IQTF-GFN: A Gated dual-path network for automatic modulation classification of dual-component overlapping emitter signals

TY - JOUR

T1 - IQTF-GFN

T2 - A Gated dual-path network for automatic modulation classification of dual-component overlapping emitter signals

AU - Zhang, Lizhi

AU - Zhang, Bo Han

AU - Hao, Xinhong

AU - Dai, Jian

AU - Hou, Chaowen

AU - Yan, Xiaopeng

N1 - Publisher Copyright: © 2026 China Ordnance Society. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd. This is an open access article under the CC BY-NC-ND license. http://creativecommons.org/licenses/by-nc-nd/4.0/

PY - 2026/5

Y1 - 2026/5

N2 - Achieving reliable modulation recognition for overlapping dual-component emitter signals in dense, low signal-to-noise ratio (SNR) electromagnetic environments presents a formidable challenge for modern electronic reconnaissance. Conventional deep learning approaches, which primarily rely on time-frequency images (TFIs), often overlook intrinsic physical properties of signals, resulting in substantial performance degradation under severe noise conditions. To address this, we propose the I/Q and Time-Frequency Gated Fusion Network (IQTF-GFN), a novel cross-modal fusion framework that systematically integrates physical priors into advanced deep learning architectures. The framework employs a parallel dual-branch structure to jointly process one-dimensional (1D) I/Q sequences and two-dimensional (2D) TFIs. Its key innovations include the incorporation of physical priors into the I/Q branch via a Higher-Order Statistics (HOS) pathway for noise-invariant feature extraction, an attention-driven Multi-Instance Learning (MIL) mechanism in the TFI branch to adaptively emphasize salient spectral regions, and a task-aware gating network for dynamic and intelligent fusion. Extensive experiments across 10 Monte Carlo trials demonstrate that IQTF-GFN sets a new state-of-the-art (SOTA) benchmark in both robustness and efficiency. Under the challenging condition of −9 dB SNR, the framework achieves an average Exact Match Ratio (EMR) of 94.11%, outperforming the strongest baseline by more than 11 percentage points. Remarkably, this performance is delivered by a highly efficient architecture with only 19.64 million parameters and 1.38 GFLOPs. The design reduces the theoretical computational load by up to 78% and achieves a practical inference latency of just 0.52 ms per sample. By combining high accuracy with computational efficiency, IQTF-GFN provides a robust and practical solution, introducing a new paradigm for embedding physical priors into deep learning for complex electromagnetic signal recognition.

AB - Achieving reliable modulation recognition for overlapping dual-component emitter signals in dense, low signal-to-noise ratio (SNR) electromagnetic environments presents a formidable challenge for modern electronic reconnaissance. Conventional deep learning approaches, which primarily rely on time-frequency images (TFIs), often overlook intrinsic physical properties of signals, resulting in substantial performance degradation under severe noise conditions. To address this, we propose the I/Q and Time-Frequency Gated Fusion Network (IQTF-GFN), a novel cross-modal fusion framework that systematically integrates physical priors into advanced deep learning architectures. The framework employs a parallel dual-branch structure to jointly process one-dimensional (1D) I/Q sequences and two-dimensional (2D) TFIs. Its key innovations include the incorporation of physical priors into the I/Q branch via a Higher-Order Statistics (HOS) pathway for noise-invariant feature extraction, an attention-driven Multi-Instance Learning (MIL) mechanism in the TFI branch to adaptively emphasize salient spectral regions, and a task-aware gating network for dynamic and intelligent fusion. Extensive experiments across 10 Monte Carlo trials demonstrate that IQTF-GFN sets a new state-of-the-art (SOTA) benchmark in both robustness and efficiency. Under the challenging condition of −9 dB SNR, the framework achieves an average Exact Match Ratio (EMR) of 94.11%, outperforming the strongest baseline by more than 11 percentage points. Remarkably, this performance is delivered by a highly efficient architecture with only 19.64 million parameters and 1.38 GFLOPs. The design reduces the theoretical computational load by up to 78% and achieves a practical inference latency of just 0.52 ms per sample. By combining high accuracy with computational efficiency, IQTF-GFN provides a robust and practical solution, introducing a new paradigm for embedding physical priors into deep learning for complex electromagnetic signal recognition.

KW - Automatic modulation classification (AMC)

KW - Gated mechanism

KW - Low signal-to-noise ratio (SNR)

KW - Multi-modal fusion

KW - Overlapping emitter signals

KW - Physical prior

UR - https://www.scopus.com/pages/publications/105034550652

U2 - 10.1016/j.dt.2025.11.001

DO - 10.1016/j.dt.2025.11.001

M3 - Article

AN - SCOPUS:105034550652

SN - 2096-3459

VL - 59

SP - 201

EP - 216

JO - Defence Technology

JF - Defence Technology

ER -