Date of Award
Master of Science in Systems Engineering
Department of Systems Engineering and Management
Michael E. Miller, PhD.
Automation use continues to increase in Air Force systems with the goal of improving operator efficiency and effectiveness. Unfortunately, systems are often complex, potentially imposing increased mental task load on the operator, or placing the operator in a supervisory role where they can become dependent on automation. Adaptive automation is a proposed solution, where automation is triggered when an operator is overloaded, and disabled as the operator is underloaded. Changes in physiological measures have shown promise in triggering automation. Unfortunately heart rate measurement can be obtrusive and impractical in day-to-day operations. This research used the Air Force Multi-Attribute Task Battery to impose varying task loads on subjects while monitoring their performance, recording their heart rate information with an electrocardiogram and obtaining subjective estimates of mental workload. Simultaneously, hyperspectral images were captured to determine if changes in heart rate might be identified through these images, providing a remote assessment of heart rate (HR). HR and several heart rate variability measurements where significantly affected by Task Load. A linear regression model was developed to predict subjects' perceived workload as a function of a proposed summary performance metric and HR measures. Additionally, this research identified several requirements for remote HR monitoring techniques.
DTIC Accession Number
Splawn, Joshua M., "Applying Hyperspectral Imaging to Heart Rate Estimation for Adaptive Automation" (2013). Theses and Dissertations. 1014.