Details
| Original language | English |
|---|---|
| Article number | 100013 |
| Journal | ISPRS Open Journal of Photogrammetry and Remote Sensing |
| Volume | 4 |
| Early online date | 9 Mar 2022 |
| Publication status | Published - Apr 2022 |
Abstract
Nowadays mobile positioning devices, such as global navigation satellite systems (GNSS) but also external sensor technology like cameras allow an efficient online collection of trajectories, which reflect the behavior of moving objects, such as cars. The data can be used for various applications, e.g., traffic planning or updating maps, which need many trajectories to extract and infer the desired information, especially when machine or deep learning approaches are used. Often, the amount and diversity of necessary data exceeds what can be collected by individuals or even single companies. Currently, data owners, e.g., vehicle producers or service operators, are reluctant to share data due to data privacy rules or because of the risk of sharing information with competitors, which could jeopardize the data owner's competitive advantage. A promising approach to exploit data from several data owners, but still not directly accessing the data, is the concept of federated learning, that allows collaborative learning without exchanging raw data, but only model parameters. In this paper, we address the problem of anomaly detection in vehicle trajectories, and investigate the benefits of using federated learning. To this end, we apply several state-of-the-art learning algorithms like one-class support vector machine (OCSVM) and isolation forest, thus solving a one-class classification problem. Based on these learning mechanisms, we successfully proposed and verified a federated architecture for the collaborative identification of anomalous trajectories at several intersections. We demonstrate that the federated approach is beneficial not only to improve the overall anomaly detection accuracy, but also for each individual data owner. The experiments show that federated learning allows to increase the anomaly detection accuracy from in average AUC-ROC scores of 97% by individual intersections up to 99% using cooperation.
Keywords
- Anomaly detection, Federated learning, Machine learning, Vehicle trajectories
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
- Social Sciences(all)
- Geography, Planning and Development
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
- Physics and Astronomy(all)
- Atomic and Molecular Physics, and Optics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Open Journal of Photogrammetry and Remote Sensing, Vol. 4, 100013, 04.2022.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Detection of anomalous vehicle trajectories using federated learning
AU - Koetsier, Christian
AU - Fiosina, Jelena
AU - Gremmel, Jan N.
AU - Müller, Jörg P.
AU - Woisetschläger, David M.
AU - Sester, Monika
N1 - Funding Information: The research was funded by the Lower Saxony Ministry of Science and Culture under grant number ZN3493 within the Lower Saxony “Vorab” of the Volkswagen Foundation and supported by the Center for Digital Innovations.
PY - 2022/4
Y1 - 2022/4
N2 - Nowadays mobile positioning devices, such as global navigation satellite systems (GNSS) but also external sensor technology like cameras allow an efficient online collection of trajectories, which reflect the behavior of moving objects, such as cars. The data can be used for various applications, e.g., traffic planning or updating maps, which need many trajectories to extract and infer the desired information, especially when machine or deep learning approaches are used. Often, the amount and diversity of necessary data exceeds what can be collected by individuals or even single companies. Currently, data owners, e.g., vehicle producers or service operators, are reluctant to share data due to data privacy rules or because of the risk of sharing information with competitors, which could jeopardize the data owner's competitive advantage. A promising approach to exploit data from several data owners, but still not directly accessing the data, is the concept of federated learning, that allows collaborative learning without exchanging raw data, but only model parameters. In this paper, we address the problem of anomaly detection in vehicle trajectories, and investigate the benefits of using federated learning. To this end, we apply several state-of-the-art learning algorithms like one-class support vector machine (OCSVM) and isolation forest, thus solving a one-class classification problem. Based on these learning mechanisms, we successfully proposed and verified a federated architecture for the collaborative identification of anomalous trajectories at several intersections. We demonstrate that the federated approach is beneficial not only to improve the overall anomaly detection accuracy, but also for each individual data owner. The experiments show that federated learning allows to increase the anomaly detection accuracy from in average AUC-ROC scores of 97% by individual intersections up to 99% using cooperation.
AB - Nowadays mobile positioning devices, such as global navigation satellite systems (GNSS) but also external sensor technology like cameras allow an efficient online collection of trajectories, which reflect the behavior of moving objects, such as cars. The data can be used for various applications, e.g., traffic planning or updating maps, which need many trajectories to extract and infer the desired information, especially when machine or deep learning approaches are used. Often, the amount and diversity of necessary data exceeds what can be collected by individuals or even single companies. Currently, data owners, e.g., vehicle producers or service operators, are reluctant to share data due to data privacy rules or because of the risk of sharing information with competitors, which could jeopardize the data owner's competitive advantage. A promising approach to exploit data from several data owners, but still not directly accessing the data, is the concept of federated learning, that allows collaborative learning without exchanging raw data, but only model parameters. In this paper, we address the problem of anomaly detection in vehicle trajectories, and investigate the benefits of using federated learning. To this end, we apply several state-of-the-art learning algorithms like one-class support vector machine (OCSVM) and isolation forest, thus solving a one-class classification problem. Based on these learning mechanisms, we successfully proposed and verified a federated architecture for the collaborative identification of anomalous trajectories at several intersections. We demonstrate that the federated approach is beneficial not only to improve the overall anomaly detection accuracy, but also for each individual data owner. The experiments show that federated learning allows to increase the anomaly detection accuracy from in average AUC-ROC scores of 97% by individual intersections up to 99% using cooperation.
KW - Anomaly detection
KW - Federated learning
KW - Machine learning
KW - Vehicle trajectories
UR - http://www.scopus.com/inward/record.url?scp=85143781173&partnerID=8YFLogxK
U2 - 10.1016/j.ophoto.2022.100013
DO - 10.1016/j.ophoto.2022.100013
M3 - Article
AN - SCOPUS:85143781173
VL - 4
JO - ISPRS Open Journal of Photogrammetry and Remote Sensing
JF - ISPRS Open Journal of Photogrammetry and Remote Sensing
SN - 2667-3932
M1 - 100013
ER -