Introducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning

This paper proposes a simple yet unexplored measurement and federated learning system architecture for connected vehicles. The novelty of the introduced system is to combine the real-time data-sharing of crowdsensing with federated learning of global traffic models, providing up-to-date information...

Full description

Saved in:
Bibliographic Details
Main Authors: Levente Alekszejenko, Peter Antal, Tadeusz Dobrowiecki
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Intelligent Transportation Systems
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11082276/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849336047816671232
author Levente Alekszejenko
Peter Antal
Tadeusz Dobrowiecki
author_facet Levente Alekszejenko
Peter Antal
Tadeusz Dobrowiecki
author_sort Levente Alekszejenko
collection DOAJ
description This paper proposes a simple yet unexplored measurement and federated learning system architecture for connected vehicles. The novelty of the introduced system is to combine the real-time data-sharing of crowdsensing with federated learning of global traffic models, providing up-to-date information for decision-making, facilitating faster learning, improving communicational channel usage, and possibly enhancing data privacy. This multi-level cooperative federated learning system generally supports operational, tactical, and strategic planning; therefore, we demonstrate its merits with a case study of parking monitoring in a simulated town as well as average speed prediction in a simulated part of Hannover, Germany. However, real-time data-sharing is essential for decision-making; it might also contain privacy-sensitive information regarding the trajectory of the vehicles. To mitigate the risk of privacy leakage, we experimented with different data selection methods for data exchange, introducing an optimization method inspired by Zeuthen’s negotiation strategy. We also checked the privacy impact of real-time data-sharing on federated learning. Our results indicate only negligible differences in privacy leakage between the proposed data selection methods. On the other hand, real-time data-sharing improves the reaction time of the federated learning system. The Zeuthen-inspired optimization method can efficiently supply valuable information for the communication partners. Moreover, it can enhance privacy protection in federated learning in some cases.
format Article
id doaj-art-5d028bb76fbe48f38d39af22d46cf076
institution Kabale University
issn 2687-7813
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Intelligent Transportation Systems
spelling doaj-art-5d028bb76fbe48f38d39af22d46cf0762025-08-20T03:45:06ZengIEEEIEEE Open Journal of Intelligent Transportation Systems2687-78132025-01-0161009102610.1109/OJITS.2025.358961211082276Introducing Intelligent Data Sharing to Vehicular Cooperative Federated LearningLevente Alekszejenko0https://orcid.org/0000-0002-3196-1950Peter Antal1https://orcid.org/0000-0002-4370-2198Tadeusz Dobrowiecki2https://orcid.org/0000-0002-8307-5096Department of Artificial Intelligence and Systems Engineering, Budapest University of Technology and Economics, Budapest, HungaryDepartment of Artificial Intelligence and Systems Engineering, Budapest University of Technology and Economics, Budapest, HungaryDepartment of Artificial Intelligence and Systems Engineering, Budapest University of Technology and Economics, Budapest, HungaryThis paper proposes a simple yet unexplored measurement and federated learning system architecture for connected vehicles. The novelty of the introduced system is to combine the real-time data-sharing of crowdsensing with federated learning of global traffic models, providing up-to-date information for decision-making, facilitating faster learning, improving communicational channel usage, and possibly enhancing data privacy. This multi-level cooperative federated learning system generally supports operational, tactical, and strategic planning; therefore, we demonstrate its merits with a case study of parking monitoring in a simulated town as well as average speed prediction in a simulated part of Hannover, Germany. However, real-time data-sharing is essential for decision-making; it might also contain privacy-sensitive information regarding the trajectory of the vehicles. To mitigate the risk of privacy leakage, we experimented with different data selection methods for data exchange, introducing an optimization method inspired by Zeuthen’s negotiation strategy. We also checked the privacy impact of real-time data-sharing on federated learning. Our results indicate only negligible differences in privacy leakage between the proposed data selection methods. On the other hand, real-time data-sharing improves the reaction time of the federated learning system. The Zeuthen-inspired optimization method can efficiently supply valuable information for the communication partners. Moreover, it can enhance privacy protection in federated learning in some cases.https://ieeexplore.ieee.org/document/11082276/Cooperative systemscrowdsensingfederated learningvehicle-to-everything
spellingShingle Levente Alekszejenko
Peter Antal
Tadeusz Dobrowiecki
Introducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning
IEEE Open Journal of Intelligent Transportation Systems
Cooperative systems
crowdsensing
federated learning
vehicle-to-everything
title Introducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning
title_full Introducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning
title_fullStr Introducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning
title_full_unstemmed Introducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning
title_short Introducing Intelligent Data Sharing to Vehicular Cooperative Federated Learning
title_sort introducing intelligent data sharing to vehicular cooperative federated learning
topic Cooperative systems
crowdsensing
federated learning
vehicle-to-everything
url https://ieeexplore.ieee.org/document/11082276/
work_keys_str_mv AT leventealekszejenko introducingintelligentdatasharingtovehicularcooperativefederatedlearning
AT peterantal introducingintelligentdatasharingtovehicularcooperativefederatedlearning
AT tadeuszdobrowiecki introducingintelligentdatasharingtovehicularcooperativefederatedlearning