Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application

TL;DR

This paper introduces FedTOP, a federated learning framework tailored for driver monitoring applications that effectively handles data heterogeneity, reduces communication costs, and enhances accuracy and privacy in IoV systems.

Contribution

The paper proposes FedTOP, a novel federated transfer-ordered-personalized learning framework that addresses heterogeneity and communication challenges in driver monitoring tasks.

Findings

Achieved up to 95.96% accuracy on real-world datasets.

Reduced communication resource consumption by 37.46%.

Demonstrated 462% improvement over baseline accuracy.

Abstract

Federated learning (FL) shines through in the internet of things (IoT) with its ability to realize collaborative learning and improve learning efficiency by sharing client model parameters trained on local data. Although FL has been successfully applied to various domains, including driver monitoring applications (DMAs) on the internet of vehicles (IoV), its usages still face some open issues, such as data and system heterogeneity, large-scale parallelism communication resources, malicious attacks, and data poisoning. This paper proposes a federated transfer-ordered-personalized learning (FedTOP) framework to address the above problems and test on two real-world datasets with and without system heterogeneity. The performance of the three extensions, transfer, ordered, and personalized, is compared by an ablation study and achieves 92.32% and 95.96% accuracy on the test clients of two datasets, respectively. Compared to the baseline, there is a 462% improvement in accuracy and a 37.46% reduction in communication resource consumption. The results demonstrate that the proposed FedTOP can be used as a highly accurate, streamlined, privacy-preserving, cybersecurity-oriented, and personalized framework for DMA.