Derin Öğrenme Modeli ile Ortogonal Frekans Bölmeli Çoklama Modülasyonlu Sinyallerin Tanımlanması

Abstract

Sinyal modülasyonu tanımlama, öncelikli alanlarda yayın yapmak için belirli ortogonal frekans bölmeli çoklama sinyal modellerini tanımlayarak güvenilir bir bölge elde etmek için 5G ve ötesi sistemlerde çok önemli bir rol oynar. Bununla birlikte, sinyallerin özelliklerinin çıkarılması nedeniyle geleneksel yöntemlerde sınırlı bir darboğaz vardır. Önerilen yöntemde, BPSK+BPSK, BPSK+8PSK, BPSK+QPSK, QPSK+BPSK, QPSK+8PSK, QPSK+QPSK olmak üzere altı farklı modüle edilmiş sinyalden yalnızca 10 bitlik verilerle farklı sinyal-gürültü oranı seviyelerinde derin öğrenme tabanlı bir frekans ayrıştırma çözümü kullanılmıştır. Sinyallerin özellikleri, düşük, orta ve yüksek frekans aşamalarında çok değişkenli varyasyonel mod ayrıştırma yöntemiyle sinyal ayrıştırmasından sonra elde edildi. Yöntem, açık erişimli ortogonal frekans bölmeli çoklama veri seti (DOI:10.21227/xwk3-t431) ile doğrulandı. Deneysel sonuçlar, önerilen modelin daha yüksek doğruluk ve iyi tutarlılık sağladığını göstermektedir. Bu, sinyal frekans özelliklerinin çıkarılması ve derin öğrenme yöntemleri konusunda bir sınıflandırma yaklaşımı sağlar. Bu sonuç, güvenli iletişim kanalı için yeni bir güvenlik katmanı eklemeyi mümkün kılmaktadır.

Keywords

• Sinyal İşleme
• Ortogonal Frekans Bölmeli Çoklama Modülasyonu
• Çok Değişkenli Varyasyonel Mod Ayrıştırması ile Özellik Çıkarma
• Derin Öğrenme Modeli ile Sınıflandırma

Ethical Statement

Hazırlanan makale için etik kurulundan izin alınmasına gerek yoktur.

Identification of Orthogonal Frequency-Division Multiplexing Modulated Signals with Deep Learning Model

Abstract

Signal modulation identification plays a crucial role in 5G and beyond systems to obtain a reliable zone by defining certain orthogonal frequency division multiplexing signal patterns for broadcasting in priority areas. However, there is a limited bottleneck traditional methods because of the extracting the features of the signals. In the proposed method, a deep learning-based frequency decomposition solution were used at different signal-to-noise ratio levels with only 10-bit data from six different modulated signals which are BPSK+BPSK, BPSK+8PSK, BPSK+QPSK, QPSK+BPSK, QPSK+8PSK, QPSK+QPSK. The features of the signals were obtained after signal decomposition with the multivariate variational mode decomposition method in low, medium and high frequency stages. The method was validated with an open access orthogonal frequency division multiplexing dataset (DOI:10.21227/xwk3-t431). Experimental results show that the proposed model provides higher accuracy and good consistency. This provides a classification stand on the extraction of signal frequency characteristics and deep learning methods. This result makes it possible to add a new layer of security for the safety communication channel.

Keywords

• Signal Processing
• Orthogonal Frequency Division Multiplexing Modulation
• Feature Extraction with Multivariate Variational Mode Decomposition
• Classification with Deep Learning Model

Ethical Statement

There is no need to obtain permission from the ethics committee for the article prepared.

References

1. [1] Á. E. Ruiz-García, C. A.Gutierrez,, J. Cortez, , E. Ruiz-Ibarra and J. Vázquez-Castillo, “SDR-Based Wideband Emulator of Non-WSSUS Channels for Vehicular Communications,” Circuits, Systems, and Signal Processing, vol. 41, no. 7, pp.3832-3852, 2022, 10.1007/s00034-022-01958-z.
2. [2] L.Xue and C. Yang, “Copying and Recreation Methods of Painting Works Relying on Mobile Digital Multimedia Big Data Analysis,” Computational Intelligence and Neuroscience, vol. 2022, no. 1, pp. 7734506, 2022, 10.1155/2022/7734506
3. [3] T.Huynh-The, T. V. Nguyen, Q. V. Pham,, D. B.da Costa, G. H. Kwon and D. S. Kim, “Efficient Convolutional Networks for Robust Automatic Modulation Classification in OFDM-Based Wireless Systems,” IEEE Systems Journal, vol. 17, no. 1, 964-975, 2022, 10.1109/JSYST.2022.3207377
4. [4] M. C. Park and D. S. Han, “Deep Learning-Based Automatic Modulation Classification with Blind OFDM Parameter Estimation,” IEEE Access, vol. 9, pp. 108305-108317, 2021, 10.1109/ACCESS.2021.3102223.
5. [5] M.Jadhav, V. Deshpande, D. Midhunchakkaravarthy, and D. Waghole, “Improving 5G network performance for OFDM-IDMA system resource management optimization using bio-inspired algorithm with RSM,” Computer Communications, vol. 193, pp. 23-37,2022, 10.1016/j.comcom.2022.06.031.
6. [6] Z.An, T. Zhang, B. Ma and Y. Xu, “A Two-Stage High-Order Modulation Recognition Based on Projected Accumulated Constellation Vector in Non-Cooperative B5G OSTBC-OFDM Systems,” Signal Processing, vol. 200, pp.108673, 2022, 10.1016/j.sigpro.2022.108673.
7. [7] M. S. Kumar, R. Ramanathan and M. Jayakumar, “Key less physical layer security for wireless networks: A survey,” Engineering Science and Technology, an International Journal, vol. 35, pp. 101260, 2022, 10.1016/j.jestch.2022.101260.
8. [8] D.Preethi and R. S. Valarmathi, “A Novel Energy-Efficient MIMO-OFDM Decoder Architecture with Error Detection,” IETE Journal of Research, vol. 69, no. 4, pp. 1974-1984, 2021, 10.1080/03772063.2021.1880340.

9. [9] Y. Xie, K. C. The and A. C. Kot, “Deep learning-based joint detection for OFDM-NOMA scheme,” IEEE Communications Letters, vol. 25, no. 8, pp. 2609-2613, 2021, 10.1109/LCOMM.2021.3077878.
10. [10] X.Wang, S.Ju, X. Zhang, S. Ramjee and A. El Gamal, “Efficient training of deep classifiers for wireless source identification using test snr estimates,” IEEE Wireless Communications Letters, vol. 9, no. 8, pp. 1314-1318, 2020, 10.1109/LWC.2020.2989286.
11. [11] M. W. Aslam, Z. Zhu and A. K. Nandi, “Automatic modulation classification using combination of genetic programming and KNN,” IEEE Transactions on Wireless Communications, vol. 11, no. 8, pp. 2742-2750, 2012, 10.1109/TWC.2012.060412.110460.
12. [12] A. Ali and F. Yangyu, “Automatic modulation classification using principle composition analysis based features selection,” In 2017 IEEE Computing Conference, London, United Kingdom, 2017, pp. 294-296.
13. [13] S. Soni, R. Makkar, D. Rawal and N. Sharma, “Performance of Selective DF Based Multiple Relayed NOMA System with Imperfect CSI and SIC Errors,” IEEE Transactions on Green Communications and Networking. Vol. 8, no. 1, pp. 79-89, 2023, 10.1109/TGCN.2023.3319082.
14. [14] X. Liu, D. Yang and A. El Gamal, “Deep neural network architectures for modulation classification,” in 2017 IEEE 51st Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2017, pp. 915-919.
15. [15] M. Zhang, Y. Zeng, Z. Han and Y. Gong, “Automatic modulation recognition using deep learning architectures,” in 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications, Kalamata, Greece, 2018, pp. 1-5.
16. [16] T.Cui, D. Wang, L. Ji, J. Han and Z. Huang, “Time and phase features network model for automatic modulation classification,” Computers and Electrical Engineering, vol. 111, pp. 108948, 2023, https://doi.org/10.1016/j.compeleceng.2023.108948
17. [17] L. Chong, “OFDM modulation classification dataset,” IEEE Dataport. https://dx.doi.org/10.21227/xwk3-t431, Access Date:19.01.2026.
18. [18] N. ur Rehman and H. Aftab, “Multivariate variational mode decomposition,” IEEE Transactions on Signal Processing, vol. 67, no. 23, pp. 6039-6052, 2019, 10.1109/TSP.2019.2951223.
19. [19] S. Luo, B. Wei and L. Chen, “Multi-point deformation monitoring model of concrete arch dam based on MVMD and 3D-CNN,” Applied Mathematical Modelling, vol. 125, pp. 812-826, 2024, https://doi.org/10.1016/j.apm.2023.10.030.
20. [20] D. Li, Y. Wen, S. Xu, Q. Wang, R. Bai and J. Zhao, “EDChannel: channel prediction of backscatter communication network based on encoder-decoder,” Telecommunication Systems, vol. 81, no. 1, pp. 99-114, 2022, https://doi.org/10.1007/s11235-022-00929-8.
21. [21] A. Rostamian and J. G. O’Hara, “Event prediction within directional change framework using a CNN-LSTM model,” Neural Computing and Applications, vol. 34, no. 20, pp. 17193-17205, 2022, 10.1007/s00521-022-07687-3.
22. [22] M. Waqas, K. Kumar, A. A. Laghari, U. Saeed, M.M. Rind, A. A. Shaikh and A. Q. Qazi, “Botnet attack detection in Internet of Things devices over cloud environment via machine learning,” Concurrency and Computation: Practice and Experience, vol. 34, no. 4, pp. e6662, 2022, 10.1002/cpe.6662
23. [23] S. Hong, Y. Zhang, Y. Wang, H. Gu, G. Gui, and H. Sari, “Deep learning-based signal modulation identification in OFDM systems,” IEEE Access, vol. 7, pp. 114631-114638, 2019, 10.1109/ACCESS.2019.2934976.
24. [24] J. Kim, H. Ro, and H. Park, “Deep learning-based detector for dual mode OFDM with index modulation,” IEEE Wireless Communications Letters, vol. 10, no. 7, pp. 1562-1566, 2021, 10.1109/LWC.2021.3074433.
25. [25] G. Song, M. Jang and D. Yoon, “CNN-Based Automatic Modulation Classification in OFDM Systems,” in 2022 IEEE International Conference on Computer, Information and Telecommunication Systems, Piraeus, Greece 2022, pp.1-4, 10.1109/CITS55221.2022.9832989.
26. [26] X.Hu, W. Liu, and H. Huo, “An intelligent network traffic prediction method based on Butterworth filter and CNN-LSTM,” Computer Networks, vol. 240, pp. 110172, 2024, 10.1016/j.comnet.2024.110172.
27. [27] C. Hou, G. Liu, Q. Tian, Z. Zhou, L. Hua and Y. Lin, “Multi-signal Modulation Classification Using Sliding Window Detection and Complex Convolutional Network in Frequency Domain,” IEEE Internet of Things Journal. 9(19), 19438-19449, 2022, 10.1109/JIOT.2022.3167107.
28. [28] Z. Ge, H. Jiang, Y. Guo and J. Zhou, “Accuracy Analysis of Feature-Based Automatic Modulation Classification via Deep Neural Network,” Sensors, vol. 21, no. 24, pp.8252, 2021, 10.3390/s21248252.