Leveraging Subject Matter Expertise to Optimize Machine Learning Techniques for Air and Space Applications

Abstract

n this research, we develop machine learning and statistical methods that are tailored for Air Force applications throughthe incorporation of subject matter expertise. In particular, we develop techniques for incorporating subject matterknowledge in neural networks, Bayesian regression, and structural causal models. These techniques are developed in thecontext of three separate application areas: localizing point defects in transmission electron microscopy (TEM) ofcrystalline materials; estimating the relationship between attributes of fighter pilot communities and flight mishap rate;and analyzing Air Force evaluation process.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2022
Accession Number
AD1181527

Entities

People

  • Philip Y Cho

Organizations

  • Air Force Institute of Technology

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence
  • Aviation Accidents
  • Bayesian Networks
  • Commercial Aviation
  • Computational Science
  • Data Analysis
  • Data Mining
  • Data Science
  • Department Of Defense
  • Electron Microscopy
  • Information Science
  • Machine Learning
  • Military Aviation
  • Military Pilots
  • Neural Networks
  • Test And Evaluation

Fields of Study

  • Computer science

Readers

  • Aerospace logistics and air mobility.
  • Neural Network Machine Learning.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks
  • Microelectronics
  • Space