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

Monitoring working memory load during computer-based tasks with EEG pattern recognition methods

A Gevins1, M E Smith, H Leong

  • 1SAM Technology and EEG Systems Laboratory, San Francisco, CA 94105, USA. alan@eeg.com

Human Factors
|May 14, 1998
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

Developing a national treatment strategy for personality disorder in Ireland.

Irish journal of psychological medicine·2025
Same author

Pharmacogenomics of NSAID-Induced Upper Gastrointestinal Toxicity.

Frontiers in pharmacology·2021
Same author

The carbon partitioning of glucose and DIC in mixotrophic, heterotrophic and photoautotrophic cultures of Tetraselmis suecica.

Biotechnology letters·2021
Same author

Trainee experience in diagnosis and management of personality disorders.

Irish journal of psychological medicine·2020
Same author

The effect of a multidisciplinary care bundle on the incidence of delirium after hip fracture surgery: a quality improvement study.

Anaesthesia·2019
Same author

Client personal recovery and recovery orientation of an Irish suicide intervention charity.

Irish journal of psychological medicine·2018

We used electroencephalography (EEG) to monitor brain activity and accurately detect cognitive workload during computer tasks. This technology shows promise for real-time monitoring of mental effort in human-computer interaction.

Area of Science:

  • Neuroscience
  • Cognitive Science
  • Computer Science

Background:

  • Assessing cognitive load is crucial for optimizing human-computer interaction.
  • Existing methods for monitoring cognitive load can be invasive or impractical for real-time applications.

Purpose of the Study:

  • To evaluate the feasibility of using electroencephalography (EEG) spectral features and neural network pattern recognition to assess working memory load during computer use.
  • To determine if EEG patterns can reliably differentiate between various levels of cognitive workload.

Main Methods:

  • Eight participants performed working memory tasks at high, moderate, and low cognitive loads.
  • EEG data was recorded, focusing on frontal theta and alpha activity.
  • Neural network pattern recognition was applied to EEG spectral features for classification of cognitive load levels.
Keywords:
Non-programmatic

Related Experiment Videos

Main Results:

  • Frontal theta activity increased, and alpha activity decreased with rising cognitive load, indicating increased mental effort.
  • Neural networks achieved over 95% accuracy in discriminating between high and low cognitive load states.
  • Moderate load states were discriminated from high or low load states with over 80% accuracy.
  • The trained networks demonstrated significant generalization across different days, tasks, and participants.

Conclusions:

  • EEG spectral features, analyzed with neural networks, provide a reliable, non-invasive method for monitoring cognitive workload.
  • These findings support the potential of EEG-based systems for real-time cognitive load assessment in human-computer interaction.