Comparative Evaluation of STFT–Random Forest and Fuzzy STFT– SVM Frameworks for Robust Spectrum Sensing Using QPSK I/Q Data
Abstract
The current work exhibits an overview involving the comparison of two different machine learning–based spectrum sensing pipelines which make use of Quadrature Phase-Shift Keying (QPSK) in-phase/quadrature (I/Q) data generated in GNU Radio. The two pipelines share as common the Short-Time Fourier Transform (STFT)–based spectral features along with pseudo-labeling taken from energy detection. Direct handling of raw STFT features by a Random Forest (RF) model is the first pipeline. The second pipeline on the contrary, integrates a fuzzy feature engineering phase where STFT features are altered with neuro-fuzzy processing before being passed to classification with a Support Vector Machine (SVM) technique that is referred to as the Fuzzy STFT–SVM (FuST-SVM) framework. The different methodical tests are carried out when the signal-to-noise ratio (SNR) is low (−10 dB), medium (5 dB), and high (10 dB). The outcome shows that the FuST-SVM pipeline is the one that always has the superiority over the RF-based method that even reaches the highest 92.46% in accuracy measurement through the tested SNR levels from 90.65% to 92.46%. The studies support that the utilization of fuzzy spectral representations in spectrum sensing improves the noise and uncertainty handling in the proposed FuST-SVM framework that it becomes an evenly efficient and dependable solution for wireless environments that are challenging.References
JMitola III, "Cognitive radio: An integrated agent architecture for software defined radio," Ph.D. dissertation, KTH Royal Institute of Technology, Stockholm, Sweden, 2000.
S. Haykin, "Cognitive radio: brain-empowered wireless communications," IEEE Journal on Selected Areas in Communications, vol. 23, no. 2, pp. 201–220, Feb. 2005.
R. T. B. de Souza, C. R. C. M. da Silva, and J. M. N. da Silva, "Energy detection for spectrum sensing in cognitive radio: A review," Journal of Communication and Information Systems, vol. 30, no. 1, pp. 43-53, 2015
J. G. Proakis and D. G. Manolakis, Digital Signal Processing: Principles, Algorithms and Applications. Pearson Education, 4th ed., 2007.
M. Polydorou and G. P. Koundourakis, "Machine learning techniques for spectrum sensing in cognitive radio networks: A survey," Wireless Networks, vol. 26, no. 1, pp. 605-625, Jan. 2020.
X. Li, Q. Zhang, S. Zhang, and X. Yuan, "Spectrum sensing based on support vector machine in cognitive radio," in Proc. IEEE International Conference on Communication Technology (ICCT), Chengdu, China, Nov. 2011, pp. 696-699.
M. H. Arshad, F. Khan, and M. W. Akbar, "Fuzzy logic based adaptive threshold for energy detection in cognitive radio," in Proc. IEEE International Conference on Communication Technologies (ICCT), Rawalpindi, Pakistan, Apr. 2014, pp. 416-420.
A. R. S. Al-ali and B. S. Al-Jubouri, "Wavelet transform based features for spectrum sensing in cognitive radio," Iraqi Journal of Science, vol. 59, no. 4A, pp. 1913-1922, 2018.
B. K. Al-Ani, A. H. R. Al-Obaidi, and A. H. Al-Shamma, "Spectrum sensing using hybrid feature extraction and machine learning classifiers for cognitive radio networks," Journal of Engineering and Applied Sciences, vol. 12, no. 2, pp. 317-323, 2017.
M. T. Islam, K. S. Hasan, M. A. Hasan, and M. R. Karim, "Performance analysis of random forest classifier for spectrum sensing in cognitive radio networks," in Proc. IEEE International Conference on Electrical, Computer and Communication Engineering (ECCE), Cox's Bazar, Bangladesh, Feb. 2019, pp. 1-6.
Z. M. Hameed and A. H. Mohammed, "A novel approach for spectrum sensing based on neuro-fuzzy system in cognitive radio networks," Journal of Physics: Conference Series, vol. 1879, no. 2, p. 022026, 2021.
Y. Sun, J. Yang, M. E. Z. Xu, and Y. Wang, "Deep learning for intelligent spectrum sensing: A survey," IEEE Communications Surveys & Tutorials, vol. 23, no. 2, pp. 1162-1191, Second Quarter 2021.
C. C. Hung, S. H. Wu, and C. C. Fan, "Cyclostationarity-based spectrum sensing with machine learning for cognitive radio," Sensors, vol. 20, no. 18, p. 5202, Sep. 2020.
D. J. G. Blazquez, C. E. E. D. G. de Dios, and J. M. V. Guerrero, "A novel statistical feature extraction method for spectrum sensing in cognitive radio," Wireless Personal Communications, vol. 109, no. 1, pp. 605-620, Nov. 2019.
L. H. Qureshi, N. U. H. Khattak, and N. M. K. Khattak, "Energy-efficient cooperative spectrum sensing based on machine learning for cognitive radio networks," International Journal of Communication Systems, vol. 35, no. 5, p. e4923, Apr. 2022.
J. P. E. G. Silva and J. B. Marques, "Machine learning approaches for dynamic spectrum access in cognitive radio: A review," Journal of Network and Computer Applications, vol. 175, p. 102924, Mar. 2021.
H. Y. Fu, W. H. Fan, J. L. Zhang, and X. N. Zhang, "Spectrum sensing with fuzzy-logic-based adaptive thresholding for cognitive radio networks," in Proc. IEEE Global Telecommunications Conference (GLOBECOM), Washington, DC, USA, Dec. 2016, pp. 1-6.
S. H. Kim, J. H. Park, and D. G. Kim, "Feature extraction using higher-order cumulants for robust spectrum sensing in cognitive radio," Journal of Electrical Engineering & Technology, vol. 14, no. 4, pp. 1795-1801, July 2019.
K. W. K. K. M. O. H. H. Al-Shaikh and L. B. M. Al-Hajji, "Spectrum sensing performance of SVM classifier with different kernel functions for cognitive radio," International Journal of Computer Networks and Communications, vol. 10, no. 6, pp. 31-41, Nov. 2018
M. R. N. M. Azlan, S. M. Razali, and M. R. Hassan, "Performance of naive Bayes classifier for spectrum sensing in cognitive radio," in Proc. IEEE 10th International Conference on Telecommunication Systems, Services, and Applications (TSSA), Bali, Indonesia, Oct. 2016, pp. 1-5.
Reddy DN, Priyanka R, Sanjana S, Santrupti MB, Sadiya S. Machine learning algorithms for detection: A survey and classification. Turkish Journal of Computer and Mathematics Education. 2021;12(10):3468-74.
Du J, Wang X, Zhang H. Secure Power Management in Wireless Sensor Networks for Power Monitoring Using Deep Reinforcement Learning. Informatica. 2025 Apr 7;49(19).
Xiang S, Gan R. A Machine Learning-Based Approach to Cross-Application of Computer Vision and Visual Communication Design for Automatic Labelling and Classification. Informatica. 2025 Jan 31;49(6).
DOI:
https://doi.org/10.31449/inf.v50i1.12154Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
