Efficient Asynchronous Federated Learning Research in the Internet of Vehicles

Yang, Zhigang; Zhang, Xuhua; Wang, Dapeng; Wang, Ruyan; Zhang, Puning; Wu, Yu

doi:10.1109/jiot.2022.3230412

Cited by 17 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These challenges are particularly relevant for predictive maintenance in transportation fleets, where the clients are individual vehicles. Due to individual travel patterns, the vehicles produce data at different sizes and may drop out due to connectivity problems (Yang et al 2022). In this paper, we propose a novel data disparity aware asynchronous federated model which enables predictive maintenance for engines in transportation fleets.…”

Section: Introductionmentioning

confidence: 99%

Data Disparity and Temporal Unavailability Aware Asynchronous Federated Learning for Predictive Maintenance on Transportation Fleets

Von Wahl,

Heidenreich,

Mitra

et al. 2024

AAAI

View full text Add to dashboard Cite

Predictive maintenance has emerged as a critical application in modern transportation, leveraging sensor data to forecast potential damages proactively using machine learning. However, privacy concerns limit data sharing, making Federated learning an appealing approach to preserve data privacy. Nevertheless, challenges arise due to disparities in data distribution and temporal unavailability caused by individual usage patterns in transportation. In this paper, we present a novel asynchronous federated learning approach to address system heterogeneity and facilitate machine learning for predictive maintenance on transportation fleets. The approach introduces a novel data disparity aware aggregation scheme and a federated early stopping method for training. To validate the effectiveness of our approach, we evaluate it on two independent real-world datasets from the transportation domain: 1) oil dilution prediction of car combustion engines and 2) remaining lifetime prediction of plane turbofan engines. Our experiments show that we reliably outperform five state-of-the-art baselines, including federated and classical machine learning models. Moreover, we show that our approach generalises to various prediction model architectures.

show abstract

Section: Introductionmentioning

confidence: 99%

Data Disparity and Temporal Unavailability Aware Asynchronous Federated Learning for Predictive Maintenance on Transportation Fleets

Von Wahl,

Heidenreich,

Mitra

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Lu et al [14] proposed a new FL-based architecture, comprising a hybrid blockchain architecture composed of permissioned blockchain and locally directed acyclic graph, and suggested an asynchronous FL scheme. Yang et al [15] proposed an efficient asynchronous FL algorithm and a dynamic hierarchical aggregation mechanism utilizing gradient sparsification and asynchronous aggregation techniques. In the study of IoV applications, Zhao et al [16] designed an FL collaborative authentication protocol to prevent private data leakage and reduce data transmission delay for vehicle clients sharing data.…”

Section: Introductionmentioning

confidence: 99%

FLM-ICR: A Federated Learning Model for Classification of Internet of Vehicle Terminals Using Connection Records

Yang,

Du,

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

With the rapid development of Internet of Vehicles (IoV) technology, computing performance, and privacy protection have become increasingly crucial for IoV terminals (IoVT). To address privacy issues and poor computational performance in analyzing users' private data in IoV, this paper proposes a federated learning model for classification of IoVT Using connection records (FLM-ICR). In the horizontally federated learning client-server architecture, FLM-ICR uses an improved multi-layer perceptron and logistic regression network as the model backbone, employs the federated momentum gradient algorithm as the local model training optimizer, and utilizes the federated Gaussian differential privacy algorithm to protect the security of the computation process. The experiment used a confusion matrix to evaluate the model classification performance, explored the impact of the level of collaboration between clients on model performance, demonstrated the model's applicability in imbalanced data distribution, and verified the effectiveness of federated learning for model training. The accuracy, precision, recall, specificity, and F1 score of FLM-ICR are 0.795, 0.735, 0.835, 0.75, and 0.782, respectively, which is better than the existing research methods and weighs classification performance and privacy security, making it suitable for IoV Computation and analysis of private data.

show abstract

Blockchain and signcryption enabled asynchronous federated learning framework in fog computing

Zhou,

Tian,

Xiong

et al. 2024

Digital Communications and Networks

View full text Add to dashboard Cite

Efficient Asynchronous Federated Learning Research in the Internet of Vehicles

Cited by 17 publications

References 33 publications

Data Disparity and Temporal Unavailability Aware Asynchronous Federated Learning for Predictive Maintenance on Transportation Fleets

Data Disparity and Temporal Unavailability Aware Asynchronous Federated Learning for Predictive Maintenance on Transportation Fleets

FLM-ICR: A Federated Learning Model for Classification of Internet of Vehicle Terminals Using Connection Records

Blockchain and signcryption enabled asynchronous federated learning framework in fog computing

Contact Info

Product

Resources

About