International Journal of Computer Networks and Applications

Open Access Open Access  Restricted Access Subscription Access

Performance Evaluation of the K-Means-LSTM Hybrid Model for Optimization of Spectrum Sensing in Cognitive Radio Networks


Affiliations
1 Department of Computer Science, University of Fort Hare, Alice, Eastern Cape, South Africa
2 Department of Applied Informatics, Walter Sisulu University, East London, Eastern Cape, South Africa
 

CR (cognitive radio) technology has become an attractive field of research owing to the increased demand for spectrum resources. One of the duties of this technology is spectrum sensing which involves the opportunistic identification of vacant frequency bands for occupation by unlicensed users. Various traditional and state of art Machine-Learning algorithms have been proposed for sensing these vacant frequency bands. However, the common drawbacks of the proposed traditional techniques are degraded performance at low signal-to-noise ratios (SNR) as well as the requirement for prior information about the licensed user signal characteristics. More so, several Machine-Learning / Deep Learning techniques depend on simulated, supervised, and static (batch) spectrum datasets with synthesized features, which is not the case with real-world networks. Hence, this study aims to optimize real-time and dynamic spectrum sensing in wireless networks by establishing and evaluating a K-means-LSTM novice model (artifact) that is robust to low SNR and doesn’t require a supervised spectrum dataset. Firstly, the unsupervised spectrum dataset was collected by an RTL-SDR dongle and labelled by the K-means algorithm in MATLAB. The labelled spectrum dataset was utilized for training the LSTM algorithm. The resultant LSTM model’s performance was evaluated and compared to other commonly used spectrum detection models. Findings revealed that the proposed model established from the K-Means and LSTM algorithms yielded a Pd (detection probability) of 94%, Pfa (false-alarm probability) of 71%, and an accuracy of 97% at low SNR such as -20 dB, a performance which was superior to other models' performance. Using our proposed model, it is possible to optimize real-time spectrum sensing at low SNR without a prior supervised spectrum dataset.

Keywords

Spectrum Sensing, Cognitive Radio, K-Means-LSTM, SNR, Signal–to–Noise Ratio, Detection Probability, Pfa (False-Alarm Probability), Optimization.
User
Notifications
Font Size

  • ITU/UNESCO Broadband Commission, 2019. The State of Broadband: Broadband as a Foundation for Sustainable Development. September 2019.

  • Sutherland, E., 2021, October. Telecommunications in South Africa: enforcement of competition. In Competition Commission and Competition Tribunal 15th Annual Competition Conference (pp. 20-22).

  • Arjoune, Y. and Kaabouch, N., 2019. A comprehensive survey on spectrum sensing in cognitive radio networks: Recent advances, new challenges, and future research directions. Sensors, 19(1), p.126.

  • Rwodzi, M.J., 2016. Energy-detection-based spectrum sensing for cognitive radio on a real-time SDR platform (Master's thesis, University of Cape Town).

  • Tamuka, N. and Sibanda, K. (2023) ‘A bibliometric analysis on Spectrum Sensing in wireless networks’, Indian Journal of Computer Science and Engineering, 14(3), pp. 500–518. doi:10.21817/indjcse/2023/v14i3/231403065.

  • Sherbin, K. and Sindhu, V., 2019, May. Cyclostationary feature detection for spectrum sensing in the cognitive radio network. In 2019 International Conference on Intelligent Computing and Control Systems (ICCS) (pp. 1250-1254). IEEE.

  • Dibal, P.Y., Onwuka, E.N., Agajo, J. and Alenoghena, C.O., 2018. Application of wavelet transform in spectrum sensing for cognitive radio: A survey. Physical Communication, 28, pp.45-57.

  • Luo, J., Zhang, G. and Yan, C., 2022. An energy detection-based spectrum-sensing method for cognitive radio. Wireless Communications and Mobile Computing, 2022.

  • Salama, U., Sarker, P.L. and Chakrabarty, A., 2018, June. Enhanced energy detection using matched filter for spectrum sensing in cognitive radio networks. In 2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR) (pp. 185-190). IEEE.

  • Salahdine, F., El Ghazi, H., Kaabouch, N. and Fihri, W.F., 2015, October. Matched filter detection with dynamic threshold for cognitive radio networks. In 2015 international conference on wireless networks and mobile communications (WINCOM) (pp. 1-6). IEEE.

  • Patil, V., Yadav, K., Roy, S.D. and Kundu, S., 2017, March. Hybrid cooperative spectrum sensing with cyclostationary detector and improved energy detector for cognitive radio networks. In 2017 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) (pp. 1353-1357). IEEE.

  • Zheng, S., Chen, S., Qi, P., Zhou, H. and Yang, X., 2020. Spectrum sensing based on deep learning classification for cognitive radios. China Communications, 17(2), pp.138-148.

  • Kaur, R. and Sharma, S., 2017. A Research on Non-Cooperative Hybrid Spectrum Sensing Technique. International Journal of Electronics and Communication Engineering and Technology, 8(1).

  • Rajaguru, R., Devi, K.V. and Marichamy, P., 2020. A hybrid spectrum sensing approach to select suitable spectrum bands for cognitive users. Computer Networks, 180, p.107387.

  • Tamilselvi, T. and Rajendran, V., 2023. Comparative Study of SVM and KNN Machine Learning Algorithm for Spectrum Sensing in Cognitive Radio. In Intelligent Communication Technologies and Virtual Mobile Networks (pp. 517-527). Springer, Singapore.

  • Xie, J., Fang, J., Liu, C. and Li, X., 2020. Deep learning-based spectrum sensing in cognitive radio: A CNN-LSTM approach. IEEE Communications Letters, 24(10), pp.2196-2200.

  • Sinaga, K.P. and Yang, M.S., 2020. Unsupervised K-means clustering algorithm. IEEE access, 8, pp.80716-80727.

  • Biswal, A. (2022) Recurrent neural network (RNN) tutorial: Types and examples [updated]: Simplilearn, Simplilearn.com. Available at: https://www.simplilearn.com/tutorials/deep-learning-tutorial/rnn (Accessed: 21 May 2023).

  • Soni, B., Patel, D.K. and López-Benítez, M., 2020. Long short-term memory based spectrum sensing scheme for cognitive radio using primary activity statistics. IEEE Access, 8, pp.97437-97451.

  • Yuan, C. and Yang, H., 2019. Research on the K-value selection method of the K-means clustering algorithm. J, 2(2), pp.226-235.

  • Vabalas, A., Gowen, E., Poliakoff, E. and Casson, A.J., 2019. Machine learning algorithm validation with a limited sample size. PloS one, 14(11), p.e0224365.

  • Tamuka, N. and Sibanda, K., 2020, November. Real-time customer churn scoring model for the telecommunications industry. In 2020 2nd International Multidisciplinary.

  • Zheng, S., Chen, S., Qi, P., Zhou, H. and Yang, X., 2020. Spectrum sensing based on deep learning classification for cognitive radios. China Communications, 17(2), pp.138-148

  • Wang, Q. and Guo, B., 2022, December. CNN-SVM Spectrum Sensing in Cognitive Radio Based on Signal Covariance Matrix. In Journal of Physics: Conference Series (Vol. 2395, No. 1, p. 012052). IOP Publishing.

  • Arshid, K., Jianbiao, Z., Hussain, I., Pathan, M.S., Yaqub, M., Jawad, A., Munir, R. and Ahmad, F., 2022. Energy efficiency in cognitive radio network using cooperative spectrum sensing based on hybrid spectrum handoff. Egyptian Informatics Journal, 23(4), pp.77-88.

  • Soni, B., Patel, D.K. and López-Benítez, M., 2020. Long short-term memory based spectrum sensing scheme for cognitive radio using primary activity statistics. IEEE Access, 8, pp.97437-97451.

  • Cheng, Q., Shi, Z., Nguyen, D.N. and Dutkiewicz, E., 2018. Deep learning network-based spectrum sensing methods for OFDM systems. arXiv preprint arXiv:1807.09414.


Abstract Views: 160

PDF Views: 1




  • Performance Evaluation of the K-Means-LSTM Hybrid Model for Optimization of Spectrum Sensing in Cognitive Radio Networks

Abstract Views: 160  |  PDF Views: 1

Authors

Nyashadzashe Tamuka
Department of Computer Science, University of Fort Hare, Alice, Eastern Cape, South Africa
Khulumani Sibanda
Department of Applied Informatics, Walter Sisulu University, East London, Eastern Cape, South Africa

Abstract


CR (cognitive radio) technology has become an attractive field of research owing to the increased demand for spectrum resources. One of the duties of this technology is spectrum sensing which involves the opportunistic identification of vacant frequency bands for occupation by unlicensed users. Various traditional and state of art Machine-Learning algorithms have been proposed for sensing these vacant frequency bands. However, the common drawbacks of the proposed traditional techniques are degraded performance at low signal-to-noise ratios (SNR) as well as the requirement for prior information about the licensed user signal characteristics. More so, several Machine-Learning / Deep Learning techniques depend on simulated, supervised, and static (batch) spectrum datasets with synthesized features, which is not the case with real-world networks. Hence, this study aims to optimize real-time and dynamic spectrum sensing in wireless networks by establishing and evaluating a K-means-LSTM novice model (artifact) that is robust to low SNR and doesn’t require a supervised spectrum dataset. Firstly, the unsupervised spectrum dataset was collected by an RTL-SDR dongle and labelled by the K-means algorithm in MATLAB. The labelled spectrum dataset was utilized for training the LSTM algorithm. The resultant LSTM model’s performance was evaluated and compared to other commonly used spectrum detection models. Findings revealed that the proposed model established from the K-Means and LSTM algorithms yielded a Pd (detection probability) of 94%, Pfa (false-alarm probability) of 71%, and an accuracy of 97% at low SNR such as -20 dB, a performance which was superior to other models' performance. Using our proposed model, it is possible to optimize real-time spectrum sensing at low SNR without a prior supervised spectrum dataset.

Keywords


Spectrum Sensing, Cognitive Radio, K-Means-LSTM, SNR, Signal–to–Noise Ratio, Detection Probability, Pfa (False-Alarm Probability), Optimization.

References





DOI: https://doi.org/10.22247/ijcna%2F2023%2F223421