EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Comparative Deep Learning Framework for Multivariate Time Series Anomaly Detection in Satellite Telemetry

Ali Cengiz Rustemli, Gökhan Şahin, Erdal Akin, Kayode Sakariyah Adewole, Sabir Rustemli

Applied Sciences · 05.06.2026 · 16 (11) · 5694

DOI: 10.3390/app16115694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 05.06.2026. Verfasst von Ali Cengiz Rustemli und 4 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study compares deep learning models for point-level anomaly detection in multichannel satellite telemetry data. Raw event-based telemetry was converted into segment-based multivariate time series without windowing or feature extraction, allowing models to learn system behavior at each time step. Preprocessing included channel alignment, training set-based normalization, missing value imputation, and temporal label smoothing, while Focal Loss and segment-level oversampling addressed class imbalance. Five architectures, BiLSTM, BiGRU, Transformer, Hybrid BiLSTM–Transformer, and Hybrid BiGRU–Transformer, were evaluated, with thresholds optimized on a validation set. The results show that hybrid models combining recurrent networks and attention mechanisms effectively capture both short- and long-term dependencies. The standalone BiGRU model achieves the highest overall classification performance in terms of F1 score and accuracy. In contrast, the Hybrid BiGRU–Transformer architecture does not outperform BiGRU in classification metrics but provides superior temporal stability, improved boundary sensitivity, and better interpretability in anomaly detection tasks.

Zitieren

APA

Rustemli, A. C., Şahin, G., Akin, E., Adewole, K. S., & Rustemli, S. (2026). A Comparative Deep Learning Framework for Multivariate Time Series Anomaly Detection in Satellite Telemetry. Applied Sciences, 16(11), 5694. https://doi.org/10.3390/app16115694

Vancouver

Rustemli AC, Şahin G, Akin E, Adewole KS, Rustemli S. A Comparative Deep Learning Framework for Multivariate Time Series Anomaly Detection in Satellite Telemetry. Applied Sciences. 2026;16(11):5694. doi:10.3390/app16115694

BibTeX
@article{Rustemli2026,
  author = {Rustemli, Ali Cengiz and Şahin, Gökhan and Akin, Erdal and Adewole, Kayode Sakariyah and Rustemli, Sabir},
  title = {A Comparative Deep Learning Framework for Multivariate Time Series Anomaly Detection in Satellite Telemetry},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {11},
  pages = {5694},
  doi = {10.3390/app16115694}
}
Kostenlos starten →