Deep Learning for Spectrum Sensing and Interference Mitigation in Wireless Networks
DOI:
https://doi.org/10.58445/rars.3515Keywords:
Spectrum Sensing, Interference Detection, Deep Learning, Wireless NetworksAbstract
Effective spectrum monitoring in the congested 2.4 GHz band, where ZigBee, Wi-Fi, Bluetooth, and others coexist, requires solutions that balance high accuracy with low computational complexity for real-time operation. Existing Deep Learning (DL) approaches, such as ResNet, are often characterized by high computational loads or are trained exclusively on synthetic data, limiting their robustness in real-world conditions.
This work proposes a compact and computationally efficient Convolutional Neural Network (CNN) architecture for simultaneous radio interference detection and classification. Short-Time Fourier Transform (STFT) spectrograms are utilized as input data.
A key element of novelty is the training methodology employing a hybrid dataset, which combines synthetic signals (sourced from RadioML and MathWorks) with an extensive array of real-world raw over-the-air recordings obtained via Software-Defined Radio (SDR).
Experimental results demonstrate that the proposed architecture achieves 94% accuracy in detection and classification tasks. The model significantly outperforms baseline CNN and ResNet architectures, particularly regarding stability and robustness across various Signal-to-Noise Ratios (SNR).
The findings confirm that the proposed lightweight approach, enhanced by hybrid training, constitutes a highly effective and practical solution for real-world deployment in dynamic radio resource management systems.
References
Zhu, J., Waltho, A., Yang, X., & Guo, X. (2007, August). Multi-radio coexistence: Challenges and opportunities. In 2007 16th International Conference on Computer Communications and Networks (pp. 358-364). IEEE.
Sharma, N., & Kaur, A. (2010, November). Coexistence: Threat to the Performance of Heterogeneous Network. In AIP Conference Proceedings (Vol. 1324, No. 1, pp. 90-94). American Institute of Physics.
Jha, U. S. (2002). Wireless Landscape–Need for Seamless Connectivity. Wireless Personal Communications, 22(2), 275-283.
Zheng, L., Lops, M., Eldar, Y. C., & Wang, X. (2019). Radar and communication coexistence: An overview: A review of recent methods. IEEE Signal Processing Magazine, 36(5), 85-99.
Su, Y., Lin, Y., Liu, S., Liwang, M., Liao, X., Wu, T., ... & Wang, X. (2024). Coexistence of hybrid VLC-RF and Wi-Fi for indoor wireless communication systems: an intelligent approach. IEEE Transactions on Network and Service Management.
Omotere, O., Fuller, J., Qian, L., & Han, Z. (2018, August). Spectrum occupancy prediction in coexisting wireless systems using deep learning. In 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall) (pp. 1-7). IEEE.
Miller, R. D., Kokalj-Filipovic, S., Vanhoy, G., & Morman, J. (2019, November). Policy based synthesis: Data generation and augmentation methods for rf machine learning. In 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP) (pp. 1-5). IEEE.
O'shea, T. J., & West, N. (2016, September). Radio machine learning dataset generation with gnu radio. In Proceedings of the GNU radio conference (Vol. 1, No. 1).
Kattenborn, T., Leitloff, J., Schiefer, F., & Hinz, S. (2021). Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS journal of photogrammetry and remote sensing, 173, 24-49.
Lu, X., Tao, M., Fu, X., Gui, G., Ohtsuki, T., & Sari, H. (2021, September). Lightweight network design based on ResNet structure for modulation recognition. In 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall) (pp. 1-5). IEEE.
Podder, P., Zawodniok, M., & Madria, S. (2024, June). Deep learning for UAV detection and classification via Radio frequency signal analysis. In 2024 25th IEEE International Conference on Mobile Data Management (MDM) (pp. 165-174). IEEE.
Nguyen, H. N., Vomvas, M., Vo-Huu, T., & Noubir, G. (2021, November). Wideband, real-time spectro-temporal RF identification. In Proceedings of the 19th ACM international symposium on mobility management and wireless access (pp. 77-86).
Boegner, L., Vanhoy, G., Vallance, P., Gulati, M., Feitzinger, D., Comar, B., & Miller, R. D. (2022). Large scale radio frequency wideband signal detection & recognition. arXiv preprint arXiv:2211.10335.
Fan, C., Yuan, X., & Zhang, Y. J. (2019). CNN-based signal detection for banded linear systems. IEEE Transactions on Wireless Communications, 18(9), 4394-4407.
Scholl, S. (2022). RF signal classification with synthetic training data and its real-world performance. arXiv preprint arXiv:2206.12967.
Carlson, A., Skinner, K. A., Vasudevan, R., & Johnson-Roberson, M. (2019). Sensor transfer: Learning optimal sensor effect image augmentation for sim-to-real domain adaptation. IEEE Robotics and Automation Letters, 4(3), 2431-2438.
Hu, C., Hudson, S., Ethier, M., Al-Sharman, M., Rayside, D., & Melek, W. (2022, June). Sim-to-real domain adaptation for lane detection and classification in autonomous driving. In 2022 IEEE Intelligent Vehicles Symposium (IV) (pp. 457-463). IEEE.
Tandra, R., & Sahai, A. (2008). SNR walls for signal detection. IEEE Journal of selected topics in Signal Processing, 2(1), 4-17.
Jagannath, A., & Jagannath, J. (2021, June). Multi-task learning approach for automatic modulation and wireless signal classification. In ICC 2021-IEEE International Conference on Communications (pp. 1-7). IEEE.
Huang, Z., Pemasiri, A., Denman, S., Fookes, C., & Martin, T. (2023, June). Multi-task learning for radar signal characterisation. In 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (pp. 1-5). IEEE.
Downloads
Posted
Categories
License
Copyright (c) 2025 Adilzhan Ayazbek, Olzhas Myrzakhmet
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license
