Elsagheer, M., Abd Elsayed, K., Ramzy, S. (2024). Optimizing Automatic Modulation Classification through Gaussian-Regularized Hybrid CNN-LSTM Architecture. JES. Journal of Engineering Sciences, (), 46-61. doi: 10.21608/jesaun.2024.271102.1315
Mohamed Elsagheer; Khairy Abd Elsayed; safwat Ramzy. "Optimizing Automatic Modulation Classification through Gaussian-Regularized Hybrid CNN-LSTM Architecture". JES. Journal of Engineering Sciences, , , 2024, 46-61. doi: 10.21608/jesaun.2024.271102.1315
Elsagheer, M., Abd Elsayed, K., Ramzy, S. (2024). 'Optimizing Automatic Modulation Classification through Gaussian-Regularized Hybrid CNN-LSTM Architecture', JES. Journal of Engineering Sciences, (), pp. 46-61. doi: 10.21608/jesaun.2024.271102.1315
Elsagheer, M., Abd Elsayed, K., Ramzy, S. Optimizing Automatic Modulation Classification through Gaussian-Regularized Hybrid CNN-LSTM Architecture. JES. Journal of Engineering Sciences, 2024; (): 46-61. doi: 10.21608/jesaun.2024.271102.1315
Optimizing Automatic Modulation Classification through Gaussian-Regularized Hybrid CNN-LSTM Architecture
Electrical Engineering Department, Faculty of Engineering, Sohag University, Sohag, Egypt.
Abstract
This paper presents an innovative deep-learning model for Automatic Modulation Classification (AMC) in wireless communication systems. The proposed architecture integrates Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) networks, augmented by a Gaussian noise layer to mitigate overfitting. The integration of both networks seeks to enhance classification accuracy and performance by leveraging the unique capabilities of CNNs and LSTMs in capturing spatial and temporal features, respectively. The model is expected to distinguish between eight digital and two analog modulation modes. Experimental evaluation on the RadioML2016.10b dataset demonstrates a peak recognition accuracy of 93.2% at 18 dB SNR. Comparative analyses validate the superior performance of the proposed architecture. The Gaussian noise layer contributes significantly to a 3% performance improvement at 18 dB SNR. The model achieves recognition accuracy exceeding 96% for most modulation modes, highlighting its robustness. Finally, computational complexity analysis underscores the efficiency of the proposed architecture, reinforcing its practical viability.
Deep Learning Neural Networks Approaches," SVU-Int. J. Eng. Sci. Appl., vol. 4, pp. 48–54,
2023.
[15] T. Huynh-The, Q.-V. Pham, T.-V. Nguyen, T.T. Nguyen, D.B. da Costa, D.-S. Kim, "RanNet:
Learning Residual-Attention Structure in CNNs for Automatic Modulation Classification,"
IEEE Wirel. Commun. Lett. vol. 11, pp. 1243–1247, 2022.
[16] T. O’Shea, J. Corgan, T. Clancy, "Convolutional Radio Modulation Recognition Networks," in
2016. [17] T.J. O’Shea, T. Roy, T.C. Clancy, "Over-the-Air Deep Learning Based Radio Sign Classification," IEEE J. Sel. Top. Signal Process. vol. 12, pp. 168–179, 2018.
[18] X. Hao, Y. Luo, Q. Ye, Q. He, G. Yang, C.-C. Chen, "Automatic Modulation Recognition
Method Based on Hybrid Model of Convolutional Neural Networks and Gated Recurrent
Units," Sens. Mater. vol. 33, pp. 4229–4243, 2021.
[19] Y. Wang, M. Liu, J. Yang, G. GUI, "Data-Driven Deep Learning for Automatic Modulation
Recognition in Cognitive Radios," IEEE Trans. Veh. Technol., vol. 68, pp. 4074–4077, 2019.
[20] D. Inc, "RF Datasets for Machine Learning," DeepSig. [Online]. Available: