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 Experiment Videos

Automated eye tracking system calibration using artificial neural networks.

M J Coughlin1, T R H Cutmore, T J Hine

  • 1School of Applied Psychology (Health Sciences), Mt Gravatt Campus, Griffith University, Brisbane, Queensland 4111, Australia.

Computer Methods and Programs in Biomedicine
|October 27, 2004
PubMed
Summary
This summary is machine-generated.

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

Automated ECG diagnostic P-wave analysis using wavelets.

Computer methods and programs in biomedicine·2010
Same author

[Not Available].

Operative Orthopadie und Traumatologie·2006
Same author

Intermediate and high peri-operative cardiac enzyme release following isolated coronary artery bypass surgery are independently associated with higher one-year mortality.

Journal of cardiothoracic surgery·2006
Same author

Low-probability event-detection and separation via statistical wavelet thresholding: an application to psychophysiological denoising.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2002
Same author

Operative treatment of interdigital neuroma. A long-term follow-up study.

The Journal of bone and joint surgery. American volume·2001
Same author

Roger A. Mann Award . The reliability of angular measurements in hallux valgus deformities. .

Foot & ankle international·2001
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026
Same journal

Relative spectral and frication-based descriptors as numerical indicators of place of articulation shifts in fricatives produced by Polish children.

Computer methods and programs in biomedicine·2026
Same journal

Leaflet resection improves valve expansion and hemodynamic performance in redo TAVI with balloon- and self-expanding transcatheter heart valve configurations.

Computer methods and programs in biomedicine·2026
Same journal

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026
See all related articles

Artificial neural networks (ANNs) can accurately convert electro-oculogram (EOG) recordings into precise eye positions. This advancement enhances the utility of EOG for eye movement analysis in clinical and research settings.

Area of Science:

  • Biomedical Engineering
  • Neuroscience
  • Computer Science

Background:

  • The electro-oculogram (EOG) is a common method for recording eye movements, particularly in clinical environments.
  • A significant limitation of EOG is the lack of efficient and accurate methods for converting raw data into quantifiable eye position.
  • This gap hinders the full potential of EOG in detailed eye-tracking applications.

Purpose of the Study:

  • To develop and evaluate an artificial neural network (ANN) model for accurate 2D eye position estimation from EOG recordings.
  • To compare the performance of multi-layer perceptrons (MLPs) against linear perceptrons (LPs) for EOG data calibration.
  • To assess the accuracy of the ANN-based EOG calibration against a gold-standard infrared eye tracker.

Main Methods:

Related Experiment Videos

  • Utilized multi-layer perceptrons (MLPs) with non-linear activation functions and backpropagation for training.
  • Simulated EOG data and real EOG recordings from five subjects were used for calibration.
  • Compared MLP performance against linear perceptrons (LPs) and an infrared eye tracker.

    • Main Results:

    • MLPs achieved a mean accuracy of 0.33 degrees on simulated EOG data.
    • For real EOG data, MLPs demonstrated a mean accuracy of 1.09 degrees, closely matching the infrared tracker's 0.98 degrees.
    • LP models were significantly less accurate than MLPs.
    • Transfer learning by using initial weights from another subject reduced MLP training time, achieving convergence in as few as 20 iterations.

    Conclusions:

    • MLPs provide an efficient and accurate method for calibrating 2D electro-oculogram data to eye position.
    • The accuracy achieved by MLPs is comparable to that of infrared eye trackers for saccadic eye movements.
    • ANNs, specifically MLPs, significantly enhance the utility of EOG recordings for precise eye-tracking applications.