Drone Detection Using Tiny Machine Learning
Date of Award
12-12-2024
Degree Name
M.S. in Electrical Engineering
Department
Department of Electrical and Computer Engineering
Advisor/Chair
James Browning
Abstract
As Machine Learning (ML) technology advances, the devices and servers required to collect, process, and store data are becoming increasingly complex. Tiny Machine Learning (TinyML) addresses this challenge by enabling simple ML models to run on small, low-power devices, such as microcontrollers. By processing data locally, TinyML reduces the amount of data that must be transferred to a server, resulting in greater spectral efficiency and faster response times. One practical application of TinyML is drone detection in modern warfare. A low-cost microcontroller with an integrated microphone can be equipped with a TinyML model to detect drone presence, provide immediate warnings, and operate with an extended battery life—enhancing both functionality and portability in field conditions.
Keywords
Tiny Machine Learning, Edge Computing, Drone Detection, Acoustic Drone Detection
Rights Statement
Copyright © 2024, author.
Recommended Citation
Mays, Eric, "Drone Detection Using Tiny Machine Learning" (2024). Graduate Theses and Dissertations. 7478.
https://ecommons.udayton.edu/graduate_theses/7478
