Driver Identification using Multivariate In-vehicle Time Series Data

Paper #:
  • 2018-01-1198

Published:
  • 2018-04-03
Author(s):
Affiliated:
Abstract:
All drivers come with a driving signature during a driving. By aggregating adequate driving data of a driver via multiple driving sessions, which is already embedded with driving behaviors of a driver, driver identification task could be treated as a supervised machine-learning classification problem. In this paper, we use a random forest classifier to implement the classification task. Therefore, we collected many time series signals from 60 driving sessions (4 sessions per driver and 15 drivers totally) via the Controller Area Network. In order to reduce the redundancy of information, we proposed a method for signal pre-selection. Besides, we proposed a strategy for parameters tuning, which includes signal refinement, interval feature extraction and selection, and optimal segmentation of a signal. We also explored the performance of different types of arrangement of features and samples. By following the proposed tuning strategy, the prediction performance of the random forest classifier achieved an accuracy of 89.14% in terms of an identification task of four drivers, and 60.36% of fifteen drivers.
Access
Now
SAE MOBILUS Subscriber? You may already have access.
Buy
Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Select
Price
List
Download
$22.00
Mail
$22.00
Members save up to 36% off list price.
Share
HTML for Linking to Page
Page URL

Related Items

Event
2018-04-10
Article
2017-07-26
Training / Education
2005-11-15
Technical Paper / Journal Article
2011-05-17