A Hybrid Deep Learning and Bagging Method for Automatic Modulation Recognition Utilizing Time-Frequency Data

Intisar K. Saleh

Intisar K. Saleh Technical Engineering College-Kirkuk, Northern Technical University

Keywords: Neural network, Deep learning, Modulation, Bagging method, Noise level.

Abstract

In satellite communications systems, submarine communications, and military communications, determining out the type of modulation is a crucial issue. A newly developed digital modulation classification model is introduced in this study to identify many types of modulated signals. At the first step, the density of specter for the frequencies accompanied with the modulation signals at the scalogram image is visually represented using continuous wavelet transform (CWT). Then, a deep convolutional neural network (CNN) is utilized to extract features from the scalogram pictures. The MRMR method is then used to get the best features. By decreasing the size of the features, the MRMR method improves classification speed and model interpretation. Using the group learning technique, the modulations are categorized in the fourth stage. Modulated signals with various levels of noise and SNRs ranging from 0 to 25 dB are taken into consideration in the simulations. The simulations' result shows that the suggested model outperforms other earlier research and functions effectively related to various noise levels.

References

D. Zhang, Y. Lu, Y. Li, et al., "Frequency learning attention networks based on deep learning for automatic modulation classification in wireless communication," Pattern Recognit., vol. 137, p. 109345, 2023.

S. Wei, Z. Sun, Z. Wang, et al., "An efficient data augmentation method for automatic modulation recognition from low-data imbalanced-class regime," Appl. Sci., vol. 13, p. 3177, 2023, doi: 10.3390/app13053177.

B. Jdid, K. Hassan, I. Dayoub, et al., "Machine learning based automatic modulation recognition for wireless communications: A comprehensive survey," IEEE Access, vol. 9, pp. 57851–57873, 2021, doi: 10.1109/ACCESS.2021.3071801.

W. Chen, Z. Xie, L. Ma, et al., "A faster maximum-likelihood modulation classification in flat fading non-Gaussian channels," IEEE Commun. Lett., vol. 23, pp. 454–457, 2019.

A. Krayani, A. S. Alam, M. Calipari, et al., "Automatic modulation classification in cognitive-IoT radios using generalized dynamic Bayesian networks," in Proc. 7th IEEE World Forum Internet Things (WF-IoT), pp. 235–240, 2021, doi: 10.1109/WF-IoT51360.2021.9594936.

P. Urriza, E. Rebeiz, P. Pawelczak, and D. Cabric, "Computationally efficient modulation level classification based on probability distribution distance functions," IEEE Commun. Lett., vol. 15, pp. 476–478, 2011, doi: 10.1109/LCOMM.2011.032811.110316.

M. R. Ismael, H. J. Abd, and M. T. Gatte, "Recognition of APSK digital modulation signal based on wavelet scattering transform," in Lecture Notes in Networks and Systems, Springer, pp. 469–478, 2022.

X. Wu, L. Lu, and M. Jiang, "Deep learning aided cyclostationary feature analysis for blind modulation recognition in massive MIMO systems," Digit. Signal Process., p. 103890, 2023.

X. Tan, Z. Xie, X. Yuan, et al., "Small sample signal modulation recognition based on higher-order cumulants and CatBoost," in Proc. 7th Int. Conf. Commun., Image Signal Process. (CCISP), IEEE, pp. 324–329, 2022.

Y. Liu and Y. Liu, "Modulation recognition with pre-denoising convolutional neural network," Electron. Lett., vol. 56, pp. 255–257, 2020, doi: 10.1049/el.2019.3586.

P. Ghasemzadeh, "A novel graph neural network-based framework for automatic modulation classification in mobile environments," 2023.

A. A. Salama, M. E. Morsy, S. H. Darwish, and E. I. Mohamed, "A novel SVM-based automatic modulation classifier," in Proc. Int. Telecommun. Conf. (ITC-Egypt), 2022, doi: 10.1109/ITC-Egypt55520.2022.9855683.

X. Sun, S. Su, Z. Zuo, et al., "Modulation classification using compressed sensing and decision tree–support vector machine in cognitive radio system," Sensors (Switzerland), vol. 20, 2020, doi: 10.3390/s20051438.

B. A. Alhadi, T. M. Hasan, and H. A. Hamed, "Digitally modulated signal recognition based on feature extraction optimization and random forest classifier," in New Trends Inf. Commun. Technol. Appl.: Proc. 4th Int. Conf. NTICT, Springer, pp. 75–84, 2020.

Y. Li, G. Hong, and C. Feng, "Application and effectiveness of weighted KNN in pattern recognition of communication modulated signals," in Proc. IEEE 4th Int. Conf. Civil Aviation Safety Inf. Technol. (ICCASIT), IEEE, pp. 744–748, 2022.

A. Kamble, P. H. Ghare, and V. Kumar, "Deep-learning-based BCI for automatic imagined speech recognition using SPWVD," IEEE Trans. Instrum. Meas., vol. 72, pp. 1–10, 2022.

S. Peng, L. Cao, Y. Zhou, et al., "A survey on deep learning for textual emotion analysis in social networks," Digit. Commun. Netw., vol. 8, pp. 745–762, 2022.

Z. Lingxin, S. Junkai, and Z. Baijie, "A review of the research and application of deep learning-based computer vision in structural damage detection," Earthq. Eng. Eng. Vib., vol. 21, pp. 1–21, 2022.

H. Tayakout, E. Boutellaa, and F. Z. Bouchibane, "On the robustness of digital modulation recognition for cooperative relaying networks under imperfect CSI," in Proc. 7th Int. Conf. Image Signal Process. Appl. (ISPA), IEEE, pp. 1–6, 2022.

C. T. Nguyen, N. Van Huynh, N. H. Chu, et al., "Transfer learning for wireless networks: A comprehensive survey," Proc. IEEE, 2022.

Z. Wang, P. Wang, and P. Lan, "Automatic modulation classification based on CNN, LSTM and attention mechanism," in Proc. IEEE 8th Int. Conf. Comput. Commun. (ICCC), IEEE, pp. 105–110, 2022.

Y. Wang, S. Fang, Y. Fan, and Z. Wang, "A CLSTM network algorithm for automatic modulation recognition," in Proc. Int. Conf. Signal Process., Comput. Netw., Commun. (SPCNC), SPIE, pp. 456–462, 2022.

N. Chakravarty, M. Dua, and S. Dua, "Automatic modulation classification using amalgam CNN-LSTM," in Proc. IEEE Radio Antenna Days Indian Ocean (RADIO), IEEE, pp. 1–2, 2023.

S. Hanna, C. Dick, and D. Cabric, "Signal processing-based deep learning for blind symbol decoding and modulation classification," IEEE J. Sel. Areas Commun., vol. 40, pp. 82–96, 2022, doi: 10.1109/JSAC.2021.3126088.

P. Ghasemzadeh, M. Hempel, and H. Sharif, "A robust graph convolutional neural network-based classifier for automatic modulation recognition," in Proc. Int. Wireless Commun. Mobile Comput. (IWCMC), IEEE, pp. 907–912, 2022.

C. Hou, G. Liu, Q. Tian, et al., "Multi-signal modulation classification using sliding window detection and complex convolutional network in frequency domain," IEEE Internet Things J., vol. 9, pp. 19438–19449, 2022, doi: 10.1109/JIOT.2022.3167107.

K. Liao, Y. Zhao, J. Gu, et al., "Sequential convolutional recurrent neural networks for fast automatic modulation classification," IEEE Access, vol. 9, pp. 27182–27188, 2021, doi: 10.1109/ACCESS.2021.3053427.

S. Huang, R. Dai, J. Huang, et al., "Automatic modulation classification using gated recurrent residual network," IEEE Internet Things J., vol. 7, pp. 7795–7807, 2020.

R. Utrilla, E. Fonseca, A. Araujo, and L. A. Dasilva, "Gated recurrent unit neural networks for automatic modulation classification with resource-constrained end-devices," IEEE Access, vol. 8, pp. 112783–112794, 2020, doi: 10.1109/ACCESS.2020.3002770.

Q. Zhou, X. Jing, Y. He, et al., "LSTM-based automatic modulation classification," in Proc. IEEE Int. Symp. Broadband Multimedia Syst. Broadcast. (BMSB), IEEE, pp. 1–4, 2020.

Y. Li, G. Shao, and B. Wang, "Automatic modulation classification based on bispectrum and CNN," in Proc. IEEE 8th Joint Int. Inf. Technol. Artif. Intell. Conf. (ITAIC), IEEE, pp. 311–316, 2019.

M. Patel, X. Wang, and S. Mao, "Data augmentation with conditional GAN for automatic modulation classification," in Proc. 2nd ACM Workshop Wirel. Secur. Mach. Learn. (WiseML), pp. 31–36, 2020, doi: 10.1145/3395352.3402622.

A. Jagannath and J. Jagannath, "Multi-task learning approach for automatic modulation and wireless signal classification," in Proc. IEEE Int. Conf. Commun. (ICC), 2021, doi: 10.1109/ICC42927.2021.9500447.

C. Hou, Y. Li, X. Chen, and J. Zhang, "Automatic modulation classification using KELM with joint features of CNN and LBP," Phys. Commun., vol. 45, p. 101259, 2021, doi: 10.1016/j.phycom.2020.101259.

A. H. Shah, A. H. Miry, and T. M. Salman, "Automatic modulation classification based deep learning with mixed feature," Int. J. Electr. Comput. Eng., vol. 13, pp. 1647–1653, 2023, doi: 10.11591/ijece.v13i2.pp1647-1653.

X. Fu, G. Gui, Y. Wang, et al., "Automatic modulation classification based on decentralized learning and ensemble learning," IEEE Trans. Veh. Technol., vol. 71, pp. 7942–7946, 2022, doi: 10.1109/TVT.2022.3164935.

D. Anandkumar and R. G. Sangeetha, "A survey on performance enhancement in free space optical communication system through channel models and modulation techniques," Springer US, 2021.

A. Nambisan, V. Gajjar, and K. Kosbar, "Scalogram aided automatic modulation classification," Int. Found. Telemetering, 2022.

O. Almanza-Conejo, D. L. Almanza-Ojeda, J. L. Contreras-Hernandez, and M. A. Ibarra-Manzano, "Emotion recognition in EEG signals using the continuous wavelet transform and CNNs," Neural Comput. Appl., vol. 35, pp. 1409–1422, 2023, doi: 10.1007/s00521-022-07843-9.

H. S. Ghanem, M. R. Shoaib, S. El‐Gazar, et al., "Automatic modulation classification with 2D transforms and convolutional neural network," Trans. Emerg. Telecommun. Technol., vol. 33, p. e4623, 2022.

B. Mirzaei, B. Nikpour, and H. Nezamabadi-pour, "CDBH: A clustering and density-based hybrid approach for imbalanced data classification," Expert Syst. Appl., vol. 164, p. 114035, 2021, doi: 10.1016/j.eswa.2020.114035.

B. Mirzaei, F. Rahmati, and H. Nezamabadi-pour, "A score-based preprocessing technique for class imbalance problems," Pattern Anal. Appl., vol. 25, pp. 913–931, 2022.

R. Lin, W. Ren, X. Sun, et al., "A hybrid neural network for fast automatic modulation classification," IEEE Access, vol. 8, pp. 130314–130322, 2020, doi: 10.1109/ACCESS.2020.3009471.

S. Mohsen, A. M. Ali, and A. Emam, "Automatic modulation recognition using CNN deep learning models," Multimed. Tools Appl., 2023, doi: 10.1007/s11042-023-15814-y.

K. Liu and F. Li, "Automatic modulation recognition based on a multiscale network with statistical features," Phys. Commun., vol. 58, p. 102052, 2023, doi: 10.1016/j.phycom.2023.102052.

L. Qian, H. Wu, T. Zhang, and X. Yang, "Research and implementation of modulation recognition based on cascaded feature fusion," IET Commun., vol. 17, pp. 1037–1047, 2023, doi: 10.1049/cmu2.12604.