Hybrid time series transformer–deep belief network for robust anomaly detection in mobile communication networks

Anita Ershadi Oskouei; Mehrdad Kaveh; F. Hernando-Galego; Diego Martín

doi:10.3390/sym17111800

Publication record · 2025

Hybrid time series transformer–deep belief network for robust anomaly detection in mobile communication networks

Authors: Anita Ershadi Oskouei · Mehrdad Kaveh · F. Hernando-Galego · Diego Martín
Year: 2025
Publisher: MDPI
Journal or publication: Symmetry
Google Scholar citations: 4

Journal indicators

CiteScore 2025 (Scopus)5.2

Best quartileQ1

Top 10% in any categoryYes

Positions by category

Mathematics (all)36/414 · Q1 · percentile 91 · Top 10%
Physics and Astronomy (miscellaneous)18/88 · Q1 · percentile 80
Computer Science (miscellaneous)63/179 · Q2 · percentile 65
Chemistry (miscellaneous)66/137 · Q2 · percentile 52

Scopus source ↗

JCR (Clarivate): Not verified: the supplied ranking file is Scopus CiteScore, not JCR.

Included in the supplied report on non-standard bibliometric behaviour (2017–2019).

The report is an independent analysis published in 2021; it is not an official ANECA ban or endorsement list.

Research summary

A time-series Transformer and deep-belief-network architecture, tuned by an improved orchard algorithm, detects anomalies across heterogeneous 5G, IoT, edge and DDoS traffic. Four benchmarks test temporal modelling, generalization and scalability toward 6G networks.

Original description prepared for this website; consult the publication for its authoritative abstract.

DOI 10.3390/sym17111800 ↗ · Open-access version ↗ · View Google Scholar record ↗