UW-Madison is at the forefront in Systems Computing applied to Edge Computing architectures. Our multi-faceted approach engages several key disciplines needed to solve open problems with Edge implementations and drive adoption in compelling use cases.
The N+1 Institute enables industry leaders to engage with our pioneering researchers.
Online federated learning based object detection across autonomous vehicles in a virtual world
In the context of edge computing applications, the research "Online Federated Learning based Object Detection across Autonomous Vehicles in a Virtual World" explores a novel approach to improve the performance of object detection systems for self-driving cars.
Adaptive uplink data compression in spectrum crowdsensing systems
This research paper focuses on FlexSpec, a framework for adaptive uplink data compression in spectrum crowdsensing systems.
QfaR: Location-Guided Scanning of Visual Codes from Long Distances
This research paper presents QfaR, a novel system that enables mobile devices to scan visual codes (like QR codes) from significantly longer distances than traditional methods.
When Two Cameras Are a Crowd
This research paper explores the challenges and solutions related to multi-camera interference (MCI) in environments where multiple active 3D cameras operate simultaneously.
Cloud-LoRa: Enabling Cloud Radio Access LoRa Networks Using Reinforcement Learning Based Bandwidth-Adaptive Compression
This research paper introduces Cloud-LoRa, a novel approach to enhancing the performance of LoRa networks by leveraging cloud computing principles.
Sustainable Spectrum Crowdsensing
This research paper focuses on Sustainable Spectrum Crowdsensing, a paradigm that leverages the power of edge computing to measure spectrum usage in wireless networks using crowdsourced data from diverse sensors.
Hierarchical Federated Learning with Privacy
This research paper explores the challenges of privacy in traditional federated learning (FL) systems, where gradient updates are shared with a central server. These gradient updates can be exploited by adversaries to infer private information about the training data.
Exploring the Design Space of Optical See-through AR Head-Mounted Displays to Support First Responders in the Field
This research paper investigates the design space of optical see-through AR head-mounted displays (HMDs) specifically tailored for first responders in the field.