Vae-Based Feature Disentanglement for Data Augmentation and Compression in Generalized Gnss Interference Classification

Heublein L, Kocher S, Feigl T, Ruxsgamer A, Mutschler C, Ott F (2025)

Publication Type: Conference contribution

Publication year: 2025

Conference Proceedings Title: 2025 International Conference on Localization and GNSS (ICL-GNSS)

Event location: Rome IT

Journal Issue: 2025

DOI: 10.1109/ICL-GNSS65520.2025.11046129

Abstract

Distributed learning and Edge AI necessitate efficient data processing, low-latency communication, decentralized model training, and stringent data privacy to facilitate realtime intelligence on edge devices while reducing dependency on centralized infrastructure and ensuring high model performance. In the context of global navigation satellite system (GNSS) applications, the primary objective is to accurately monitor and classify interferences that degrade system performance in distributed environments, thereby enhancing situational awareness. To achieve this, machine learning (ML) models can be deployed on low-resource devices, ensuring minimal communication latency and preserving data privacy. The key challenge is to compress ML models while maintaining high classification accuracy. In this paper, we propose variational autoencoders (VAEs) for disentanglement to extract essential latent features that enable accurate classification of interferences. We demonstrate that the disentanglement approach can be leveraged for both data compression and data augmentation by interpolating the lower-dimensional latent representations of signal power. To validate our approach, we evaluate three VAE variants - vanilla, factorized, and conditional generative - on four distinct datasets, including two collected in controlled indoor environments and two real-world highway datasets. Additionally, we conduct extensive hyperparameter searches to optimize performance. Our proposed VAE achieves a data compression rate ranging from 512 to 8,192 and achieves an accuracy up to 99.92 %.

Authors with CRIS profile

Tobias Feigl
Christopher Mutschler

Involved external institutions

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

How to cite

APA:

Heublein, L., Kocher, S., Feigl, T., Ruxsgamer, A., Mutschler, C., & Ott, F. (2025). Vae-Based Feature Disentanglement for Data Augmentation and Compression in Generalized Gnss Interference Classification. In 2025 International Conference on Localization and GNSS (ICL-GNSS). Rome, IT.

MLA:

Heublein, Lucas, et al. "Vae-Based Feature Disentanglement for Data Augmentation and Compression in Generalized Gnss Interference Classification." Proceedings of the International Conference on Localization and GNSS (ICL-GNSS), Rome 2025.

BibTeX: Download