EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Autoencoder-Based Self-Supervised Anomaly Detection in Wireless Sensor Networks: A Taxonomy-Driven Meta-Synthesis

Rana Muhammad Subhan, Young-Doo Lee, Insoo Koo

Applied Sciences · 31.01.2026 · 16 (3) · 1448

DOI: 10.3390/app16031448 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 31.01.2026. Verfasst von Rana Muhammad Subhan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 145 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: “Regional Innovation System & Education (RISE)” through the Ulsan RISE Center, Ministry of Education (MOE) and the Ulsan Metropolitan City, Republic of Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wireless Sensor Networks (WSNs) are widely deployed for long-term monitoring in environments characterized by nonstationary sensing dynamics, intermittent connectivity and continuously evolving network topologies, while reliable, fine-grained labeled data capturing faults and adversarial behaviors remain scarce. This survey systematically reviews and synthesizes recent research that integrates autoencoder-based representation learning with self-supervised learning (SSL) objectives to enhance anomaly detection under these practical constraints. We structure the existing literature through a unified taxonomy encompassing autoencoder variants, self-supervised pretext tasks, spatio-temporal encoding mechanisms and the increasing use of graph-structured autoencoders for topology-aware modeling. Across distinct methodological categories, SSL-augmented frameworks consistently demonstrate improved robustness and stability compared to purely reconstruction-driven baselines, particularly in heterogeneous, dynamic and temporally drifting WSN environments. Nevertheless, this review also highlights several unresolved challenges that hinder real-world adoption, including uncertain scalability to large-scale networks, limited model interpretability, nontrivial energy and memory overheads on resource-constrained sensor nodes and a lack of standardized evaluation protocols and reporting practices. By consolidating publicly available datasets, experimental configurations and comparative performance trends, we derive concrete design requirements for robust and resource-aware anomaly detection in operational WSNs and outline promising future research directions, emphasizing lightweight model architectures, explainable learning mechanisms and federated AE–SSL paradigms to enable adaptive, privacy-preserving monitoring in next-generation IoT sensing systems.

Förderung

  • “Regional Innovation System & Education (RISE)” through the Ulsan RISE Center
  • Ministry of Education (MOE) and the Ulsan Metropolitan City, Republic of Korea

Zitieren

APA

Subhan, R. M., Lee, Y., & Koo, I. (2026). Autoencoder-Based Self-Supervised Anomaly Detection in Wireless Sensor Networks: A Taxonomy-Driven Meta-Synthesis. Applied Sciences, 16(3), 1448. https://doi.org/10.3390/app16031448

Vancouver

Subhan RM, Lee Y, Koo I. Autoencoder-Based Self-Supervised Anomaly Detection in Wireless Sensor Networks: A Taxonomy-Driven Meta-Synthesis. Applied Sciences. 2026;16(3):1448. doi:10.3390/app16031448

BibTeX
@article{Subhan2026,
  author = {Subhan, Rana Muhammad and Lee, Young-Doo and Koo, Insoo},
  title = {Autoencoder-Based Self-Supervised Anomaly Detection in Wireless Sensor Networks: A Taxonomy-Driven Meta-Synthesis},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {3},
  pages = {1448},
  doi = {10.3390/app16031448}
}
Kostenlos starten →