Cross-Vehicle Federated Learning for Unsupervised Scoring of Driver Behavior Under Privacy Constraint
- 7 November 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (7) , 7809-7827
Abstract
Scoring driver behavior is crucial for profiling drivers to improve driving habits with beneficial feedback, significantly reducing the risks of accidents, fuel consumption, and traffic emissions. Although connected vehicles enable extensive collection of driving data for accurate scoring models, two key challenges persist: the absence of target scores for traditional regression algorithms and privacy concerns that hinder centralized learning to build unsupervised scoring models. We introduce FedDriveScore, a privacy-preserving unsupervised scoring framework tailored for the Internet of Vehicles context. This solution leverages a mixed distribution approach to form an objective scoring model that utilizes probability distributions and statistical weights to assess driver behavior. Homomorphic encryption-based federated learning is employed to collaboratively implement the scoring model across multiple vehicles without sharing raw data. To mitigate the detrimental effects of skewed metric distributions, an enhanced federated learning method is developed to ensure utility consistency between models generated through federated learning and centralized learning. Experimental results from two real-world datasets show that the proposed solution achieves remarkable performance, with scoring utility losses of less than 0.0001 (mean squared error) and 0.01 (mean absolute error), representing approximately a 99% improvement over traditional federated learning benchmark. Our solution demonstrates high alignment with centralized learning outcomes while effectively profiling drivers in an objective and equitable manner.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFB2501200)
- National Natural Science Foundation of China (52372426)
- European Union Horizon Europe Program (101103695)
- Fundamental Research Funds for the Central Universities, CHD (300102243711)
This publication has 33 references indexed in Scilit:
- Privacy enabled driver behavior analysis in heterogeneous IoV using federated learningEngineering Applications of Artificial Intelligence, 2023
- Federated clustering for recognizing driving styles from private trajectoriesEngineering Applications of Artificial Intelligence, 2022
- Light-weight federated learning-based anomaly detection for time-series data in industrial control systemsComputers in Industry, 2022
- Profiling drivers to assess safe and eco-driving behavior – A systematic review of naturalistic driving studiesAccident Analysis & Prevention, 2021
- A bi-level distribution mixture framework for unsupervised driving performance evaluation from naturalistic truck driving dataEngineering Applications of Artificial Intelligence, 2021
- Classifying travelers' driving style using basic safety messages generated by connected vehicles: Application of unsupervised machine learningTransportation Research Part C: Emerging Technologies, 2021
- Driver behaviour profiles for road safety analysisAccident Analysis & Prevention, 2015
- Inter-company comparison using modified TOPSIS with objective weightsComputers & Operations Research, 2000
- Public-Key Cryptosystems Based on Composite Degree Residuosity Classes1999
- Determining objective weights in multiple criteria problems: The critic methodComputers & Operations Research, 1995