Date of Award

3-2023

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Electrical and Computer Engineering

First Advisor

David W. King, PhD

Abstract

Research towards improving the performance of artificial intelligence networks has found that larger and more complex networks tends to yield better results, and continuous hardware upgrades enables the development of larger, more complicated, and better performing neural networks. However, many devices that are widely available and more practical to everyday use, such as drones or smartphones, are unable to use the state-of-the-art neural networks because they simply do not have the processing capabilities to run them in addition to their normal function. It is possible to overcome this lower performance by using a variety of these smaller neural networks as an ensemble. However, tasks that use multiple mobile devices cannot guarantee that each ensemble member will receive the same perspective of the same object. Moreover, ensemble members cannot know for certain if they are all looking at the same object due to these multiple perspectives. Fortunately, this can be resolved using each device’s position and orientation to calculate an object’s position in the real world, allowing for aggregation on the same object despite the different perspectives.

AFIT Designator

AFIT-ENG-MS-23-M-050

Comments

A 12-month embargo was observed.

Approved for public release: 88ABW-2023-0202

Download

Share

COinS