In EDS ansehen

CAIC-Net: Robust Radio Modulation Classification via Unified Dynamic Cross-Attention and Cross-Signal-to-Noise Ratio Contrastive Learning

Gespeichert in:
Bibliographische Detailangaben
Titel: CAIC-Net: Robust Radio Modulation Classification via Unified Dynamic Cross-Attention and Cross-Signal-to-Noise Ratio Contrastive Learning
Autoren: Teng Wu, Quan Zhu, Runze Mao, Changzhen Hu, Shengjun Wei
Quelle: Sensors ; Volume 26 ; Issue 3 ; Pages: 756
Verlagsinformationen: Multidisciplinary Digital Publishing Institute
Publikationsjahr: 2026
Bestand: MDPI Open Access Publishing
Schlagwörter: automatic modulation classification, deep learning techniques, feature-based extraction, dynamic cross-attention
Beschreibung: In complex wireless communication environments, automatic modulation classification (AMC) faces two critical challenges: the lack of robustness under low-signal-to-noise ratio (SNR) conditions and the inefficiency of integrating multi-scale feature representations. To address these issues, this paper proposes CAIC-Net, a robust modulation classification network that integrates a dynamic cross-attention mechanism with a cross-SNR contrastive learning strategy. CAIC-Net employs a dual-stream feature extractor composed of ConvLSTM2D and Transformer blocks to capture local temporal dependencies and global contextual relationships, respectively. To enhance fusion effectiveness, we design a Dynamic Cross-Attention Unit (CAU) that enables deep bidirectional interaction between the two branches while incorporating an SNR-aware mechanism to adaptively adjust the fusion strategy under varying channel conditions. In addition, a Cross-SNR Contrastive Learning (CSCL) module is introduced as an auxiliary task, where positive and negative sample pairs are constructed across different SNR levels and optimized using InfoNCE loss. This design significantly strengthens the intrinsic noise-invariant properties of the learned representations. Extensive experiments conducted on two standard datasets demonstrate that CAIC-Net achieves competitive classification performance at moderate-to-high SNRs and exhibits clear advantages in extremely low-SNR scenarios, validating the effectiveness and strong generalization capability of the proposed approach.
Publikationsart: text
Dateibeschreibung: application/pdf
Sprache: English
Relation: Communications; https://dx.doi.org/10.3390/s26030756
DOI: 10.3390/s26030756
Verfügbarkeit: https://doi.org/10.3390/s26030756
Rights: https://creativecommons.org/licenses/by/4.0/
Dokumentencode: edsbas.57DCDC72
Datenbank: BASE
Beschreibung
Abstract:In complex wireless communication environments, automatic modulation classification (AMC) faces two critical challenges: the lack of robustness under low-signal-to-noise ratio (SNR) conditions and the inefficiency of integrating multi-scale feature representations. To address these issues, this paper proposes CAIC-Net, a robust modulation classification network that integrates a dynamic cross-attention mechanism with a cross-SNR contrastive learning strategy. CAIC-Net employs a dual-stream feature extractor composed of ConvLSTM2D and Transformer blocks to capture local temporal dependencies and global contextual relationships, respectively. To enhance fusion effectiveness, we design a Dynamic Cross-Attention Unit (CAU) that enables deep bidirectional interaction between the two branches while incorporating an SNR-aware mechanism to adaptively adjust the fusion strategy under varying channel conditions. In addition, a Cross-SNR Contrastive Learning (CSCL) module is introduced as an auxiliary task, where positive and negative sample pairs are constructed across different SNR levels and optimized using InfoNCE loss. This design significantly strengthens the intrinsic noise-invariant properties of the learned representations. Extensive experiments conducted on two standard datasets demonstrate that CAIC-Net achieves competitive classification performance at moderate-to-high SNRs and exhibits clear advantages in extremely low-SNR scenarios, validating the effectiveness and strong generalization capability of the proposed approach.
DOI:10.3390/s26030756