Research Avenues for GNSS Interference Classification Robustness: Domain Adaptation, Continual Learning & Federated Learning

Heublein L, Ott F, Feigl T (2024)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 2024

Pages Range: 1-4

Conference Proceedings Title: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases

Event location: VILNIUS, LITHUANIA

Abstract

Jamming devices present a significant risk by disrupting sig- nals from the global navigation satellite system (GNSS), compromis- ing the reliability of accurate positioning. The detection of anomalies within frequency snapshots is crucial for effectively mitigating such interferences. The capacity to adapt to diverse, unforeseen interference characteristics is essential for ensuring the reliability of GNSS in practical applications. Our proposed GNSS dataset, recorded along a high- way, encompasses various research challenges, including adaptation to novel interference characteristics, change in environmental conditions, and variances in GNSS receiver stations. These obstacles prompt explo- ration into various research directions such as transfer learning, domain adaptation, continual learning, and few-shot learning. Furthermore, real- world applications require federated learning methods for orchestrating ML models in a privacy-preserving manner. This paper elaborates on the associated challenges and outlines potential research inquiries.

Authors with CRIS profile

Tobias Feigl Lehrstuhl für Informatik 2 (Programmiersysteme)

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Heublein, L., Ott, F., & Feigl, T. (2024). Research Avenues for GNSS Interference Classification Robustness: Domain Adaptation, Continual Learning & Federated Learning. In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (pp. 1-4). VILNIUS, LITHUANIA.

MLA:

Heublein, Lucas, Felix Ott, and Tobias Feigl. "Research Avenues for GNSS Interference Classification Robustness: Domain Adaptation, Continual Learning & Federated Learning." Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), VILNIUS, LITHUANIA 2024. 1-4.

BibTeX: Download