Neural Network Classification of Mental Workload Conditions by Analysis of Spontaneous Electroencephalograms

Abstract

Artificial neural networks were explored in this study to determine their capability to discriminate workload tasks on the basis of electroencephalograms (EEGs) recorded during task performance. EEG traces were recorded by placing electrodes at the occipital (Oz), parietal (Pz), central (Cz), and frontal (Fz) midline positions during workload tasks. Two conditions of workload were presented to the subjects. The first condition, an eye condition, varied whether eyes were open or closed while subjects counted or sat quietly. In the second condition, the workload conditions presented to the subjects were high and low levels of display monitoring and math processing tasks.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1991
Accession Number
ADA243369

Entities

People

  • Gretchen D. Lizza

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Advanced Electronics
  • Energy and Power Technologies
  • Human Systems
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Accuracy
  • Analysis Of Variance
  • Artificial Intelligence
  • Classification
  • Cognition
  • Cognitive Workload
  • Computers
  • Discriminant Analysis
  • Human Factors Engineering
  • Information Processing
  • Information Science
  • Medical Personnel
  • Neural Networks
  • Psychology
  • Psychophysiology
  • Signal Processing
  • Statistical Analysis

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks