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

Babaodan suppresses inflammatory and vascular microenvironment in triple-negative breast cancer by inhibiting the cGAS-STING/NF-κB signaling pathway.

Journal of ethnopharmacology·2026
Same author

Signatures of fractional charges via anyon-trions in twisted MoTe<sub>2</sub>.

Nature·2026
Same author

Atomically Resolved Acoustic Dynamics Coupled with Magnetic Order in a Van der Waals Antiferromagnet.

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

Spatiotemporal trends and driving factors of gonorrhea incidence in China: a 20-year analysis (2003-2022).

Frontiers in public health·2026
Same author

Development and comparison of machine learning models for predicting moderate-to-severe tinnitus in patients with hearing loss.

Frontiers in neurology·2026
Same author

Optical control of integer and fractional Chern insulators.

Nature·2026

Related Experiment Video

Updated: Jul 8, 2025

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

10.2K

Cross-subject emotion EEG signal recognition based on source microstate analysis.

Lei Zhang1, Di Xiao1, Xiaojing Guo2

  • 1Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China.

Frontiers in Neuroscience
|December 13, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces source microstate analysis for improved cross-subject emotion recognition from electroencephalogram (EEG) signals. This method enhances accuracy by better utilizing spatial information, outperforming traditional methods like PSD and DE.

Keywords:
EEGcross-subjectemotion recognitionsource microstatestyle transfer mapping

More Related Videos

Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.4K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.7K

Related Experiment Videos

Last Updated: Jul 8, 2025

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

10.2K
Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.4K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.7K

Area of Science:

  • Neuroscience
  • Signal Processing
  • Machine Learning

Background:

  • Electroencephalogram (EEG) signals suffer from low spatial resolution, limiting accuracy in cross-subject emotion classification.
  • Microstate analysis offers a way to capture spatiotemporal characteristics of EEG signals by clustering them into prototype topographies.
  • Utilizing spatial information is crucial for improving the neural representation of emotional dynamics.

Purpose of the Study:

  • To enhance cross-subject EEG-based emotion classification accuracy by leveraging spatial information through source microstate analysis.
  • To investigate the robustness and abstract emotional information represented by source microstate features.
  • To compare the performance of source microstate features against traditional features (DE, PSD) in SVM and CNN models.

Main Methods:

  • Conducted source localization analysis on EEG signals to reconstruct sources.
  • Performed microstate analysis on source-reconstructed EEG signals to extract microstate features.
  • Applied style transfer mapping for domain adaptation and utilized Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs) for emotion recognition.

Main Results:

  • Source microstate feature topologies showed high correlation across participants for the same emotion.
  • Microstate features demonstrated more abstract emotional information and greater robustness compared to DE and PSD.
  • Cross-subject classification accuracies using microstate features in SVMs were 7.19-8.24% higher than PSD and 0.51-6.95% higher than DE.
  • In CNNs, microstate features achieved 7.71-19.41% higher accuracy than PSD and 2.7-11.76% higher than DE.

Conclusions:

  • Source microstate analysis effectively utilizes spatial information in EEG signals for more accurate cross-subject emotion recognition.
  • Microstate features provide a robust and abstract representation of emotional dynamics, outperforming conventional spectral and entropy-based features.
  • The proposed method shows significant potential for advancing brain-computer interfaces and affective computing applications.