Modulation Scheme Classification in Cognitive Radio Networks Using the Long Short Term Memory (LSTM) of Deep Learning



Abstract Views
681

Downloads
432

Citations

Share

##plugins.themes.bootstrap3.article.sidebar##

Submitted Feb 4, 2022
Published Mar 4, 2022
10.24018/ejeng.2022.7.2.2739

Abstract viewed = 681 times

Table of Contents

##plugins.themes.bootstrap3.article.main##

Cognitive Radio (CR) system has been adopted for efficient utilization of radio frequency spectrum. The classification of signal modulation schemes is one of the main characteristics of the CR for appropriate demodulation of sensed signals. However, conventional Modulation Classification (MC) techniques require extensive extraction of signal features, which is not often guaranteed. Thus, Deep Learning (DL) has been seen as a promising solution to this drawback in MC. This paper proposes a DL-based MC technique using the Long Short-Term Memory (LSTM) network architecture. The proposed LSTM model was trained on M-ary Phase Shift Keying (MPSK) and M-ary Quadrature Amplitude Modulation (MQAM) signal types. The LSTM directly learns the features of a given modulation scheme of a signal sample during training. The signal samples were generated via computer simulation for Signal-to-Noise Ratios (SNRs) from -10 dB to 20 dB with an interval of 5 dB over flat fading channel and Additive white Gaussian noise (AWGN). Simulation results show that the proposed LSTM model achieves an average classification accuracy of 95% at SNRs above 0 dB.

Keywords: Cognitive Radio (CR), Deep Learning (DL), Long Short-Term Memory (LSTM), Modulation Classification (MC)

Downloads

Download data is not yet available.

References

  1. Mardani MR, Ghanbari M. Mohebi S. Energy and latency-aware scheduling under channel uncertainties in LTE networks for massive IoT. Wireless Personal Communications. 2018 Dec 17; 103(3):2137-2154.
     Google Scholar
  2. Yang K-P, McDowell P, Devkota P, Pradhan S, Bhandari R, Madewell Z. Detecting gas leaks: a case study in IoT technologies. European Journal of Engineering and Technology Research. 2021; 6(7):103-106.
     Google Scholar
  3. Salam AO. Adaptive coded modulation classification and spectrum sensing for cognitive radio systems. Ph.D. Thesis. University of Bradford; 2018.
     Google Scholar
  4. Elias FGM, Fernández EMG. An analysis of energy detector based on improved approximations of the chi?square distributions. J Wireless Com Network. 2021; 44(2021): 1-18. doi: 10.1186/s13638?021?01915?5.
     Google Scholar
  5. Bahloul MR, Yusoff MZ, Abdel-Aty A-H, Saad MNM, Kudsi L. Spectrum sensing for cognitive radio systems using modulation classification: a review. Appl. Math. Inf. Sci. 2017 May 1; 11(3):857-865.
     Google Scholar
  6. Al-Nuaimi DH, Hashim IA, Abidin ISZ, Salman LB, Isa NAM. Performance of feature-based techniques for automatic digital modulation recognition and classification — a review. Electronics. 2019 Nov 26; 8(1407):2-25. doi: 10.3390/electronics8121407.
     Google Scholar
  7. Kharbech S, Dayoub I, Colin MZ, Simon EP. On classifiers for blind feature-based automatic modulation classification Over Multiple-Input Multiple-Output Channels. IET Communications. 2016; 10(7):790-795.
     Google Scholar
  8. Le B, Rondeau TW, Bostian CW. Modulation identification using neural networks for cognitive radios. Software Defined Radio Forum Technical Conference; 2005.
     Google Scholar
  9. Abu-Romoh M, Aboutaleb A, Rezki Z. Automatic modulation classification using moments and likelihood maximization. IEEE Communications Letters. 2018; 1(1):1-4. doi: 10.1109/lcomm.2018.2806489.
     Google Scholar
  10. Abdelbar M, Tranter B, Bose T. Cooperative modulation classification of multiple signals in cognitive radio networks. Proceedings of the IEEE ICC 2014 - Cognitive Radio and Networks Symposium. pp. 1483-1488, Sydney, Australia, Jun 2014. doi: 10.1109/ICC.2014.6883531.
     Google Scholar
  11. Ahmed AG. Automatic modulation recognition based on artificial neural networks over wireless fading channel in cognitive radio. International Journal of Advanced Computational Engineering and Networking. 2017 Oct 17; 5(10):5-8.
     Google Scholar
  12. Sun X, Su S, Zuo Z, Guo X, Tan X. Modulation classification using compressed sensing and decision tree–support vector machine in cognitive radio system. Sensors. 2020 Mar 6; 20(1438):2-16. doi: 10.3390/s20051438.
     Google Scholar
  13. Salam AOA, Sheriff RE, Al-Araji SR, Mezher K, Nasir Q. Automatic modulation classification in cognitive radio using multiple antennas and maximum-likelihood techniques. Proceedings of the 2015 IEEE International Conference on Computer and Information Technology; Liverpool, UK. 2015. doi: 10.1109/CIT/IUCC/DASC/PICOM.2015.3
     Google Scholar
  14. Ghauri SA, Qureshi IM, Shah I, Khan N. Modulation classification using cyclostationary features on fading channels. Research Journal of Applied Sciences, Engineering and Technology. 2014 Jun 25; 7(24):5331-5339. doi: 10.19026/rjaset.7.932.
     Google Scholar
  15. Zhang T, Shuai C, Zhou Y. Deep learning for robust automatic modulation recognition method for IoT applications. IEEE Access. 2020; 8(1):117689–117697.
     Google Scholar
  16. Zhou S, Yin Z, Wu Z, Chen Y, Zhao N, Yang Z. A robust modulation classification method using convolutional neural networks. EURASIP Journal on Advances in Signal Processing. 2019; 21(1):1-15. doi: 10.1186/s13634-019-0616-6.
     Google Scholar
  17. Ajayi OO, Badrudeen AA, Oyedeji AI. Deep learning based spectrum sensing technique for smarter cognitive radio networks. Journal of Inventive Engineering and Technology (JIET). 2021 Sep 23; 1(5):64-77.
     Google Scholar
  18. Wang Y, Liu M, Yang J, Gui G. Data-driven deep learning for automatic modulation recognition in cognitive radios. IEEE Trans. Veh. Technol. 2019 Feb 20; 68(4):4074–4077.
     Google Scholar
  19. Zheng S, Qi P, Chen S, Yang X. Fusion methods for CNN-based automatic modulation classification. IEEE Access. 2019 May 22; 7(2019):66496-66504. doi 10.1109/ACCESS.2019.2918136.
     Google Scholar
  20. Kim SH, Kim JW, Nwadiugwu WP, Kim DS. Deep learning-based robust automatic modulation classification for cognitive radio networks. IEEE Access. 2021 Jul 5; 9(2021):92386-92393.
     Google Scholar
  21. Lin R, Ren W, Sun X, Yang Z, Fu K. A hybrid neural network for fast automatic modulation classification. IEEE Access. 2020 Jul 27; 8(2021):130314–130322.
     Google Scholar
  22. Zhu X. Studies on modulation classification in cognitive radios using machine learning. Ph.D. Thesis. The University of Electro-Communications; 2017.
     Google Scholar
  23. Clement JC, Indira N, Vijayakumar P, Nandakumar R. Deep learning based modulation classi?cation for 5G and beyond wireless systems. Peer-to-Peer Networking and Applications. 2021 Jan 1; 14(1): 319-332. doi: 10.1007/s12083-020-01003-3.
     Google Scholar
  24. Gers FA, Schmidhuber J, Cummins F. Learning to forget: Continual prediction with LSTM. Neural Computation. 2000; 12(10):2451–2471.
     Google Scholar