Learning driving style embedding from GPS-derived moving patterns for driver identification
Author:
Preprint
Abstract
Learning fingerprint-like driving style representations is crucial to accurately identify who is behind the wheel in open driving situations. This study explores the learning of driving styles with GPS signals that are currently available in connected vehicles for short-term driver identification. First, an input driving trajectory is windowed into subtrajectories with fixed time lengths. Then, each subtrajectory is further divided into overlapping dynamic segments. For each segment, the local features are obtained by combining statistical and state transitional patterns. Finally, the driving style embedded in each subtrajectory is learned with the proposed regularized recurrent neural network (RNN) for short-term driver identification. We evaluate the impacts of key factors and the effectiveness of the proposed approach on the identification performance of 5 and 10 drivers. The results show that our proposed neural network structure, which complements movement statistics (MS) with state transitions (ST), provides better prediction performance than existing deep learning methods.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Few-shot driver identification via meta-learningExpert Systems with Applications, 2022
- Analysis of risky driving behaviors among bus drivers in China: The role of enterprise management, external environment and attitudes towards traffic safetyAccident Analysis & Prevention, 2022
- DriverRep: Driver identification through driving behavior embeddingsJournal of Parallel and Distributed Computing, 2022
- Driver identification using 1D convolutional neural networks with vehicular CAN signalsIET Intelligent Transport Systems, 2020
- Driving maneuver early detection via sequence learning from vehicle signals and video imagesPattern Recognition, 2020
- Multivariate LSTM-FCNs for time series classificationNeural Networks, 2019
- A graphical modeling method for individual driving behavior and its application in driving safety analysis using GPS dataTransportation Research Part F: Traffic Psychology and Behaviour, 2019
- Driver identification in intelligent vehicle systems using machine learning algorithmsIET Intelligent Transport Systems, 2018
- Survey of smartphone‐based sensing in vehicles for intelligent transportation system applicationsIET Intelligent Transport Systems, 2015
- Profiling drivers based on driver dependent vehicle driving featuresApplied Intelligence, 2015