A Novel Hybrid Evolutionary Transformer-Long Short-Term Memory Model for Unified Anomaly Detection in IoT and Cyber-Physical Networks

Pardis Sadatian Moghaddam; Mahyar Mahmoudi; Nuria Serrano; F. Hernando-Galego; Diego Martín; José Vicente Álvarez-Bravo

doi:10.32604/cmc.2026.081311

Publication record · 2026

A Novel Hybrid Evolutionary Transformer-Long Short-Term Memory Model for Unified Anomaly Detection in IoT and Cyber-Physical Networks

Authors: Pardis Sadatian Moghaddam · Mahyar Mahmoudi · Nuria Serrano · F. Hernando-Galego · Diego Martín · José Vicente Álvarez-Bravo
Year: 2026
Publisher: Tech Science Press
Journal or publication: Computers, Materials & Continua
Google Scholar citations: 0

Journal indicators

CiteScore 2025 (Scopus)6.6

Best quartileQ1

Top 10% in any categoryNo

Positions by category

Modeling and Simulation45/397 · Q1 · percentile 88
Electrical and Electronic Engineering230/1030 · Q1 · percentile 77
Mechanics of Materials98/408 · Q1 · percentile 76
Computer Science Applications269/1022 · Q2 · percentile 73
Biomaterials61/146 · Q2 · percentile 58

Scopus source ↗

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

Not identified 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 unified anomaly-detection framework couples Transformer global context with LSTM temporal modelling and evolutionary hyperparameter optimisation. Evaluation across four heterogeneous CIC datasets tests generalisation in conventional, IoT and vehicular network traffic.

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

DOI 10.32604/cmc.2026.081311 ↗ · Open-access version ↗ · View Google Scholar record ↗