Autors: Syed S.N., Ivanov, A. S., Khan F.A., Ahmed Q.Z., Poulkov, V. K., Lazaridis P.I.
Title: A Lightweight CNN with Dilations for Spectrum Sensing Using Experimentally Collected Datasets
Keywords: 6G, Cognitive Radio (CR), Deep Learning (DL), Deep Neural Networks (DNNs), Machine Learning (ML), Software-Defined Radio (SDR), Spectrum Sensing (SS), Universal Software Radio Peripheral (USRP)

Abstract: Spectrum sensing enables Secondary Users (SUs) in cognitive radio networks to opportunistically access underutilized spectrum without causing interference to Primary Users (PUs). While deep neural networks have shown strong potential for this task, most existing approaches rely heavily on simulated datasets, limiting their applicability in real-world environments. In this work, we present a real-world dataset collected using two Universal Software Radio Peripheral (USRP) B210 devices, where one emulates the PU and the other acts as the SU. Additionally, a baseline additive white Gaussian noise dataset is collected using a wired setup. We further propose a lightweight convolutional neural network with dilated convolutions that achieves the highest sensing accuracy across all modulation schemes. At a signal-to-noise ratio of -6 dB, it outperforms the second-best method by 19.35% while being 40.5% smaller in size and requiring 85.18% fewer floating-point operations. Experiments using our real-world datasets and synthetic datasets derived from the widely used RadioML2016.10A and RML22 datasets reveal a significant drop in model performance on real-world data, highlighting the limitations of simulation-based evaluations and the importance of realistic datasets in spectrum sensing research.

References

  1. X. Cao et al., “AI-Empowered Multiple Access for 6G: A Survey of Spectrum Sensing, Protocol Designs, and Optimizations,” in Proc. IEEE, vol. 112, no. 9, pp. 1264–1302, 2024.
  2. C. Nguyen, T. M. Hoang, and A. A. Cheema, “Channel Estimation Using CNN-LSTM in RIS-NOMA Assisted 6G Network,” in IEEE Trans. Mach. Learn. Commun. Netw., vol. 1, pp. 43–60, 2023.
  3. Q. Wang, B. Su, C. Wang, L. P. Qian, Y. Wu, and X. Yang, “ConvLSTM-Based Spectrum Sensing at Very Low SNR,” in IEEE Wireless Commun. Lett., vol. 12, no. 6, pp. 967–971, 2023.
  4. L. Wang, J. Hu, C. Zhang, R. Jiang, and Z. Chen, “Deep Learning Models for Spectrum Prediction: A Review,” in IEEE Sens. J., vol. 24, no. 18, pp. 28553–28575, 2024.
  5. Z. Su, K. C. Teh, S. G. Razul, and A. C. Kot, “Robust Channel Invariant Deep Noncooperative Spectrum Sensing,” in IEEE Wireless Commun. Lett., vol. 12, no. 3, pp. 436–440, 2023.
  6. Z. Chen, Y. Q. Xu, H. Wang, and D. Guo, “Deep STFT-CNN for Spectrum Sensing in Cognitive Radio,” in IEEE Commun. Lett., vol. 25, no. 3, pp. 864–868, 2021.
  7. S. N. Syed et al., “Deep Neural Networks for Spectrum Sensing: A Review,” in IEEE Access, vol. 11, pp. 89591–89615, 2023.
  8. J. Xie, J. Fang, C. Liu, and X. Li, “Deep Learning-Based Spectrum Sensing in Cognitive Radio: A CNN-LSTM Approach,” in IEEE Commun. Lett., vol. 24, no. 10, pp. 2196–2200, 2020.
  9. D. Inc., “RF Datasets For Machine Learning,” [Online]. Available: https://www.deepsig.ai/datasets. [Accessed 21 December 2024].
  10. T. J. Shea and N. West, “Radio Machine Learning Dataset Generation with GNU Radio,” in Proceedings of the GNU Radio Conference, [S. I.], vol. 1, no. 1, Sep. 2016. [Online]. Available: https://pubs.gnuradio.org/index.php/grcon/article/view/11. [Accessed 24 December 2024].
  11. V. Sathyanarayanan, P. Gerstoft, and A. E. Gamal, “RML22: Realistic Dataset Generation for Wireless Modulation Classification,” in IEEE Trans. Wireless Commun., vol. 22, no. 11, pp. 7663–7675, 2023.
  12. “3rd Generation Partnership Project (3GPP). Evolved Universal Terrestrial Radio Access (E-UTRA); User Equipment (UE) Radio Transmission and Reception. Version 14.3.0. Number 36.101.” [Online]. Available: https://www.etsi.org/deliver/etsi ts/136100 136199/136101/14.03.00 60/ts 136101v140300p.pdf.
  13. J. Xie, C. Liu, Y.-C. Liang, and J. Fang, “Activity Pattern Aware Spectrum Sensing: A CNN-Based Deep Learning Approach,” in IEEE Commun. Lett., vol. 23, no. 6, pp. 1025–1028, 2019.
  14. J. Gao, X. Yi, C. Zhong, X. Chen, and Z. Zhang, “Deep Learning for Spectrum Sensing,” in IEEE Wireless Commun. Lett., vol. 8, no. 6, pp. 1727–1730, 2019.
  15. J. Xie, J. Fang, C. Liu, and L. Yang, “Unsupervised Deep Spectrum Sensing: A Variational Auto-Encoder Based Approach,” in IEEE Trans. Veh. Technol., vol. 69, no. 5, pp. 5307–5319, 2020.
  16. Z. Su, K. C. Teh, S. G. Razul and A. C. Kot, “Deep Non-Cooperative Spectrum Sensing Over Rayleigh Fading Channel,” in IEEE Trans. on Veh. Technol., vol. 71, no. 4, pp. 4460-4464, April 2022.
  17. Q. Peng, A. Gilman, N. Vasconcelos, P. C. Cosman, and L. B. Milstein, “Robust Deep Sensing Through Transfer Learning in Cognitive Radio,” in IEEE Wireless Commun. Lett., vol. 9, no. 1, pp. 38–41, 2020.
  18. Q. Cheng, Z. Shi, D. N. Nguyen, and E. Dutkiewicz, “Sensing OFDM Signal: A Deep Learning Approach,” in IEEE Trans. Commun., vol. 67, no. 11, pp. 7785–7798, 2019.
  19. W. M. Lees, A. Wunderlich, P. J. Jeavons, P. D. Hale, and M. R. Souryal, “Deep Learning Classification of 3.5-GHz Band Spectrograms With Applications to Spectrum Sensing,” in IEEE Trans. Cogn. Commun. Netw., vol. 5, no. 2, pp. 224–236, 2019.
  20. B. Soni, D. K. Patel, and M. Lopez-Benitez, “Long Short-Term Memory Based Spectrum Sensing Scheme for Cognitive Radio Using Primary Activity Statistics,” in IEEE Access, vol. 8, pp. 97437–97451, 2020.
  21. S. Subray, S. Tschimben, and K. Gifford, “Towards Enhancing Spectrum Sensing: Signal Classification Using Autoencoders,” in IEEE Access, vol. 9, pp. 82288–82299, 2021.
  22. X. Ding, T. Ni, Y. Zou, and G. Zhang, “Deep Learning for Satellites Based Spectrum Sensing Systems: A Low Computational Complexity Perspective,” in IEEE Trans. Veh. Technol., vol. 72, no. 1, pp. 1366–1371, 2023.
  23. Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,” in IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 12, pp. 1–21, 2021.
  24. Y. He and L. Xiao, “Structured Pruning for Deep Convolutional Neural Networks: A Survey,” in IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 5, pp. 2900–2919, 2024.
  25. S. N. Syed et al., “Deep Learning Approaches for Spectrum Sensing in Cognitive Radio Networks,” Proc. 25th Int. Symp. Wireless Pers. Multimedia Commun. (WPMC), Herning, Denmark, 2022, pp. 480–485.
  26. J. Cai, F. Gan, X. Cao and W. Liu, “Signal Modulation Classification Based on the Transformer Network,” in IEEE Trans. Cogn. Commun. Netw., vol. 8, no. 3, pp. 1348-1357, Sept. 2022.
  27. S. Mehta and M. Rastegari, “MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer,” arXiv preprint arXiv:2110.02178, Oct. 2021.
  28. T. O’Shea and J. Hoydis, “An Introduction to Deep Learning for the Physical Layer,” in IEEE Trans. Cogn. Commun. Netw., vol. 3, no. 4, pp. 563–575, 2017.
  29. F. F. Digham, M. -S. Alouini and M. K. Simon, “On the Energy Detection of Unknown Signals Over Fading Channels,” in IEEE Trans. Commun., vol. 55, no. 1, pp. 21-24, Jan. 2007.
  30. E. Research, “USRP B210 USB Software Defined Radio (SDR),” [Online]. Available: https://www.ettus.com/all-products/ub210-kit/. [Accessed 15 April 2025].
  31. GNU Radio Wiki, “Simulation example: BPSK Demodulation,” [Online]. Available: https://wiki.gnuradio.org/index.php/Simulation_example:_BPSK_Dem odulation. [Accessed 15 June 2024].
  32. GNU Radio Wiki, “QPSK Mod and Demod,” [Online]. Available: https://wiki.gnuradio.org/index.php?title=QPSK_Mod_and_Demod. [Accessed 16 June 2024].
  33. F. Yu and V. Koltun, “Multi-Scale Context Aggregation by Dilated Convolutions,” arXiv:1511.07122 [cs], Apr. 2016.
  34. T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785-794.
  35. T. J. O’Shea, T. Roy, and T. C. Clancy, “Over-the-Air Deep Learning Based Radio Signal Classification,” in IEEE J. Sel. Top. Signal Process., vol. 12, no. 1, pp. 168–179, 2018.
  36. M. W. Aslam, Z. Zhu, and A. K. Nandi, “Automatic Modulation Classification Using Combination of Genetic Programming and KNN,” in IEEE Trans. Wireless Commun., vol. 11, no. 8, pp. 2742–2750, 2012.
  37. TensorFlow, “Models and layers | TensorFlow.js,” [Online]. Available: https://www.tensorflow.org/js/guide/models_and_layers. [Accessed 19 November 2024]
  38. M. Li, J. Lin, Y. Ding, Z. Liu, J.-Y. Zhu, and S. Han, “GAN Compression: Efficient Architectures for Interactive Conditional GANs,” Jun. 2020.
  39. V. Sze, Y. -H. Chen, T. -J. Yang and J. S. Emer, “Efficient Processing of Deep Neural Networks: A Tutorial and Survey,” in Proc. of the IEEE, vol. 105, no. 12, pp. 2295-2329, Dec. 2017.
  40. H. Qi, E. R. Sparks, and A. Talwalkar, “PALEO: A performance model for deep neural networks,” in Proc. Int. Conf. on Learning Representations (ICLR), 2016.
  41. X. Chen, D. Z. Chen, Y. Han, and X. S. Hu, “moDNN: Memory Optimal Deep Neural Network Training on Graphics Processing Units,” in IEEE Trans. Parallel Distrib. Syst., vol. 30, no. 3, pp. 646–661, 2019.
  42. D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv preprint arXiv:1412.6980, Dec. 2014.
  43. Y. Yao, L. Rosasco, and A. Caponnetto, “On Early Stopping in Gradient Descent Learning,” Tech. Rep., Sept. 2005.

Issue

IEEE Sensors Journal, 2026, United States, https://doi.org/10.1109/JSEN.2026.3658247

Copyright IEEE

Вид: статия в списание, публикация в издание с импакт фактор, публикация в реферирано издание, индексирана в Scopus