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

Differences in Perspectives and Policies Regarding End-of-Life Care Between Hematologists and Gastroenterologists.

Cancer medicine·2026
Same author

[Successful treatment of cardiac tamponade due to/pericardial infiltration with pericardial drainage and intrapericardial chemotherapy in a patient with acute myeloid leukemia].

[Rinsho ketsueki] The Japanese journal of clinical hematology·2026
Same author

Mirogabalin efficacy and safety for chemotherapy-induced peripheral neuropathy: single-centre retrospective observational study.

BMJ supportive & palliative care·2025
Same author

SMU-pRMS: a novel cell line of pleomorphic rhabdomyosarcoma.

Human cell·2025
Same author

Autism Spectrum Disorder Detection Using Prominent Connectivity Features from Electroencephalography.

International journal of neural systems·2025
Same author

Efficacy of eribulin monotherapy for bone marrow carcinomatosis of breast cancer in a patient with Werner syndrome.

Geriatrics & gerontology international·2025

Related Experiment Video

Updated: Jul 18, 2025

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

16.7K

Improved EEG-based emotion recognition through information enhancement in connectivity feature map.

M A H Akhand1, Mahfuza Akter Maria2, Md Abdus Samad Kamal3

  • 1Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna, 9203, Bangladesh. akhand@cse.kuet.ac.bd.

Scientific Reports
|August 23, 2023
PubMed
Summary

Combining EEG connectivity features improves emotion recognition accuracy. Fused connectivity feature maps (CFMs) using methods like phase-locking value (PLV) and mutual information (MI) enhance machine learning models for better human emotion recognition (ER).

More Related Videos

Brain Imaging Investigation of the Neural Correlates of Emotion Regulation
14:04

Brain Imaging Investigation of the Neural Correlates of Emotion Regulation

Published on: August 26, 2011

12.6K
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

9.1K

Related Experiment Videos

Last Updated: Jul 18, 2025

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

16.7K
Brain Imaging Investigation of the Neural Correlates of Emotion Regulation
14:04

Brain Imaging Investigation of the Neural Correlates of Emotion Regulation

Published on: August 26, 2011

12.6K
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

9.1K

Area of Science:

  • Neuroscience and Artificial Intelligence
  • Brain-Computer Interfaces
  • Machine Learning for Affective Computing

Background:

  • Electroencephalography (EEG) is a key brain signal for automatic human emotion recognition (ER).
  • Extracting informative features from EEG signals is crucial for accurate ER.
  • Existing methods for constructing connectivity feature maps (CFMs) from EEG signals, such as Pearson correlation coefficient (PCC), mutual information (MI), phase-locking value (PLV), and transfer entropy (TE), often result in symmetric and redundant data representations.

Purpose of the Study:

  • To propose an innovative technique for constructing more informative CFMs for improved EEG-based ER.
  • To investigate the efficacy of fusing connectivity measures from different methods to create enhanced CFMs.
  • To evaluate the performance of fused CFMs in classifying emotions using machine learning models without increasing computational costs.

Main Methods:

  • Constructed fused CFMs by combining pairs of established connectivity measures: PCC, PLV, MI, and TE.
  • Generated six types of fused CFMs: PCC+PLV, PCC+MI, PCC+TE, PLV+MI, PLV+TE, and MI+TE.
  • Utilized a convolutional neural network (CNN) to classify emotions based on the proposed fused CFMs.
  • Conducted experiments on the benchmark DEAP EEG dataset.

Main Results:

  • The proposed fused CFMs demonstrated superior ER performance compared to CFMs derived from single connectivity methods.
  • Fused CFMs, such as PLV+MI, showed significant improvements in emotion classification accuracy.
  • The fusion approach did not introduce additional computational overhead during the machine learning model training phase.

Conclusions:

  • Combining different EEG channel connectivity measures into fused CFMs is an effective strategy to enhance ER.
  • The PLV+MI fused CFM emerged as the most promising approach, outperforming other single and fused methods.
  • This study offers a computationally efficient method for improving automatic human emotion recognition using EEG signals.