MGFKD: A semi-supervised multi-source domain adaptation algorithm for cross-subject EEG emotion recognition.

Rui Zhang1, Huifeng Guo1, Zongxin Xu1

  • 1Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, PR China.

Brain Research Bulletin
|February 14, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a novel algorithm for cross-subject EEG emotion recognition, effectively addressing negative transfer with minimal labeled target data. The method significantly enhances classification accuracy, showing strong potential for real-world applications.

Keywords:
Emotion recognitionGolden subjectsNegative transferSemi-supervised domain adaptation algorithmTransfer learning

More Related Videos

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

13.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

Related Experiment Videos

Last Updated: Jul 3, 2025

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K
Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome
08:31

Conscious and Non-conscious Representations of Emotional Faces in Asperger's Syndrome

Published on: July 31, 2016

13.2K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Biomedical Engineering

Background:

  • Cross-subject electroencephalography (EEG) emotion recognition faces challenges due to negative transfer.
  • Existing models often overlook the negative transfer problem in EEG-based emotion recognition.
  • Limited labeled data from target subjects hinders personalized emotion recognition.

Purpose of the Study:

  • To propose a semi-supervised domain adaptive algorithm, MGFKD, to address negative transfer in cross-subject EEG emotion recognition.
  • To leverage few labeled samples from the target subject for improved model performance.
  • To enhance the efficiency and applicability of EEG-based emotion recognition systems.

Main Methods:

  • Developed a multi-domain geodesic flow kernel dynamic distribution alignment (MGFKD) algorithm.
  • Employed a GFK common feature extractor to project source and target subject features onto Grassmann manifold space.
  • Integrated a source domain selector to identify 'golden source subjects' using weak classifiers and target subject labels.
  • Utilized a label corrector with dynamic distribution balancing to refine pseudo-labels of the target subject.

Main Results:

  • MGFKD significantly outperformed unsupervised and semi-supervised domain adaptation algorithms on SEED and SEED-IV datasets.
  • Achieved high average accuracies (87.51±7.68% on SEED, 68.79±8.25% on SEED-IV) with only one labeled sample per target subject.
  • Accuracy further improved to 90.20±7.57% (SEED) and 69.99±7.38% (SEED-IV) with 5 labeled samples and 6 source domains.

Conclusions:

  • The proposed MGFKD algorithm effectively mitigates negative transfer in cross-subject EEG emotion recognition.
  • The algorithm demonstrates strong performance even with a minimal number of labeled samples from new subjects.
  • MGFKD holds significant application value for future real-time EEG-based emotion recognition systems.