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

Artificial Intelligence in Eye Disease: Recent Developments, Applications, and Surveys.

Diagnostics (Basel, Switzerland)·2022
Same author

Review of Machine Learning Applications Using Retinal Fundus Images.

Diagnostics (Basel, Switzerland)·2022
See all related articles

Related Experiment Video

Updated: Jun 29, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K

Bimodal Transformer with Regional EEG Data for Accurate Gameplay Regularity Classification.

Jinui Lee1,2, Jae-Ho Han1,3

  • 1Department of Brain and Cognitive Engineering, Korea University, 145 Anam Rd., Seoul 02841, Republic of Korea.

Brain Sciences
|March 28, 2024
PubMed
Summary

This study uses electroencephalography (EEG) and a novel bimodal Transformer model to classify game usage frequency. The model accurately predicts player engagement, aiding in customized game development for better player acquisition.

Keywords:
Transformerclassificationdeep learningelectroencephalographygaming industry

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

10.9K
EEG Mu Rhythm in Typical and Atypical Development
11:50

EEG Mu Rhythm in Typical and Atypical Development

Published on: April 9, 2014

25.8K

Related Experiment Videos

Last Updated: Jun 29, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

10.9K
EEG Mu Rhythm in Typical and Atypical Development
11:50

EEG Mu Rhythm in Typical and Atypical Development

Published on: April 9, 2014

25.8K

Area of Science:

  • Neuroscience
  • Computer Science
  • Human-Computer Interaction

Background:

  • Games are increasingly used in education and healthcare.
  • Understanding user behavior is vital for effective game development and player acquisition.
  • Existing methods for analyzing gameplay frequency lack precision.

Purpose of the Study:

  • To classify game usage frequency using electroencephalography (EEG) data.
  • To introduce a novel bimodal Transformer architecture for analyzing brain activity.
  • To provide insights for improving game development and player acquisition strategies.

Main Methods:

  • Utilized the multimodal mobile brain-body imaging (MOBI) dataset.
  • Categorized game usage frequency into 'often' and 'sometimes'.
  • Developed a bimodal Transformer model with dedicated channels for frontal (AF) and temporal (TP) lobes, integrating convolutional, self-attention, and cross-attention mechanisms.

Main Results:

  • Achieved classification accuracies of 88.86% (five-fold cross-validation) and 85.11% (leave-one-subject-out cross-validation).
  • The model effectively differentiated between AF and TP brain channels, revealing functional differences.
  • Demonstrated the model's capability in analyzing inter-channel correlations.

Conclusions:

  • The proposed model accurately classifies gameplay frequency, offering valuable insights for game development.
  • This methodology supports targeted player engagement and customized game design.
  • Contributes to strategic player acquisition through data-driven game development.