Development of a Cyclostationary Spectrum Sensing Framework Using Deep Learning Techniques for Cognitive Radio Networks in mmWave Band

Nomfundo Vicky Masuku; Kibet Langat; Elijah Mwangi

doi:10.48084/etasr.18193

Authors

Nomfundo Vicky Masuku Department of Electrical Engineering, Pan African University Institute for Basic Sciences, Technology and Innovation, Nairobi, Kenya
Kibet Langat Department of Telecommunication and Information Engineering, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya
Elijah Mwangi Faculty of Engineering, University of Nairobi, Nairobi, Kenya

Volume: 16 | Issue: 3 | Pages: 36111-36118 | June 2026 | https://doi.org/10.48084/etasr.18193

Received: 15 February 2026 | Revised: 23 March 2026 and 2 April 2026 | Accepted: 3 April 2026 | Online: 6 May 2026

Corresponding author: Nomfundo Vicky Masuku

Abstract

Spectrum sensing is a fundamental component of Dynamic Spectrum Access (DSA) and Cognitive Radio (CR) technology. Accurate and rapid detection of signal presence is essential for the dynamic allocation of spectrum resources to specific devices. This capability is especially important in millimeter-Wave (mmWave) and wideband communication systems. These systems experience significant frequency-selective fading, severe multipath effects, and rapid signal variations over their wide bandwidths; therefore, reliable spectrum sensing methods are required. This paper proposes a spectrum sensing framework based on wavelet-derived cyclostationary feature extraction and a hybrid Convolutional Neural Network–Graph Neural Network (CNN-GNN) model. The extracted wavelet-based cyclostationary features are used to train a Multi-Layer Perceptron (MLP) for nonlinear feature learning. A CNN is trained to learn a time-frequency representation of the signals, whereas the GNN is used to learn both spatial and structural properties of the signals. The proposed model is compared with three different benchmark methods: energy detection, Cyclostationary Feature Detection (CFD) based on the Spectral Correlation Function (SCF), and a CNN-MLP baseline, across multiple evaluation metrics, including the probability of detection ( ), the probability of false alarm ( ), Area Under the Curve (AUC), accuracy, and runtime. Simulation results show that the proposed model achieves a above 0.95, an accuracy above 0.95, a below 0.05, and lower runtime than the other methods, demonstrating its effectiveness in supporting DSA and Software-Defined Access (SDA) in mmWave systems.

Keywords:

spectrum sensing, Cognitive Radio (CR), Cyclostationary Feature Detection (CFD), Convolutional Neural Network (CNN), Multi-Layer Perceptron (MLP), Graph Neural Network (GNN), probability of detection

Downloads

Download data is not yet available.

References

Nidhi, A. Mihovska, and R. Prasad, "Spectrum Sharing and Dynamic Spectrum Management Techniques in 5G and Beyond Networks: A Survey," Journal of Mobile Multimedia, vol. 17, no. 1–3, pp. 65–78, Jan. 2021.

J. John, M. Noor-A-Rahim, A. Vijayan, H. V. Poor, and D. Pesch, "Industry 4.0 and Beyond: The Role of 5G, WiFi 7, and Time-Sensitive Networking (TSN) in Enabling Smart Manufacturing," Future Internet, vol. 16, no. 9, Sept. 2024, Art. no. 345.

S. I. Loutfi, I. Shayea, U. Tureli, A. A. El-Saleh, and W. Tashan, "An overview of mobility awareness with mobile edge computing over 6G network: Challenges and future research directions," Results in Engineering, vol. 23, Sept. 2024, Art. no. 102601.

M. Maman et al., "Beyond private 5G networks: applications, architectures, operator models and technological enablers," EURASIP Journal on Wireless Communications and Networking, vol. 2021, no. 1, Dec. 2021, Art. no. 195.

A. Aijaz, "Private 5G: The Future of Industrial Wireless," IEEE Industrial Electronics Magazine, vol. 14, no. 4, pp. 136–145, Dec. 2020.

Framework and overall objectives of the future development of IMT for 2030 and beyond, Recommendation ITU-R M.2160-0, International Telecommunication Union Radiocommunication Sector (ITU-R), Geneva, Switzerland, Nov. 2023.

Service requirements for the 5G system, 3GPP TS 22.261 V17.10.0, 3rd Generation Partnership Project (3GPP), Sophia Antipolis, France, May 2022.

J. Mitola and G. Q. Maguire, "Cognitive radio: making software radios more personal," IEEE Personal Communications, vol. 6, no. 4, pp. 13–18, Aug. 1999.

S. Haykin, "Cognitive radio: brain-empowered wireless communications," IEEE Journal on Selected Areas in Communications, vol. 23, no. 2, pp. 201–220, Feb. 2005.

O. T. H. Alzubaidi, S. Alheejawi, M. N. Hindia, K. Dimyati, and K. A. Noordin, "Interference Mitigation Strategies in Beyond 5G Wireless Systems: A Review," Electronics, vol. 14, no. 11, June 2025, Art. no. 2237.

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, Dec. 2024, Art. no. 7907.

A. Kumar et al., "Cyclostationary and energy detection spectrum sensing beyond 5G waveforms," Electronic Research Archive, vol. 31, no. 6, pp. 3400–3416, 2023.

M. Nouri, H. Behroozi, N. K. Mallat, and S. A. Aghdam, "A Wideband 5G Cyclostationary Spectrum Sensing Method by Kernel Least Mean Square Algorithm for Cognitive Radio Networks," IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 68, no. 7, pp. 2700–2704, July 2021.

A. Xu, "Spectrum sensing based on deep learning with fading channels," M.S. thesis, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, 2024.

Y. Zhang and Z. Luo, "A Deep-Learning-Based Method for Spectrum Sensing with Multiple Feature Combination," Electronics, vol. 13, no. 14, July 2024, Art. no. 2705.

M. M. Bhavani, P. Balamurugan, V. N. Sankaran, S. Majumder, Rakshitha. L. P, and K. Nandagopal, "Spectrum Sensing Methodology Using Artificial Intelligence for Cognitive Radio Network," in 2025 First International Conference on Advances in Computer Science, Electrical, Electronics, and Communication Technologies, Bhimtal, Nainital, India, 2025, pp. 910–914.

T. Nawaz and A. Alzahrani, "Machine-Learning-Assisted Cyclostationary Spectral Analysis for Joint Signal Classification and Jammer Detection at the Physical Layer of Cognitive Radio," Sensors, vol. 23, no. 16, Aug. 2023, Art. no. 7144.

B. N. Getu, A. Al-Ataby, and H. Attia, "Deep Learning-Based Signal Classification in Wireless Fading Channels," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 30296–30303, Dec. 2025.

M. H. Abood and H. N. Abdullah, "Enhanced Cyclostationary Detector Complexity Based on Haar Wavelet and Signed Correlator," Mathematical Modelling of Engineering Problems, vol. 11, no. 7, pp. 1851–1858, June 2024.

S. Brody, U. Alon, and E. Yahav, "How Attentive are Graph Attention Networks?," in 10th International Conference on Learning Representations, Virtual Event, 2022.

A. Alkhateeb et al., "DeepSense 6G: A Large-Scale Real-World Multi-Modal Sensing and Communication Dataset," IEEE Communications Magazine, vol. 61, no. 9, pp. 122–128, Sept. 2023.