Title: Sensing Systems for Studying Animal Activities, Behavior, and Communication
Date: October 22nd, 2024
Time: 9:00 AM - 11:00 AM EDT
Location: Technology Square Research Building (85 5th St NW), Room 217a
Virtual meeting: https://gatech.zoom.us/j/91435374840?pwd=jjnQ1VkN5kmhaGXFObaWmz7f9bR1jl.1&from=addon
Charles Ramey
School of Interactive Computing
College of Computing
Georgia Institute of Technology
Committee:
Dr. Thad Starner (co-advisor) - School of Interactive Computing, Georgia Institute of Technology
Dr. Melody Jackson, (co-advisor) - School of Interactive Computing, Georgia Institute of Technology
Dr. Thomas Ploetz - School of Interactive Computing, Georgia Institute of Technology
Dr. Omer Inan - School of Electrical and Computer Engineering, Georgia Institute of Technology
Dr. David Roberts - College of Engineering, North Carolina State University
Abstract:
The field of Animal Computer Interaction was founded as an interdisciplinary community of researchers for the development of technology that improves animal welfare, supports animal agency, and fosters the relationship between humans and non-human animals. While wearable and ubiquitous sensing systems for humans only need to concern themselves with designing around the form factor, affordances, sensing, and articulation ability of a single species, this is not the case within sensing systems developed for studying similar phenomena in animals. Technologies for studying animals must be designed across these dimensions and more, including environment and domestication status, for each new system.
While the unique contexts across design dimensions limit the development of generalized animal-centered technology frameworks, advances in digital sensing technologies and manufacturing techniques have made the creation of bespoke computing systems that are optimized for each study's unique set of constraints more accessible than ever. In this dissertation, I present three novel animal-centered studies, each leveraging an embedded sensing system, custom study methodology, and time-series machine learning-based analysis to recognize animal activities, characterize animal-object interactions, and mediate two-way acoustic interactions between animals and humans.