Hybrid Neutral Architecture for Spectrum Sensing: A Comparative Study of CNN-LSTM and LSTM-DQN in Cognitive Radio Networks
Keywords:
Cognitive Radio Networks, Spectrum Sensing, Convolutional Neural Networks, Long Short-Term Memory, Deep Q-Networks, Deep Learning, Reinforcement LearningAbstract
Cognitive Radio Networks (CRNs) have been recognized as an enabler of dynamic spectrum access, aimed at mitigating spectrum underutilization by permitting unlicensed users to access idle licensed bands opportunistically. For such access to be reliable, accurate spectrum sensing is essential to avoid interference with primary users (PUs). In recent years, deep learning (DL) models have emerged as potent alternatives to traditional sensing methods due to their adaptability in noise-prone environments and high detection performance [1][4]. This paper presents a comparative analysis of three state-of-the-art deep learning architectures: Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Deep Q-Networks (DQNs). A review of their standalone capabilities, followed by the assessment of hybrid combinations such as CNN-LSTM and LSTM-DQN, is provided. The evaluation is supported through architectural illustrations, theoretical insights, and simulated benchmark results..
Downloads
References
J. Xie, J. Fang, C. Liu, and X. Li, “Deep Learning-Based Spectrum Sensing in Cognitive Radio: A CNN-LSTM Approach,” IEEE Commun. Lett., vol. 24, no. 10, pp. 2196–2200, 2020.
S. Solanki, V. Dehalwar, J. Choudhary, M. L. Kolhe, and K. Ogura, “Spectrum Sensing in Cognitive Radio Using CNN-RNN and Transfer Learning,” IEEE Access, vol. 10, pp. 113482–113490, 2022.
K. Wang, Y. Chen, D. Bo, and S. Wang, “A Novel Multi-user Collaborative Cognitive Radio Spectrum Sensing Model: Based on a CNN-LSTM Model,” PLOS ONE, vol. 20, no. 1, Jan. 2025.
S. E. Abdelbaset, H. M. Kasem, A. A. Khalaf, A. H. Hussein, and A. A. Kabeel, “Deep Learning-Based Spectrum Sensing for Cognitive Radio Applications,” Sensors, vol. 24, no. 24, p. 7907, Dec. 2024.
Y. Zhang and Z. Luo, “A Review of Research on Spectrum Sensing Based on Deep Learning,” Electronics, vol. 12, no. 21, p. 4514, 2023.
C. Li et al., “A Skipping Spectrum Sensing Scheme Based on Deep Reinforcement Learning for Transform Domain Communication Systems,” Scientific Reports, vol. 14, Article no. 1062, Apr. 2024.
X. Xing, H. Zhang, S. Li, and Y. Wang, “Cooperative Spectrum Sensing Based on LSTM-CNN Networks in CRNs,” IEEE Trans. Cogn. Commun. Netw., vol. 7, no. 4, pp. 1042–1053, Dec. 2021.
[8] M. Chen, U. Challita, W. Saad, C. Yin, and M. Debbah, “Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial,” IEEE Commun. Surveys Tuts., vol. 21, no. 4, pp. 3039–3071, 2019.
O. Yıldırım, “A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification,” Computers in Biology and Medicine, vol. 96, pp. 189–202, Mar. 2018, doi: 10.1016/j.compbiomed.2018.03.016.
B. Soni, D. K. Patel, and M. López-Benítez, “Long short-term memory based spectrum sensing scheme for cognitive radio using primary activity statistics,” IEEE Access, vol. 8, pp. 97437–97451, 2020, doi: 10.1109/ACCESS.2020.2995971.
B. M. Pati, M. Kaneko, and A. Taparugssanagorn, “A deep convolutional neural network based transfer learning method for non-cooperative spectrum sensing,” IEEE Access, vol. 8, pp. 164529–164545, 2020, doi: 10.1109/ACCESS.2020.3021835.
R. Zhou, F. Liu, and C. W. Gravelle, “Deep learning for modulation recognition: A survey with a demonstration,” IEEE Access, vol. 8, pp. 67366–67376, 2020, doi: 10.1109/ACCESS.2020.2986331.
.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
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 permits.
