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

Enhancing Network Visibility and Security with Advanced Port Scanning Techniques.

Sensors (Basel, Switzerland)·2023
Same author

Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification.

Sensors (Basel, Switzerland)·2022
Same author

Extraction and Calculation of Roadway Area from Satellite Images Using Improved Deep Learning Model and Post-Processing.

Journal of imaging·2022
Same author

Improved image classification explainability with high-accuracy heatmaps.

iScience·2022
Same author

Learning Subject-Generalized Topographical EEG Embeddings Using Deep Variational Autoencoders and Domain-Adversarial Regularization.

Sensors (Basel, Switzerland)·2021
Same author

Cross-Frequency Power-Power Coupling Analysis: A Useful Cross-Frequency Measure to Classify ICA-Decomposed EEG.

Sensors (Basel, Switzerland)·2020
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: Nov 10, 2025

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

12.0K

A Comparative Study of Window Size and Channel Arrangement on EEG-Emotion Recognition Using Deep CNN.

Panayu Keelawat1,2, Nattapong Thammasan3, Masayuki Numao4

  • 1Department of Computer Science and Engineering, University of California San Diego, La Jolla, CA 92093-0404, USA.

Sensors (Basel, Switzerland)
|April 3, 2021
PubMed
Summary
This summary is machine-generated.

Optimizing convolutional neural network (CNN) hyperparameters like window size significantly improves electroencephalogram-based emotion recognition. Valence recognition performed best with an 8-second window, while arousal recognition was optimal with a 10-second window.

Keywords:
CNNEEGbrainwaveelectrode orderemotion recognitionmachine learningneurosciencespatiotemporal datawindow size

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

14.1K
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

21.7K

Related Experiment Videos

Last Updated: Nov 10, 2025

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

12.0K
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

14.1K
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

21.7K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Affective Computing

Background:

  • Emotion recognition using electroencephalograms (EEGs) is a challenging research area, particularly for subject-independent tasks.
  • Convolutional Neural Networks (CNNs) show promise for generalization in emotion recognition from brainwaves.

Purpose of the Study:

  • To investigate the impact of CNN hyperparameter selection, specifically window size and electrode order, on subject-independent emotion recognition.
  • This study is the first to extensively analyze the effect of parameter selection on CNN performance for EEG-based emotion recognition.

Main Methods:

  • Employed machine learning techniques, focusing on CNNs, for emotion recognition from EEG data.
  • Systematically manipulated CNN hyperparameters, including temporal window size and electrode ordering, to assess their influence on classification accuracy.
  • Compared CNN performance with Support Vector Machines (SVM) regarding sensitivity to window size variations.

Main Results:

  • Temporal information, determined by window size, significantly impacts emotion recognition performance.
  • CNNs demonstrated greater responsiveness to window size changes compared to SVMs.
  • Optimal performance for arousal classification was achieved with a 10-second window (56.85% accuracy, MCC 0.1369).
  • Optimal performance for valence classification was achieved with an 8-second window (73.34% accuracy, MCC 0.4669).
  • Spatial information from electrode order variations had a minimal effect on classification outcomes.

Conclusions:

  • Hyperparameter tuning, particularly window size, is crucial for enhancing CNN-based EEG emotion recognition.
  • Valence recognition significantly outperformed arousal recognition, potentially due to hemispheric asymmetry in brain activity.
  • CNNs offer a robust framework for subject-independent emotion recognition, with performance sensitive to temporal feature extraction.