Adaptive Wavelet-Denoising and Attention-Enhanced CNN Transformer Network for Robust Automatic Modulation Classification under Low-SNR Wireless Channels

Author

Monika Dhurve, Dinesh Pratap Singh, Gaurav Morghare

Abstract

 Automatic modulation classification (AMC) becomes challenging in low signal-to-noise ratio (SNR) conditions because noise obscures discriminative signal characteristics. This paper proposes AWD-ACT-AMC, an integrated deep-learning architecture that combines (i) SNR-adaptive wavelet soft-threshold denoising of raw I/Q samples, (ii) multi-scale convolutional feature extraction, (iii) channel and temporal attention, and (iv) a lightweight Transformer encoder with an additional time-frequency token. The proposed model is evaluated on an RML2016.10a-style synthetic dataset containing 11 modulation classes over −20 to +18 dB SNR and is compared with a single-scale CNN trained under identical conditions. AWD-ACT-AMC achieves 52.25% average accuracy and 50.91% macro-F1, compared with 46.45% and 44.81% for the baseline, corresponding to improvements of 5.80 and 6.10 percentage points. For SNR ≥ 0 dB, the proposed model reaches 78.66% accuracy, providing an 8.91-point improvement over the baseline. The improvement becomes particularly pronounced in the medium- and high-SNR regimes, demonstrating the effectiveness of combining adaptive denoising, multi-scale feature extraction, attention, and sequence modelling for robust AMC

Keywords

Automatic modulation classification, wavelet denoising, attention, Transformer, low SNR, deep learning

Full Text:

Download Paper PDF

References

[1] S. Peng, S. Sun, and Y.-D. Yao, “A survey of modulation classification using deep learning: Signal representation and data preprocessing,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 12, pp. 7020–7038, Dec. 2022.

[2] Y. Zhang, Z. Zhou, Y. Cao, G. Li, and X. Li, “MAMC—Optimal on accuracy and efficiency for automatic modulation classification with extended signal length,” IEEE Commun. Lett., vol. 28, no. 12, pp. 2864–2868, Dec. 2024.

[3] A. P. Hermawan, R. R. Ginanjar, D.-S. Kim, and J.-M. Lee, “CNN-based automatic modulation classification for beyond 5G communications,” IEEE Commun. Lett., vol. 24, no. 5, pp. 1038–1041, May 2020.

[4] J. Xu, C. Luo, G. Parr, and Y. Luo, “A spatiotemporal multi-channel learning framework for automatic modulation recognition,” IEEE Wireless Commun. Lett., vol. 9, no. 10, pp. 1629–1632, Oct. 2020.

[5] F. Zhang, C. Luo, J. Xu, and Y. Luo, “An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation,” IEEE Commun. Lett., vol. 25, no. 10, pp. 3287–3290, Oct. 2021.

[6] Z. Ke and H. Vikalo, “Real-time radio technology and modulation classification via an LSTM auto-encoder,” IEEE Trans. Wireless Commun., vol. 21, no. 1, pp. 370–382, Jan. 2022.

[7] A. Gu and T. Dao, “Mamba: Linear-time sequence modeling with selective state spaces,” arXiv:2312.00752, 2023.

[8] D. L. Donoho, “De-noising by soft-thresholding,” IEEE Trans. Inf. Theory, vol. 41, no. 3, pp. 613–627, May 1995.

[9] M. Zhao, S. Zhong, X. Fu, B. Tang, and M. Pecht, “Deep residual shrinkage networks for fault diagnosis,” IEEE Trans. Ind. Informat., vol. 16, no. 7, pp. 4681–4690, Jul. 2020.

[10] J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 7132–7141.

[11] A. Vaswani et al., “Attention is all you need,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2017, pp. 5998–6008.

[12] T. O’Shea and N. West, “Radio machine learning dataset generation with GNU radio,” in Proc. GNU Radio Conf., vol. 1, no. 1, Sep. 2016, pp. 1–6.

[13] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2015.

[14] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception architecture for computer vision,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 2818–2826.

[15] T. J. O’Shea, J. Corgan, and T. C. Clancy, “Convolutional radio modulation recognition networks,” in Proc. Int. Conf. Eng. Appl. Neural Netw. (EANN), 2016, pp. 213–226.

[16] D. L. Donoho and I. M. Johnstone, “Ideal spatial adaptation by wavelet shrinkage,” Biometrika, vol. 81, no. 3, pp. 425–455, Sep. 1994.

[17] S. G. Mallat, “A theory for multiresolution signal decomposition: The wavelet representation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no.  

7, pp. 674–693, Jul. 1989.

 

 

Share your valuable work from Social Media Buttons