TFAM-AAE-Uk: A Dual-Metric Spectrum Anomaly Detection Algorithm

• Published in: IEEE communications letters 2024-11, Vol.28 (11), p.2638-2642
• Main Authors: Ji, Haipeng, Zhang, Tao, Qiao, Xiaoqiang, Wu, Hao, Gui, Guan
• Format: Article
• Language: English
• Subjects: adversarial autoencoder; Anomaly detection; Feature extraction; Fingerprint recognition; Law; openset recognition; Spectrum anomaly detection; time frequency attention mechanism; Time-frequency analysis; Training; Vectors
• ISSN: 1089-7798
• DOI: 10.1109/LCOMM.2024.3430314

Effective spectrum management critically depends on the ability to detect anomalies caused by both legal user (LU) violations and illegal user (IU) intrusions. In this study, we introduce TFAM-AAE- \mathbf {U_{k}} , an innovative spectrum anomaly detection framework that integrates an Adversarial Autoencoder (AAE) with a Time Frequency Attention Mechanism (TFAM) and a specialized user discriminator, \mathbf {U_{k}} . This framework first employs the TFAM-AAE to reconstruct spectrum data by exploiting latent, time, and frequency features of the input. The reconstruction error serves as the primary anomaly detection metric. To address the challenges posed by low interference-to-signal ratio (ISR) IUs and camouflaged LUs, \mathbf {U_{k}} is utilized to extract fingerprint features vectors from IQ data, establishing class center vectors for each LU. The Mahalanobis distance between these vectors is then calculated as a secondary metric for anomaly detection. Our experimental results demonstrate that TFAM-AAE- \mathbf {U_{k}} consistently achieves excellent detection performance, particularly in scenarios involving challenging and hard-to-detect anomalies.