发表机构
Ankara Yildirim Beyazit University（安卡拉伊尔迪里姆贝亚兹特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低SNR与调制方案多样性限制现有RF调制识别性能的问题，提出融合FFT预处理频谱信息与STFT时频特征的不确定性驱动混合深度学习架构，通过2D CNN初级分类、MC Dropout不确定性估计及BiLSTM次级决策实现宽覆盖识别，在仿真环境中取得优异性能。
AI 中文摘要
自动射频（RF）调制识别在频谱监测、电子战和认知无线电应用中至关重要，然而低信噪比（SNR）条件以及调制方案多样性的不断增长限制了现有方法的性能。本文提出一种用于宽调制空间内射频信号识别的不确定性驱动混合深度学习架构，该方法结合基于低成本快速傅里叶变换（FFT）预处理获取的频谱信息与从短时傅里叶变换（STFT）语谱图提取的时频特征，执行多阶段分类流程。该架构包含基于二维卷积神经网络（2D CNN）的路径，用于快速、低延迟的初级分类；支持蒙特卡洛 dropout（MC Dropout）的贝叶斯不确定性估计，用于评估分类可靠性；以及在高不确定性条件下激活的基于双向长短期记忆网络（BiLSTM）的次级决策机制。该系统在涵盖不同SNR水平和调制类别的受控仿真环境中进行评估，实验结果显示，初级2D CNN路径实现了83.3±0.7%的准确率，每个样本的推理时间仅为0.138 ms，相比传统基于规则和经典机器学习方法表现更优。此外，研究结果揭示了紧凑频谱特征表示及缺乏时序建模的分类器的局限性，尤其是在区分基于频移键控（FSK）的调制时，不确定性估计模块在检测低置信度决策方面展现出良好效果，所提方法为实时射频调制识别提供了低延迟、可扩展解决方案的潜力。
英文摘要
Automatic RF modulation recognition is of critical importance in spectrum monitoring, electronic warfare, and cognitive radio applications, where low signal-to-noise ratio (SNR) conditions and the growing diversity of modulation schemes limit the performance of existing methods. This paper proposes an uncertainty-driven hybrid deep learning architecture for recognizing RF signals over a broad modulation space. The proposed approach carries out a multi-stage classification process by combining spectral information obtained through low-cost FFT-based preprocessing with time-frequency features extracted from short-time Fourier transform (STFT) spectrograms. The architecture comprises a 2D convolutional neural network (2D CNN)-based path for fast, low-latency primary classification, MC Dropout-supported Bayesian uncertainty estimation for assessing classification reliability, and a BiLSTM-based secondary decision mechanism activated under high-uncertainty conditions. The proposed system is evaluated in a controlled simulation environment spanning different SNR levels and modulation classes. Experimental results show that the primary 2D CNN path achieves $83.3\pm0.7\%$ accuracy with an inference time of only 0.138 ms per sample, providing superior performance compared with traditional rule-based and classical machine-learning approaches. Furthermore, the obtained findings reveal the limitations of compact spectral feature representations and classifiers lacking temporal modeling, particularly in disambiguating FSK-based modulations. The uncertainty estimation module offers promising results for detecting low-confidence decisions, and the proposed approach demonstrates the potential of a low-latency and scalable solution for real-time RF modulation recognition.
Comments6 pages, 7 figures, 5 tables. Accepted to ASYU 2026
