Performance Evaluation of Certified Pilots in Flight Simulator
Date of Award
2023
Degree Name
M.S. in Computer Science
Department
Department of Computer Science
Advisor/Chair
Tam V. Nguyen
Abstract
As information technology advances swiftly, virtual reality (VR) technology has moved from theory to application. Performance analysis is one area where VR technology is having an ever-growing impact. VR technology can be viewed as an aid that can be used to simulate specific tasks. Applications of machine learning algorithms, using the output data that is retrieved, can be used for human performance predictive models. This thesis explores how virtual reality technology can be used to analyze the performance of certified aircraft pilots executing simulated, routine inflight maneuvers based on machine learning algorithms using either descriptive or temporal data, or combinations thereof. The results provide human-machine applications for ranking common machine learning algorithms that can be used for performance prediction and error analysis within knowledge-based behaviors. This thesis also explores how virtual reality technology can be used to analyze the motor control techniques, or behaviors, of certified pilots used to achieve those specified tasks. Specifically using the data that is retrieved, regression analyses can be used to forecast human-machine behavior. This part of the work demonstrates the improvement made using multiple output regression models over single regression models to forecast pilot behavior during simulated flight activities.
Keywords
Aerospace Engineering, Aerospace Materials, Department of Computer Science, Performance Evaluation of certified Pilots, Performance of Pilots in flight simulator Pilots in Virtual Reality, Evaluation between Single and multi-output regression Performance of pilots in different environments
Rights Statement
Copyright © 2023, author
Recommended Citation
Krishna, Anandu, "Performance Evaluation of Certified Pilots in Flight Simulator" (2023). Graduate Theses and Dissertations. 7230.
https://ecommons.udayton.edu/graduate_theses/7230