Detail publikace

An Android Federated Learning Framework for Emergency Management Applications

MICHÁLEK, J. OUJEZSKÝ, V. ŠKORPIL, V.

Originální název

An Android Federated Learning Framework for Emergency Management Applications

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

In this paper, we present an Android federated learning framework designed specifically for emergency management applications. Our focus is on addressing the challenges related to communication in such scenarios. To overcome the limitations of centralized server architectures, we propose a novel communication protocol that enables the framework to efficiently collaborate with multiple centralized servers. This protocol facilitates effective knowledge sharing and model training while ensuring data privacy and security. By leveraging this protocol, our framework enhances the performance and robustness of critical infrastructure systems on the Android platform, enabling real-time operational scenarios. Through this research, we contribute to the advancement of emergency management applications by providing a comprehensive solution that optimizes communication and enables seamless collaboration with multiple centralized servers.

Klíčová slova

Android; communication protocol; federated learning; framework; machine learning

Autoři

MICHÁLEK, J.; OUJEZSKÝ, V.; ŠKORPIL, V.

Vydáno

30. 10. 2023

Nakladatel

IEEE

ISBN

979-8-3503-9328-6

Kniha

2023 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

ISSN

2157-023X

Periodikum

International Congress on Ultra Modern Telecommunications and Control Systems and Workshops

Stát

neuvedeno

Strany od

97

Strany do

101

Strany počet

5

URL

BibTex

@inproceedings{BUT185682,
  author="Jakub {Michálek} and Václav {Oujezský} and Vladislav {Škorpil}",
  title="An Android Federated Learning Framework for Emergency Management Applications",
  booktitle="2023 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)",
  year="2023",
  journal="International Congress on Ultra Modern Telecommunications and Control Systems and Workshops",
  pages="97--101",
  publisher="IEEE",
  doi="10.1109/ICUMT61075.2023.10333300",
  isbn="979-8-3503-9328-6",
  issn="2157-023X",
  url="https://ieeexplore.ieee.org/document/10333300"
}