Related Experiment Video
Updated: Jun 2, 2026
Eye Tracking During A Complex Aviation Task For Insights Into Information Processing
Published on: April 4, 2025
Predicting success in the tactical air combat party training pipeline
John Kalns1, Jonathan Baskin, Andrew Reinert
1Hyperion Biotechnology, 13302 Langtry Street, San Antonio, TX 78248, USA.
Objectives:
To develop a statistical model that predicts the likelihood of success or failure of military training candidates using tests administered before initial skill training as inputs.
Methods:
Data were acquired from candidates before the start of U.S. Air Force Tactical Air Control Party training, including (1) demographic, (2) psychological composition evaluated using Emotional Quotient Inventory, (3) physical performance capability, (4) a physical activity questionnaire, and (5) salivary fatigue biomarker index. A total of 126 candidates were tracked until they either passed or failed the training, and a total of 55 variables were used as inputs for creation of the model.
Results:
Clustering analysis of the data revealed that only 4 of 55 variables were useful for predicting success or failure. The variables in the order of their importance are as follows: run time, number of miles run per week in the last year, level of salivary fatigue biomarker, and height.
Conclusions:
The results suggest that simple testing methods can identify candidates at high risk of failure.
