Robust Multi-Task Signal Classification via Multi-Scale Multi-Component Decomposition and Fusion Network
IEEE Communications Letters · 2026 · 30 · 1340-1344
DOI: 10.1109/lcomm.2026.3672922 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Yuchi Zhao und 6 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Gefördert von: Natural Science Foundation of China, Major and Key Project Principal Investigator (PI) Development Program of Nanjing University of Posts and Telecommunications.
Abstract (Originalsprache)
The increasing complexity of modern wireless communication systems calls for robust signal recognition techniques capable of capturing multidimensional characteristics under challenging channel conditions. Conventional single-label classification approaches often fall short in such scenarios, particularly exhibiting poor robustness in low signal-to-noise ratio (SNR) environments. To overcome these limitations, this letter proposes a Multi-Scale Multi-Component Decomposition and Fusion Network (MSCDFN) within a multi-task learning (MTL) framework for joint modulation classification and signal type recognition. The proposed MSCDFN employs a novel multi-scale decomposition module to extract both principal and residual components across multiple resolutions, followed by a hierarchical fusion strategy that effectively enhances discriminative feature representation. Experimental results on the RadComAWGN and RadComDynamic datasets demonstrate that MSCDFN consistently outperforms state-of-the-art baseline models across a wide range of SNR conditions, verifying its robustness and practical potential for real-world wireless signal recognition.
Förderung
- Natural Science Foundation of China
- Major and Key Project Principal Investigator (PI) Development Program of Nanjing University of Posts and Telecommunications
Zitieren
APA
Zhao, Y., Zhang, J., Wu, A., Wang, Q., Xu, L., Lin, Y., & Gui, G. (2026). Robust Multi-Task Signal Classification via Multi-Scale Multi-Component Decomposition and Fusion Network. IEEE Communications Letters, 30, 1340-1344. https://doi.org/10.1109/lcomm.2026.3672922
Vancouver
Zhao Y, Zhang J, Wu A, Wang Q, Xu L, Lin Y, et al. Robust Multi-Task Signal Classification via Multi-Scale Multi-Component Decomposition and Fusion Network. IEEE Communications Letters. 2026;30:1340-1344. doi:10.1109/lcomm.2026.3672922
BibTeX
@article{Zhao2026,
author = {Zhao, Yuchi and Zhang, Jie and Wu, Aiping and Wang, Qin and Xu, Lexi and Lin, Yun and Gui, Guan},
title = {Robust Multi-Task Signal Classification via Multi-Scale Multi-Component Decomposition and Fusion Network},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {1340--1344},
doi = {10.1109/lcomm.2026.3672922}
}
EUVIMED