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

Event-Driven Neuromorphic Gaze Decoding via e-Skin Electrooculography.

ACS nano·2026
Same author

High-ambition climate action in all sectors can achieve a 59% greenhouse gas emissions reduction in Korea by 2035.

Scientific reports·2026
Same author

Explainable AI-Enhanced Ensemble Protocol Using Gradient-Boosted Models for Zero-False-Alarm Seizure Detection from EEG.

Sensors (Basel, Switzerland)·2026
Same author

Improving single-trial detection of error-related potentials by considering the effect of heartbeat-evoked potentials in a motor imagery-based brain-computer interface.

Computers in biology and medicine·2025
Same author

Hybrid BCI for Meal-Assist Robot Using Dry-Type EEG and Pupillary Light Reflex.

Biomimetics (Basel, Switzerland)·2025
Same author

Event-related pupillary response-based authentication system using eye-tracker add-on augmented reality glasses for individual identification.

Frontiers in physiology·2024

Related Experiment Video

Updated: Jan 17, 2026

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

3.2K

AI-driven pupillary-computer interface via binary-coded flickering stimuli.

Sangin Park1, Sungchul Mun2

  • 1Next-generation Mechanical Design Laboratory, Korea University, Seoul, 04763, Republic of Korea.

Computers in Biology and Medicine
|September 18, 2025
PubMed
Summary
This summary is machine-generated.

A new pupillary-computer interface (PCI) uses pupil responses to light changes for interaction. This AI-powered system offers high accuracy and information transfer rates, providing a stable, low-training alternative to traditional hardware.

Keywords:
Brain–Computer Interface (BCI)Convolutional Neural Network (CNN)Human–Computer Interface (HCI)Keyboard spellerPupillary Light Reflex (PLR)Pupillary–Computer Interface (PCI)

More Related Videos

Stereoacuity Improvement using Random-Dot Video Games
06:25

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

15.0K
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.9K

Related Experiment Videos

Last Updated: Jan 17, 2026

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

3.2K
Stereoacuity Improvement using Random-Dot Video Games
06:25

Stereoacuity Improvement using Random-Dot Video Games

Published on: January 14, 2020

15.0K
Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition
07:45

Assessing Binocular Central Visual Field and Binocular Eye Movements in a Dichoptic Viewing Condition

Published on: July 21, 2020

4.9K

Area of Science:

  • Human-Computer Interaction
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Conventional brain-computer interfaces often require extensive user training and specialized hardware.
  • Pupillary responses to visual stimuli, known as the pupillary light reflex (PLR), offer a potential alternative for interaction.
  • Existing PLR-based interfaces face limitations in performance and complexity.

Purpose of the Study:

  • To develop and evaluate a novel pupillary-computer interface (PCI) leveraging AI for enhanced performance.
  • To overcome limitations of existing electroencephalogram-based hardware using pupil signal analysis.
  • To assess the classification accuracy and information transfer rate (ITR) of the proposed PCI system.

Main Methods:

  • A novel PCI system was designed using artificial intelligence to model pupil size variations.
  • Binary-coded visual stimuli with varying brightness were presented to participants.
  • Convolutional neural network (CNN)-based deep learning was employed for signal pattern classification.
  • Experiments were conducted with 12 healthy subjects using 4-, 10-, and 20-class stimuli.

Main Results:

  • The proposed PCI system achieved high classification accuracies: 91.84% (20-class), 93.84% (10-class), and 98.61% (4-class).
  • Information transfer rates (ITR) reached 59.74 bits/min (20-class), 62.04 bits/min (10-class), and 69.36 bits/min (4-class).
  • Performance significantly outperformed previous PLR-based interface studies.

Conclusions:

  • The developed PCI system offers a simple, cost-effective, and low-training interface solution.
  • The system demonstrates high accuracy and ITR, making it a viable alternative for human-computer interaction.
  • The proposed PCI maintains long-term stability and requires minimal user training.