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

Emotion recognition of CNN bidirectional long short-term memory with center and Softmax loss function (CNN-BiLSTM-CS) EEG -based.

Cognitive neurodynamics·2025
Same author

Intelligent Song Recognition via a Hollow-Microstructure-Based, Ultrasensitive Artificial Eardrum.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2024
Same author

Optimal channel dynamic selection for Constructing lightweight Data EEG-based emotion recognition.

Heliyon·2024
Same author

Feature Pyramid Networks and Long Short-Term Memory for EEG Feature Map-Based Emotion Recognition.

Sensors (Basel, Switzerland)·2023
Same author

Polyphenols: Potential source of drugs for the treatment of ischaemic heart disease.

Pharmacology & therapeutics·2016
Same author

xCT deficiency induces autophagy via endoplasmic reticulum stress activated p38-mitogen-activated protein kinase and mTOR in sut melanocytes.

European journal of cell biology·2016

Related Experiment Video

Updated: Jun 29, 2025

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

Cross-subject EEG-based emotion recognition through dynamic optimization of random forest with sparrow search

Xiaodan Zhang1, Shuyi Wang1, Kemeng Xu1

  • 1School of Electronics and Information, Xi'an Polytechnic University, Xi'an, Shaanxi 710060, China.

Mathematical Biosciences and Engineering : MBE
|March 29, 2024
PubMed
Summary

This study introduces a Sparrow Search Algorithm-optimized Random Forest (SSA-RF) for more accurate cross-subject emotion recognition using EEG signals. The novel approach enhances classification accuracy, offering advancements in artificial intelligence and bioinformatics applications.

Keywords:
DTNLMNSSA-RFcross-subjectemotion recognition

More Related Videos

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.5K
Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion
15:57

Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion

Published on: May 4, 2011

16.5K

Related Experiment Videos

Last Updated: Jun 29, 2025

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: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.5K
Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion
15:57

Brain Imaging Investigation of the Memory-Enhancing Effect of Emotion

Published on: May 4, 2011

16.5K

Area of Science:

  • Neuroscience
  • Computer Science
  • Artificial Intelligence

Background:

  • EEG-based emotion recognition aims to classify emotions from brain signals.
  • Cross-subject emotion recognition faces challenges due to poor model parameter adaptability, leading to low accuracy.
  • Existing methods struggle with generalizing across different individuals.

Purpose of the Study:

  • To develop a more accurate cross-subject emotion recognition model.
  • To address the limitations of traditional Random Forest models in cross-subject scenarios.
  • To improve the adaptability of classification model parameters.

Main Methods:

  • Proposed a dynamically optimized Random Forest model named SSA-RF.
  • Utilized the Sparrow Search Algorithm (SSA) to dynamically optimize the decision tree number (DTN) and minimum leaf number (LMN) of the Random Forest.
  • Employed 12 features to construct optimal feature combinations.
  • Validated the model using the DEAP and SEED datasets.

Main Results:

  • Achieved 76.81% accuracy for binary classification on the DEAP dataset.
  • Attained 75.96% accuracy for triple classification on the SEED dataset.
  • Demonstrated superior performance compared to traditional Random Forest models.

Conclusions:

  • The SSA-RF model offers significant improvements in cross-subject emotion recognition accuracy.
  • Dynamic optimization of Random Forest parameters by SSA enhances model adaptability.
  • This research provides valuable insights for advancing artificial intelligence and bioinformatics applications in emotion recognition.