Resumen
Intelligent Transportation Systems (ITS) have progressively incorporated ma-
chine learning (ML) to optimize traffic efficiency, enhance safety, and improve real-time
decision-making. However, the traditional centralized ML paradigm faces critical lim-
itations regarding data privacy, scalability, and single-point vulnerabilities. This study
explores federated learning (FL) as a decentralized alternative that preserves privacy by
training local models without transferring raw data. Based on a systematic literature review
encompassing 39 ITS-related studies, this work classifies applications according to their
architectural detail—distinguishing systems from models—and identifies three families
of FL frameworks: privacy-focused, integrable, and advanced-infrastructure. Three repre-
sentative frameworks—FedGRU, DT+HFL, and TFL-CNN—were comparatively analyzed
against a client–server baseline to assess their suitability for ITS adaptation. The find-
ings reveal that DT+HFL and TFL-CNN, characterized by hierarchical aggregation and
intermediate edge components such as cloudlets or roadside units (RSUs), offer superior
scalability and adaptability across vehicular and traffic domains. FedGRU, while conceptu-
ally relevant as a meta-framework for coordinating multiple organizational models, is more
suitable as a complementary reference than as a standalone architecture for large-scale ITS
deployment. Through application-level evaluations—including traffic prediction, accident
detection, transport-mode identification, and driver profiling—this study demonstrates
that FL can be effectively integrated into ITS with moderate architectural adjustments.
Overall, the results establish a solid methodological foundation for migrating centralized
ITS architectures toward federated, privacy-preserving intelligence, in alignment with the
evolution of edge and 6G infrastructures.
chine learning (ML) to optimize traffic efficiency, enhance safety, and improve real-time
decision-making. However, the traditional centralized ML paradigm faces critical lim-
itations regarding data privacy, scalability, and single-point vulnerabilities. This study
explores federated learning (FL) as a decentralized alternative that preserves privacy by
training local models without transferring raw data. Based on a systematic literature review
encompassing 39 ITS-related studies, this work classifies applications according to their
architectural detail—distinguishing systems from models—and identifies three families
of FL frameworks: privacy-focused, integrable, and advanced-infrastructure. Three repre-
sentative frameworks—FedGRU, DT+HFL, and TFL-CNN—were comparatively analyzed
against a client–server baseline to assess their suitability for ITS adaptation. The find-
ings reveal that DT+HFL and TFL-CNN, characterized by hierarchical aggregation and
intermediate edge components such as cloudlets or roadside units (RSUs), offer superior
scalability and adaptability across vehicular and traffic domains. FedGRU, while conceptu-
ally relevant as a meta-framework for coordinating multiple organizational models, is more
suitable as a complementary reference than as a standalone architecture for large-scale ITS
deployment. Through application-level evaluations—including traffic prediction, accident
detection, transport-mode identification, and driver profiling—this study demonstrates
that FL can be effectively integrated into ITS with moderate architectural adjustments.
Overall, the results establish a solid methodological foundation for migrating centralized
ITS architectures toward federated, privacy-preserving intelligence, in alignment with the
evolution of edge and 6G infrastructures.
| Idioma original | Inglés |
|---|---|
| Publicación | Smart Cities |
| Estado | Presentada - 4 nov. 2025 |
ODS de las Naciones Unidas
Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible
