Towards building reliable deep learning based driver identification systems

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Volkswagen AG
View graph of relations

Details

Original languageEnglish
Title of host publication2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022
EditorsMarek Reformat, Du Zhang, Nikolaos G. Bourbakis
Pages766-773
Number of pages8
ISBN (electronic)9798350397444
Publication statusPublished - 2022
Event34th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2022 - Virtual, Online, China
Duration: 31 Oct 20222 Nov 2022

Publication series

NameProceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volume2022-October
ISSN (Print)1082-3409

Abstract

Recent studies have shown the potential of leveraging neural networks to achieve high levels of accuracy in re-identifying drivers by learning latent features from vehicular sensor data. However, deploying such networks in real-world applications (like theft detection or fleet management) requires re-training the networks with new data to transfer the learnings from the initial dataset to the target drivers. In this paper, we highlight the importance of the evaluation of such networks in both phases, initial training and transfer learning. Our evaluation shows that the performance of existing solutions drops significantly, when applied to new drivers that have not been seen by the networks in the initial training phase. Moreover, we propose a deep neural network that outperforms state-of-the-art solutions in both phases. For the evaluation of the transfer learning phase, we use a dataset from a real-world ride-sharing service that has not been used in the initial training.

Keywords

    driver identification, neural networks, transfer learning

ASJC Scopus subject areas

Cite this

Towards building reliable deep learning based driver identification systems. / Zeng, Li; Al-Rifai, Mohammad; Nolting, Michael et al.
2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022. ed. / Marek Reformat; Du Zhang; Nikolaos G. Bourbakis. 2022. p. 766-773 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI; Vol. 2022-October).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Zeng, L, Al-Rifai, M, Nolting, M & Nejdl, W 2022, Towards building reliable deep learning based driver identification systems. in M Reformat, D Zhang & NG Bourbakis (eds), 2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022. Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, vol. 2022-October, pp. 766-773, 34th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2022, Virtual, Online, China, 31 Oct 2022. https://doi.org/10.1109/ICTAI56018.2022.00118
Zeng, L., Al-Rifai, M., Nolting, M., & Nejdl, W. (2022). Towards building reliable deep learning based driver identification systems. In M. Reformat, D. Zhang, & N. G. Bourbakis (Eds.), 2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022 (pp. 766-773). (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI; Vol. 2022-October). https://doi.org/10.1109/ICTAI56018.2022.00118
Zeng L, Al-Rifai M, Nolting M, Nejdl W. Towards building reliable deep learning based driver identification systems. In Reformat M, Zhang D, Bourbakis NG, editors, 2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022. 2022. p. 766-773. (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI). doi: 10.1109/ICTAI56018.2022.00118
Zeng, Li ; Al-Rifai, Mohammad ; Nolting, Michael et al. / Towards building reliable deep learning based driver identification systems. 2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022. editor / Marek Reformat ; Du Zhang ; Nikolaos G. Bourbakis. 2022. pp. 766-773 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI).
Download
@inproceedings{160f8baedbe64465a82dfa542b282734,
title = "Towards building reliable deep learning based driver identification systems",
abstract = "Recent studies have shown the potential of leveraging neural networks to achieve high levels of accuracy in re-identifying drivers by learning latent features from vehicular sensor data. However, deploying such networks in real-world applications (like theft detection or fleet management) requires re-training the networks with new data to transfer the learnings from the initial dataset to the target drivers. In this paper, we highlight the importance of the evaluation of such networks in both phases, initial training and transfer learning. Our evaluation shows that the performance of existing solutions drops significantly, when applied to new drivers that have not been seen by the networks in the initial training phase. Moreover, we propose a deep neural network that outperforms state-of-the-art solutions in both phases. For the evaluation of the transfer learning phase, we use a dataset from a real-world ride-sharing service that has not been used in the initial training.",
keywords = "driver identification, neural networks, transfer learning",
author = "Li Zeng and Mohammad Al-Rifai and Michael Nolting and Wolfgang Nejdl",
note = "Funding Information: The first author has received funding from Volkswagen AG to conduct this research.; 34th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2022 ; Conference date: 31-10-2022 Through 02-11-2022",
year = "2022",
doi = "10.1109/ICTAI56018.2022.00118",
language = "English",
isbn = "979-8-3503-9745-1",
series = "Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI",
pages = "766--773",
editor = "Marek Reformat and Du Zhang and Bourbakis, {Nikolaos G.}",
booktitle = "2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022",

}

Download

TY - GEN

T1 - Towards building reliable deep learning based driver identification systems

AU - Zeng, Li

AU - Al-Rifai, Mohammad

AU - Nolting, Michael

AU - Nejdl, Wolfgang

N1 - Funding Information: The first author has received funding from Volkswagen AG to conduct this research.

PY - 2022

Y1 - 2022

N2 - Recent studies have shown the potential of leveraging neural networks to achieve high levels of accuracy in re-identifying drivers by learning latent features from vehicular sensor data. However, deploying such networks in real-world applications (like theft detection or fleet management) requires re-training the networks with new data to transfer the learnings from the initial dataset to the target drivers. In this paper, we highlight the importance of the evaluation of such networks in both phases, initial training and transfer learning. Our evaluation shows that the performance of existing solutions drops significantly, when applied to new drivers that have not been seen by the networks in the initial training phase. Moreover, we propose a deep neural network that outperforms state-of-the-art solutions in both phases. For the evaluation of the transfer learning phase, we use a dataset from a real-world ride-sharing service that has not been used in the initial training.

AB - Recent studies have shown the potential of leveraging neural networks to achieve high levels of accuracy in re-identifying drivers by learning latent features from vehicular sensor data. However, deploying such networks in real-world applications (like theft detection or fleet management) requires re-training the networks with new data to transfer the learnings from the initial dataset to the target drivers. In this paper, we highlight the importance of the evaluation of such networks in both phases, initial training and transfer learning. Our evaluation shows that the performance of existing solutions drops significantly, when applied to new drivers that have not been seen by the networks in the initial training phase. Moreover, we propose a deep neural network that outperforms state-of-the-art solutions in both phases. For the evaluation of the transfer learning phase, we use a dataset from a real-world ride-sharing service that has not been used in the initial training.

KW - driver identification

KW - neural networks

KW - transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85156114525&partnerID=8YFLogxK

U2 - 10.1109/ICTAI56018.2022.00118

DO - 10.1109/ICTAI56018.2022.00118

M3 - Conference contribution

AN - SCOPUS:85156114525

SN - 979-8-3503-9745-1

T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

SP - 766

EP - 773

BT - 2022 IEEE 34th International Conference on Tools with Artificial Intelligence, ICTAI 2022

A2 - Reformat, Marek

A2 - Zhang, Du

A2 - Bourbakis, Nikolaos G.

T2 - 34th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2022

Y2 - 31 October 2022 through 2 November 2022

ER -

By the same author(s)