FE-SKViT: A Feature-Enhanced ViT Model with Skip Attention for Automatic Modulation Recognition

Autor:	Guangyao Zheng, Bo Zang, Penghui Yang, Wenbo Zhang, Bin Li
Jazyk:	angličtina
Rok vydání:	2024
Předmět:	automatic modulation recognition vision transformers translation variant convolution Science
Zdroj:	Remote Sensing, Vol 16, Iss 22, p 4204 (2024)
Druh dokumentu:	article
ISSN:	2072-4292
DOI:	10.3390/rs16224204
Popis:	Automatic modulation recognition (AMR) is widely employed in communication systems. However, under conditions of low signal-to-noise ratio (SNR), recent studies reveal limitations in achieving high AMR accuracy. In this work, we introduce a novel network architecture that leverages a transformer-inspired approach tailored for AMR, called Feature-Enhanced Transformer with skip-attention (FE-SKViT). This innovative design adeptly harnesses the advantages of translation variant convolution and the Transformer framework, handling intra-signal variance and small cross-signal variance to achieve enhanced recognition accuracy. Experimental results on RadioML2016.10a, RadioML2016.10b, and RML22 datasets demonstrate that the Feature-Enhanced Transformer with skip-attention (FE-SKViT) excels over other methods, particularly under low SNR conditions ranging from −4 to 6 dB.
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/cca8a80adfca4569b2224775781fee8b Zobrazit plný text záznamu View record in DOAJ Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.