Graph-based temporal anomaly detection with self-supervised contrastive learning and dynamic adaptive thresholding for acoustic howling suppression

Xiaoqian Fan; F. Hernando-Galego; Diego Martín; Mohammad Khishe

doi:10.1016/j.eij.2026.100892

Publication record · 2026

Graph-based temporal anomaly detection with self-supervised contrastive learning and dynamic adaptive thresholding for acoustic howling suppression

Authors: Xiaoqian Fan · F. Hernando-Galego · Diego Martín · Mohammad Khishe
Year: 2026
Publisher: Elsevier
Journal or publication: Egyptian Informatics Journal
Google Scholar citations: 0

Journal indicators

CiteScore 2025 (Scopus)9.1

Best quartileQ1

Top 10% in any categoryNo

Positions by category

Computer Science Applications171/1022 · Q1 · percentile 83
Information Systems89/519 · Q1 · percentile 82
Management Science and Operations Research40/225 · Q1 · percentile 82

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

This work models acoustic feedback as a temporal anomaly-detection problem, combining graph representations, self-supervised contrastive learning and a dynamic threshold to suppress unintended resonance.

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

DOI 10.1016/j.eij.2026.100892 ↗ · Open-access version ↗ · View Google Scholar record ↗