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

arXiv: https://arxiv.org/abs/2608.00796 · HTML: https://mlsanity.com/paper/2608.00796/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 23 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Over the Air Deep Learning Based Radio Signal Classification](https://mlsanity.com/paper/1712.04578/) (2017)
- [Distributed Deep Learning Models for Wireless Signal Classification with Low-Cost Spectrum Sensors](https://mlsanity.com/paper/1707.08908/) (2017)
- [Deep Architectures for Modulation Recognition](https://mlsanity.com/paper/1703.09197/) (2017)
- [Deep Neural Network Architectures for Modulation Classification](https://mlsanity.com/paper/1712.00443/) (2017)
- [Deep Learning Based Automatic Modulation Recognition: Models, Datasets, and Challenges](https://mlsanity.com/paper/2207.09647/) (2022)
- [Enhancing Automatic Modulation Recognition through Robust Global Feature Extraction](https://mlsanity.com/paper/2401.01056/) (2024)
- [Open Set Wireless Signal Classification: Augmenting Deep Learning with Expert Feature Classifiers](https://mlsanity.com/paper/2302.03749/) (2023)
- [Class Information Guided Reconstruction for Automatic Modulation Open-Set Recognition](https://mlsanity.com/paper/2312.13023/) (2023)
- [MAMCA -- Optimal on Accuracy and Efficiency for Automatic Modulation Classification with Extended Signal Length](https://mlsanity.com/paper/2405.11263/) (2024)
- [AI/ML-Based Automatic Modulation Recognition: Recent Trends and Future Possibilities](https://mlsanity.com/paper/2502.05315/) (2025)
- [CNN-LSTM Hybrid Architecture for Over-the-Air Automatic Modulation Classification Using SDR](https://mlsanity.com/paper/2511.21040/) (2025)
- [An Uncertainty Quantification Framework for Deep Learning-Based Automatic Modulation Classification](https://mlsanity.com/paper/2503.04142/) (2025)

## Built on by (most cited first, 1 of 1)

- [Sub-6 GHz Over-the-Air AMC via Curriculum Fine-Tuned CNN-Transformers](https://mlsanity.com/paper/2609.07726/) (2026)

## Abstract (arXiv)

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.