skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on February 26, 2026

Title: Using Radar for Edge-based Live Learning
This paper describes how a system that performs Live Learning can be modified to use radar rather than visible light. The pipelined and iterative machine learning (ML) workflow of this system can operate at low network bandwidths for selective transmission of rare unlabeled events embedded in high-bandwidth real-time sensor data. While radar offers greater range and can overcome the severe signal attenuation experienced by visible light under conditions such as rain or fog, it poses a number of challenges for ML. This paper describes how these challenges can be overcome for Live Learning, and identifies some future directions for research.  more » « less
Award ID(s):
2106862
PAR ID:
10588988
Author(s) / Creator(s):
; ; ; ; ;
Publisher / Repository:
ACM
Date Published:
ISBN:
9798400714030
Page Range / eLocation ID:
31 to 36
Subject(s) / Keyword(s):
Edge Computing, Machine Learning, Computer Vision, Wireless Networks, Acoustic Networks, Remote Sensing, LPWAN
Format(s):
Medium: X
Location:
La Quinta CA USA
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; (, MLSys)
    Gibbons, PhillipB; Pekhimenko, Gennady; De_Sa, Christopher (Ed.)
    The emergence of ML in various cloud system management tasks (e.g., workload autoscaling and job scheduling) has become a core driver of ML-centric cloud platforms. However, there are still numerous algorithmic and systems challenges that prevent ML-centric cloud platforms from being production-ready. In this paper, we focus on the challenges of model performance variability and costly model retraining, introduced by dynamic workload patterns and heterogeneous applications and infrastructures in cloud environments. To address these challenges, we present FLASH, an extensible framework for fast model adaptation in ML-based system management tasks. We show how FLASH leverages existing ML agents and their training data to learn to generalize across applications/environments with meta-learning. FLASH can be easily integrated with an existing ML-based system management agent with a unified API. We demonstrate the use of FLASH by implementing three existing ML agents that manage (1) resource configurations, (2) autoscaling, and (3) server power. Our experiments show that FLASH enables fast adaptation to new, previously unseen applications/environments (e.g., 5.5× faster than transfer learning in the autoscaling task), indicating significant potential for adopting ML-centric cloud platforms in production. 
    more » « less
  2. ; ; ; ; ; ; ; ; (, MLSys)
    Gibbons, Phillip B; Gennady, P; De_Sa, Christopher (Ed.)
    The emergence of ML in various cloud system management tasks (e.g., workload autoscaling and job scheduling) has become a core driver of ML-centric cloud platforms. However, there are still numerous algorithmic and systems challenges that prevent ML-centric cloud platforms from being production-ready. In this paper, we focus on the challenges of model performance variability and costly model retraining, introduced by dynamic workload patterns and heterogeneous applications and infrastructures in cloud environments. To address these challenges, we present FLASH, an extensible framework for fast model adaptation in ML-based system management tasks. We show how FLASH leverages existing ML agents and their training data to learn to generalize across applications/environments with meta-learning. FLASH can be easily integrated with an existing ML-based system management agent with a unified API. We demonstrate the use of FLASH by implementing three existing ML agents that manage (1) resource configurations, (2) autoscaling, and (3) server power. Our experiments show that FLASH enables fast adaptation to new, previously unseen applications/environments (e.g., 5.5× faster than transfer learning in the autoscaling task), indicating significant potential for adopting ML-centric cloud platforms in production. 
    more » « less
  3. ; ; ; ; ; ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    The US weather radar archive holds detailed information about biological phenomena in the atmosphere over the last 20 years. Communally roosting birds congregate in large numbers at nighttime roosting locations, and their morning exodus from the roost is often visible as a distinctive pattern in radar images. This paper describes a machine learning system to detect and track roost signatures in weather radar data. A significant challenge is that labels were collected opportunistically from previous research studies and there are systematic differences in labeling style. We contribute a latent-variable model and EM algorithm to learn a detection model together with models of labeling styles for individual annotators. By properly accounting for these variations we learn a significantly more accurate detector. The resulting system detects previously unknown roosting locations and provides comprehensive spatio-temporal data about roosts across the US. This data will provide biologists important information about the poorly understood phenomena of broad-scale habitat use and movements of communally roosting birds during the non-breeding season. 
    more » « less
  4. ; (, Proceedings of the IISE Annual Conference & Expo 2023)
    Artificial Intelligence (AI) and Machine Learning (ML) capabilities have the potential for large-scale impact to tackle some of the world’s most pressing humanitarian challenges and help alleviate the suffering of millions of people. Although AI and ML systems have been leveraged and deployed by many humanitarian organizations, it remains unclear which factors contributed to their successful implementation and adoption. In this study, we aim to understand what it takes to deploy AI and ML capabilities successfully within the humanitarian ecosystem and identify challenges to be overcome. This preliminary research examines the deployment and application of an ML model developed by the Danish Refugee Council (DRC) for predicting forced displacement. We use qualitative methods to identify key barriers and enablers from a variety of sources describing the deployment of their Foresight model, a machine learning-based predictive tool. These results can help the humanitarian community to better understand enablers and barriers for deploying and scaling up AI and ML solutions. We hope this paper can spark discussions about the successful deployments of AI and ML capabilities and encourage sharing of best practices by the humanitarian community. 
    more » « less
  5. ; ; ; ; (, Advanced Physics Research)
    Abstract Among promising applications of metal‐halide perovskite, the most research progress is made for perovskite solar cells (PSCs). Data from myriads of research work enables leveraging machine learning (ML) to significantly expedite material and device optimization as well as potentially design novel configurations. This paper represents one of the first efforts in providing open‐source ML tools developed utilizing the Perovskite Database Project (PDP), the most comprehensive open‐source PSC database to date with over 43 000 entries from published literature. Three ML model architectures with short‐circuit current density (Jsc) as a target are trained exploiting the PDP. Using the XGBoost architecture, a root mean squared error (RMSE) of 3.58 , R2of 0.35 and a mean absolute percentage error (MAPE) of 9.49% are achieved. This performance is comparable to results reported in literature, and through further investigation can likely be improved. To overcome challenges with manual database creation, an open‐source data cleaning pipeline is created for PDP data. Through the creation of these tools, which have been published on GitHub, this research aims to make ML available to aid the design for PSC while showing the already promising performance achieved. The tools can be adapted for other applications, such as perovskite light‐emitting diodes (PeLEDs), if a sufficient database is available. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email