Statistical Prediction of Human Performance at Two Pattern Recognition Tasks.

Abstract

The objectives of this pilot study are to determine if it is possible (1) to predict human performance to displayed alphabetic characters that are presented in a varying noise background and (2) to predict at what range people have a 50% probability of identifying pictures of army vehicles. Each of the predictions is made using a model of the human visual system and statistical analysis. Predictions based on this analysis are compared to psychophysical performance. The results indicate the capability to predict the trend of human performance, thus warranting in-depth research into these areas.

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1974
Accession Number
ADA025789

Entities

People

  • Arthur G. Krempin
  • Earle E. Anderson

Organizations

  • Air Force Institute of Technology

Tags

DTIC Thesaurus Topics

  • Computing-Related Activities
  • Data Science
  • Information Science
  • Interdisciplinary Science
  • Mathematical Analysis
  • Mathematics
  • Motor Skills
  • Pattern Recognition
  • Personality
  • Pilot Studies
  • Probability
  • Recognition
  • Statistical Analysis
  • Statistics

Readers

  • Regression Analysis.
  • Systems Analysis and Design
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks