Details
| Original language | English |
|---|---|
| Title of host publication | 2021 IEEE International Intelligent Transportation Systems Conference, ITSC 2021 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1328-1333 |
| Number of pages | 6 |
| ISBN (electronic) | 9781728191423 |
| ISBN (print) | 978-1-7281-9143-0 |
| Publication status | Published - 19 Sept 2021 |
| Event | 2021 IEEE International Intelligent Transportation Systems Conference, ITSC 2021 - Indianapolis, United States Duration: 19 Sept 2021 → 22 Sept 2021 |
Publication series
| Name | IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC |
|---|---|
| Volume | 2021-September |
Abstract
Recent studies have shown that both the quantity and quality of the driving data are crucial for the success of deep learning based driver identification solutions. This is not only true for the training of deep neural networks, but also for their deployment. In the deployment phase the models are applied to identify new drivers that are different from the drivers in the training phase. New data is required to re-train the models and adjust them to fit the new drivers. While the focus of recent studies has been mostly on the training phase, this study focuses on the deployment phase. Inspired by face and fingerprint recognition solutions, in this paper we propose a solution that does not require model retraining in the deployment phase. Instead, only a small amount of example driving data from each driver is required. More specifically, we propose an approach that utilises the triplet loss function to learn a mapping from vehicular sensor data to an embedding space, where the distance between two embeddings represents the drivers' similarity. The resulting network can be directly used for identifying new drivers without re-training.
ASJC Scopus subject areas
- Engineering(all)
- Automotive Engineering
- Engineering(all)
- Mechanical Engineering
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2021 IEEE International Intelligent Transportation Systems Conference, ITSC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 1328-1333 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2021-September).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Triplet Loss for Effective Deployment of Deep Learning Based Driver Identification Models
AU - Zeng, Li
AU - Al-Rifai, Mohammad
AU - Nolting, Michael
AU - Nejd, Wolfgang
N1 - Funding Information: The authors affiliated with Volkswagen AG have received funding from Volkswagen AG to conduct this research.
PY - 2021/9/19
Y1 - 2021/9/19
N2 - Recent studies have shown that both the quantity and quality of the driving data are crucial for the success of deep learning based driver identification solutions. This is not only true for the training of deep neural networks, but also for their deployment. In the deployment phase the models are applied to identify new drivers that are different from the drivers in the training phase. New data is required to re-train the models and adjust them to fit the new drivers. While the focus of recent studies has been mostly on the training phase, this study focuses on the deployment phase. Inspired by face and fingerprint recognition solutions, in this paper we propose a solution that does not require model retraining in the deployment phase. Instead, only a small amount of example driving data from each driver is required. More specifically, we propose an approach that utilises the triplet loss function to learn a mapping from vehicular sensor data to an embedding space, where the distance between two embeddings represents the drivers' similarity. The resulting network can be directly used for identifying new drivers without re-training.
AB - Recent studies have shown that both the quantity and quality of the driving data are crucial for the success of deep learning based driver identification solutions. This is not only true for the training of deep neural networks, but also for their deployment. In the deployment phase the models are applied to identify new drivers that are different from the drivers in the training phase. New data is required to re-train the models and adjust them to fit the new drivers. While the focus of recent studies has been mostly on the training phase, this study focuses on the deployment phase. Inspired by face and fingerprint recognition solutions, in this paper we propose a solution that does not require model retraining in the deployment phase. Instead, only a small amount of example driving data from each driver is required. More specifically, we propose an approach that utilises the triplet loss function to learn a mapping from vehicular sensor data to an embedding space, where the distance between two embeddings represents the drivers' similarity. The resulting network can be directly used for identifying new drivers without re-training.
UR - http://www.scopus.com/inward/record.url?scp=85118455713&partnerID=8YFLogxK
U2 - 10.1109/ITSC48978.2021.9564513
DO - 10.1109/ITSC48978.2021.9564513
M3 - Conference contribution
AN - SCOPUS:85118455713
SN - 978-1-7281-9143-0
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 1328
EP - 1333
BT - 2021 IEEE International Intelligent Transportation Systems Conference, ITSC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Intelligent Transportation Systems Conference, ITSC 2021
Y2 - 19 September 2021 through 22 September 2021
ER -