20 docs tagged with "Edge AI"

Author: Yufeng Luo, MCS Research Aide, University of Wyoming, Summer 2024

Henry Abrahamson

Hi there! My name is Spencer Ng, and I’m a rising second-year studying Computer Science and Theater & Performance Studies at the University of Chicago.

Across the United States and the world, the distributed network of Sage nodes captures over 2500 images per day. These nodes have the potential of capturing photos with important features such as smoke, wildlife, and emergencies. Each image contains unique characteristics which, until now, were hard to look for without manually searching through the Sage database. With both the images and users in mind, this project has two goals: harness the power of machine learning to describe photos as they are taken, and build a user-friendly system to allow others to find what they are looking for within our database.

Authors: Saurav Koduri (University of Illinois Urbana-Champaign) and Avasyu Chukkapalli (Virginia Tech)

Authors: Jeongmin Chae (University of Southern California) and Julia Gersey (University of Michigan / Argonne National Lab)

Introduction

Kyle Lima

Authors: Sajan Neupane (University of Utah) and Pratik Kharade (University of Utah – SCI Institute)

Authors: Samuel Watson (University of Hawaiʻi at Mānoa / HCDP)

Authors: Di Fan (University of Florida), Levi Johnson (Colorado State University), John Blackwell (Colorado State University), and Atefeh Hosseini (University of Kansas)

Authors: Dave MacDonald (UC Davis), Sean Huang (University of Chicago), Clément Nunes (Inria), and Morty

Abstract

Authors: Noah Betoshana (University of California, Davis) and Liam Fitzpatrick (Michigan State University)

Authors: Ben Owusu-Amo and Hairik Honarchian Saki (Colorado State University)

Can Edge Computing Be Used in X-Ray Beamline Experiments to Process a High-Volume and Fast Data Stream and Help Scientists Make Real-Time Decisions for Experiments?

By processing data directly at the collection source, edge computing networks like Sage/Waggle offer unique advantages over using centralized servers for ecological monitoring tasks. Audio in particular is useful for tracking metrics like noise pollution from human development or population statistics for vocal wildlife in the area (birds, insects, frogs, etc.). Further analysis can provide deeper insights into the overall health of the ecosystems where nodes are deployed.

Miguel Hernandez, Northwestern University

NOTE: This document is based on the version 1.0.3 of the traffic counter application.

Hi there!