An Uncertainty-Driven Hybrid Deep Learning Approach for Broad-Coverage RF Modulation Recognition

2026/08/01 by Nurettin Safak, Durdu Can Yerdeyatar, Muhammet Sefa Demirel +3
Engineering · Computer Science · #eess.SP #cs.LG

paper · pdf

6 pages, 7 figures, 5 tables. Accepted to ASYU 2026

arxiv created 2026/08/01 · arxiv updated 2026/08/04

Abstract

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±0.7% 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.

Citations

• CNN-LSTM Hybrid Architecture for Over-the-Air Automatic Modulation Classification Using SDR
• An Uncertainty Quantification Framework for Deep Learning-Based Automatic Modulation Classification
• AI/ML-Based Automatic Modulation Recognition: Recent Trends and Future Possibilities
• MAMCA -- Optimal on Accuracy and Efficiency for Automatic Modulation Classification with Extended Signal Length
• Enhancing Automatic Modulation Recognition through Robust Global Feature Extraction
• Class Information Guided Reconstruction for Automatic Modulation Open-Set Recognition
• Open Set Wireless Signal Classification: Augmenting Deep Learning with Expert Feature Classifiers
• Deep Learning Based Automatic Modulation Recognition: Models, Datasets, and Challenges
• Deep Neural Network Architectures for Modulation Classification
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Deep Architectures for Modulation Recognition
• An Introduction to Deep Learning for the Physical Layer
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning