Dangerous Animal Detection and Alerting
Authors: Saurav Koduri (University of Illinois Urbana-Champaign) and Avasyu Chukkapalli (Virginia Tech)
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)
Kyle Lima
Authors: Jordan Gurneau (Northwestern University), Ella Neumann (Georgia Tech / MIT), Dave MacDonald (UC Davis), Deanna DiMonte (Northwestern University), and Morty (lead)
The Big Picture
Authors: Noah Betoshana (University of California, Davis) and Liam Fitzpatrick (Michigan State University)
Ice and snowfall are incredibly important parts of a river ecosystem. The Bad River is home to wild rice, which is very temperamental and prone to natural boom/bust years. Having a snow classifier can be used to create a larger dataset of snow that can be used for a variety of these additional tasks including assisting with predicting wild rice yields.
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