Li Yu

Date of Award

3-2022

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Systems Engineering and Management

First Advisor

Brent Langhals, PhD

Abstract

With ever more data becoming available to the US Air Force, it is vital to develop effective methods to leverage this strategic asset. Machine learning (ML) techniques present a means of meeting this challenge, as these tools have demonstrated successful use in commercial applications. For this research, three ML methods were applied to a unmanned aircraft system (UAS) telemetry dataset with the aim of extracting useful insight related to phases of flight. It was shown that ML provides an advantage in exploratory data analysis and as well as classification of phases. Neural network models demonstrated the best performance with over 90% accuracy in classifying of UAS phases of flight. Categorical and Regression Trees (CART) also performed well, whereas C5.0 is less suited for this task. In addition, several interesting patterns were uncovered within the dataset, which can aid UAS operators in identifying mission anomalies and atypical system operation.

AFIT Designator

AFIT-ENV-MS-22-M-275

DTIC Accession Number

AD1174742

Download

Included in

Data Science Commons

Share

COinS