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

Operator functional state classification using multiple psychophysiological features in an air traffic control task.

Glenn F Wilson1, Chris A Russell

  • 1Air Force Research Laboratory, Wright-Patterson Air Force Base, 2255 H St., OH 45504-7022, USA. glenn.wilson@wpafb.af.mil

Human Factors
|January 2, 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

The effects of day-to-day variability of physiological data on operator functional state classification.

NeuroImage·2011
Same author

Putting the brain to work: neuroergonomics past, present, and future.

Human factors·2008
Same author

Performance enhancement in an uninhabited air vehicle task using psychophysiologically determined adaptive aiding.

Human factors·2007
Same author

EEG correlates of G-induced loss of consciousness.

Aviation, space, and environmental medicine·2005
Same author

Real-time assessment of mental workload using psychophysiological measures and artificial neural networks.

Human factors·2004

This study shows artificial neural networks and discriminant classifiers accurately detect mental workload levels in air traffic controllers using psychophysiological data. This technology can identify operator overload for system testing and adaptive aiding.

Area of Science:

  • Human Factors
  • Cognitive Science
  • Psychophysiology

Background:

  • Assessing operator mental workload is crucial for safety and performance in high-stress environments like air traffic control.
  • Psychophysiological measures offer objective indicators of cognitive states.
  • Developing accurate classifiers for mental workload is essential for real-world applications.

Purpose of the Study:

  • To evaluate the efficacy of artificial neural network (ANN) and stepwise discriminant classifiers in discriminating four levels of mental workload.
  • To determine the accuracy of these classifiers using psychophysiological data during a simulated air traffic control task.
  • To explore the potential of these methods for detecting operator overload.

Main Methods:

  • Trained and tested ANN and stepwise discriminant classifiers on psychophysiological data from 7 air traffic controllers.

Related Experiment Videos

  • Utilized a simulated air traffic control task to induce varying levels of mental workload.
  • Employed feature reduction techniques, including saliency analysis for ANNs.
  • Analyzed classification accuracy for four workload levels and a two-class problem (acceptable load vs. overload).

    • Main Results:

    • Both ANN and stepwise discriminant classifiers achieved high classification accuracy, ranging from 84% to 88% for four workload levels.
    • Feature reduction in ANNs improved accuracy to a mean of 90%.
    • Classification accuracy reached nearly perfect levels (mean 98%) when distinguishing between acceptable load and overload.

    Conclusions:

    • Psychophysiological data can accurately discriminate between different levels of mental workload, including critical overload states.
    • The developed classifiers demonstrate significant potential for real-time monitoring of operator cognitive states.
    • Applications include system design evaluation, testing, and the development of adaptive support systems.