Automatic modulation recognition plays an important role in military and civilian applications, identifying the modulation format of received signals before signal demodulation. With the increasing complexity and density of the electromagnetic environment, the multicomponent modulation radar signal recognition against various signal-to-noise ratio (SNR) conditions has become a practical and urgent problem. In this article, we propose a dual-component modulation recognition framework, which incorporates the residual Swin transformer denoise network, Swin transformer feature extraction network (SwinT), residual-attention (RA) modulation recognition head, and SNR level classifier and achieves robust recognition performance against various SNR conditions with tolerable complexity and accuracy tradeoff. First, the time–frequency analysis is employed to transform dual-component radar signals into time–frequency images (TFIs). Then, the TFIs at various SNR levels are applied to the SwinT, which generates shallow and deep feature representations for the SNR classifier and RA-modulation recognition head, respectively. The ResSwinT is initiated to reconstruct low SNR TFIs only, which are again processed by the SwinT. Finally, the RA-modulation recognition head provides modulation format predictions. The proposed framework can identify randomly combined dual-component radar signals from 12 modulation formats, meanwhile, improving the utilization of the SwinT feature and reducing unnecessary computation of the ResSwinT. Simulation results show that the proposed scheme can obtain an exact match ratio (EMR) of larger than $\boldsymbol{97\%}$ at SNR $\boldsymbol{>\!-6}$ dB. At low SNR condition ($\boldsymbol{-12}$ dB), the ResSwinT can obtain about EMR gain of $\boldsymbol{20\%}$ and the overall framework can achieve EMR of more than $\boldsymbol{80\%}$, which outperforms other state-of-the-art methods and obtains better generalization capability.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Automatic Modulation Recognition of Dual-Component Radar Signals Using ResSwinT–SwinT Network


    Beteiligte:
    Ren, Bing (Autor:in) / Teh, Kah Chan (Autor:in) / An, Hongyang (Autor:in) / Gunawan, Erry (Autor:in)


    Erscheinungsdatum :

    01.10.2023


    Format / Umfang :

    5224075 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Evaluation of vortex wake predictions in the SWINT code

    ADIASOR, M. / KRIEGER, R. | AIAA | 1985



    Histogram-Informed Radar PRI Modulation Recognition With Dual-Branch Network

    Wang, Jun / Wang, Hai / Xue, Lei et al. | IEEE | 2025


    Real-time low-complexity automatic modulation classifier for pulsed radar signals

    Iglesias, Victor / Grajal, Jesus / Royer, Pablo et al. | IEEE | 2015