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

Test of hirudin activity by tracking the binding of hirudin to thrombin in the presence of BS3 cross-linking.

Blood coagulation & fibrinolysis : an international journal in haemostasis and thrombosis·2015
Same author

Systemic lupus erythematosus and malignancies risk.

Journal of cancer research and clinical oncology·2015
Same author

Asexual sporulation facilitates adaptation: The emergence of azole resistance in Aspergillus fumigatus.

Evolution; international journal of organic evolution·2015
Same author

Analysis of potassium iodate reduction in tissue homogenates using high performance liquid chromatography-inductively coupled plasma-mass spectrometry.

Journal of trace elements in medicine and biology : organ of the Society for Minerals and Trace Elements (GMS)·2015
Same author

Disruption of eyelid and cornea morphogenesis by epithelial β-catenin gain-of-function.

Molecular vision·2015
Same author

Intelligent Tracking Control for a Class of Uncertain High-Order Nonlinear Systems.

IEEE transactions on neural networks and learning systems·2015

Related Experiment Video

Updated: Mar 3, 2026

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

9.5K

Cross-Subject EEG Feature Selection for Emotion Recognition Using Transfer Recursive Feature Elimination.

Zhong Yin1, Yongxiong Wang1, Li Liu1

  • 1Shanghai Key Lab of Modern Optical System, Engineering Research Center of Optical Instrument and System, Ministry of Education, University of Shanghai for Science and TechnologyShanghai, China.

Frontiers in Neurorobotics
|April 27, 2017
PubMed
Summary

This study introduces transfer recursive feature elimination (T-RFE) for more accurate, subject-independent emotion recognition from electroencephalogram (EEG) signals. The novel method efficiently identifies key EEG indicators, improving cross-subject emotion classification performance.

Keywords:
EEGaffective computingemotion recognitionphysiological signalsrecursive feature elimination

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

2.1K
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

14.7K

Related Experiment Videos

Last Updated: Mar 3, 2026

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

9.5K
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

2.1K
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

14.7K

Area of Science:

  • * Neuroscience and Machine Learning
  • * Computational Psychiatry
  • * Affective Computing

Background:

  • * Analyzing electroencephalogram (EEG) signals with machine learning for emotion recognition is promising due to objective physiological data.
  • * Subject-specific models require extensive individual training data, posing a burden on participants.
  • * A need exists for robust, cross-subject emotion classification methods that minimize individual data requirements.

Purpose of the Study:

  • * To develop a novel EEG feature selection approach, transfer recursive feature elimination (T-RFE), for cross-subject emotion classification.
  • * To identify robust EEG indicators with stable distributions across subjects.
  • * To validate the effectiveness of T-RFE in improving emotion recognition accuracy without subject-specific training.

Main Methods:

  • * Development of the transfer recursive feature elimination (T-RFE) algorithm for selecting stable EEG features.
  • * Introduction of a validating set to optimize T-RFE hyperparameters and control overfitting.
  • * Implementation of a linear least square support vector machine classifier for performance evaluation on the DEAP database.

Main Results:

  • * T-RFE demonstrated statistically significant improvements in emotion classification compared to conventional feature selection methods.
  • * Achieved classification rates and F-scores of 0.7867 (arousal), 0.7526 (valence), 0.7875 (arousal), and 0.8077 (valence).
  • * Outperformed several recent studies on the DEAP database and two subject-generic classifiers, despite longer training times.

Conclusions:

  • * The T-RFE approach effectively identifies robust EEG indicators for accurate cross-subject emotion classification.
  • * This method offers a viable alternative to subject-specific models, reducing data collection burdens.
  • * While T-RFE enhances accuracy, its computational training time is a consideration for real-time applications.