Research Summaries

Back Analytics of Aviator Training Performance

Fiscal Year 2020
Division Research & Sponsored Programs
Department NPS Naval Research Program
Investigator(s) Rowe, Neil C.
Sponsor NPS Naval Research Program (Navy)
Summary Military training data represents a frequently insufficiently exploited resource for assessment of training policies in general. While it is excellent for routine monitoring of individuals, it can be difficult to do analytics on it because of the many stovepiped solutions employed for it. We propose to conduct a study, coordinated with the study NPS-20-N309-A, of what can be done to improve analytic capabilities for Navy aviator training data. Part of this includes developing a database solution since we found in previous work that Marine aviation training data was spread over a bewildering array of incompatible software products. Part of this includes developing specialized analytic methods for the particular kind of training data involved in aviation. This study will particularly focus on prediction of aviator performance from past records, a good solution to which can have significant financial impact on the Navy. We propose to extend previous work in modeling carrier landing assessments to include a broader range of training data. This is a classic problem for machine learning where we can test predictions from early in an aviator¿s career against their records for later in their career. We will test several methods of machine learning including neural networks, Bayesian methods, and distribution modeling and report which works the best for this problem. We propose to continue this work on a broader collection of data that includes performance assessments on other kinds of aviation skills. We will investigate the benefits of building a model of pilot performance using machine learning; a neural network could represent a more precise model of the influences on performance.
Keywords
Publications Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal