.png){kind=icon}
.png){kind=icon}
Return
Time-Shifted Transformers for Driver Identification Using Vehicle Data
.png){kind=icon}
OA
AI
DOI：10.1109/TITS.2023.3326652.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A modern vehicle contains a large number of electronic control units and sensors that are connected to cloud environments. These electronic units generate a huge amount of data that can be leveraged to identify the current driver and adapt to their behavior. For example, driver identification can improve the accuracy of range estimation in battery electric vehicles. This study focuses on identifying drivers based on their behaviour by using multivariate time series data acquired by the sensors available in the vehicle. We propose two different classifiers: one based on Bi-directional stacked Long Short-Term Memory with Attention mechanism (BiLSTM-A) and another based on a Modified Time Series Transformer (MTST). We perform driver identification in two different ways: 1) by applying a classifier on a single time segment; and 2) by using our proposed time-shift ensembles to combine predictions made from multiple time segments. We experimentally evaluate the proposed techniques on a publicly available dataset that comprises 10 drivers. By using all appropriate features, the proposed BiLSTM-A and MTST classifiers identify the driver with an accuracy of 55% and 73%, respectively, from a single time segment of 60 seconds duration. Time-shift ensembles increase the accuracy substantially, to 92% for BiLSTM-A and 97% for MTST when a 460-second time period is used for each prediction. We conclude that the proposed MTST classifier outperforms BiLSTM-A and existing classifiers in the driver identification task, and time-shift ensembles substantially improve the accuracy.
Keywords:
Index Terms- Driver identification
time shift ensembles
transformers
OBD port
multivariate time series
Journal
IF:
8.4
Papers:
9.5K
Citations:
6.3W