An Underwater Acoustic Communication Signal Modulation-Style Recognition Algorithm Based on Dual-Feature Fusion and ResNet–Transformer Dual-Model Fusion
Source abstract
Abstract
Traditional underwater acoustic reconnaissance technologies are limited in directly detecting underwater acoustic communication signals. This paper proposes a dual-feature ResNet–Transformer model with two innovative breakthroughs: (1) A dual-modal fusion architecture of ResNet and Transformer is constructed using residual connections to alleviate gradient degradation in deep networks and combining multi-head self-attention to enhance long-distance dependency modeling. (2) The time–frequency representation obtained from the smooth pseudo-Wigner–Ville distribution is used as the first input branch, and higher-order statistics are introduced as the second input branch to enhance phase feature extraction and cope with channel interference. Experiments on the Danjiangkou measured dataset show that the model improves the accuracy by 6.67% compared with the existing Convolutional Neural Network (CNN)–Transformer model in long-distance ranges, providing an efficient solution for modulation recognition in complex underwater acoustic environments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Wireless Signal Modulation Classification · Underwater Acoustics Research · Gait Recognition and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Naval Institute of Underwater Acoustic Technology, Naval University of Engineering, Wuhan 430033, China
References (25)
Show source-provided references
1. Acoustic propagation considerations for underwater acoustic communications network development10.1145/1347364.1347370 ↗
2. Channel estimation strategies for underwater acoustic (UWA) communication: An overview10.1016/j.jfranklin.2020.04.002 ↗
3. Research on development and application of underwater acoustic communication system10.1088/1742-6596/1617/1/012036 ↗
4. Fang, S. (2023). Principles and Techniques of Underwater Acoustic Reconnaissance, Science Press.
5. Yao, X., Yang, H., and Sheng, M. (2023). Automatic modulation classification for underwater acoustic communication signals based on deep complex networks. Entropy, 25.10.3390/e25020318 ↗
6. Hierarchical digital modulation classification using cumulants10.1109/26.837045 ↗
7. Nadya, H.K., Mansour, A., and Nordholm, S. (2010, January 13–15). Classification of digital modulated signals based on time frequency representation. Proceedings of the 2010 4th International Conference on Signal Processing and Communication Systems, Gold Coast, QLD, Australia.
8. Xu, Z., Wu, X., Gao, D., and Su, W. (2022, January 25–27). Blind modulation recognition of UWA signals with semi-supervised learning. Proceedings of the 2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xi’an, China.10.1109/ICSPCC55723.2022.9984242 ↗
9. Brahmjit, S., Jindal, P., Verma, P., Sharma, V., and Prakash, C. (2025, January 21–22). Automatic Modulation Recognition Using Modified Convolutional Neural Network. Proceedings of the 2025 3rd International Conference on Device Intelligence, Computing and Communication Technologies (DICCT), Dehradun, India.
10. Yogesh, B., and Emilien, D.G.D. (2025, January 21–22). A Modified Convolutional Neural Network Model for Automatic Modulation Classification. Proceedings of the 2025 Emerging Technologies for Intelligent Systems (ETIS), Dehradun, India.
11. Real-time radio technology and modulation classification via an LSTM auto-encoder10.1109/TWC.2021.3095855 ↗
12. Combined Classifier-Demodulator Scheme Based on LSTM Architecture
13. Research on modulation recognition method in low SNR based on LSTM10.1088/1742-6596/2189/1/012003 ↗
14. Modulation recognition of underwater acoustic signals using deep hybrid neural networks10.1109/TWC.2022.3144608 ↗
15. West Nathan, E., and O’shea, T. (2017, January 6–9). Deep architectures for modulation recognition. Proceedings of the 2017 IEEE international symposium on dynamic spectrum access networks (DySPAN), Baltimore, MD, USA.10.1109/DySPAN.2017.7920754 ↗
16. Signal modulation classification based on the transformer network10.1109/TCCN.2022.3176640 ↗
17. Zhang, W., Xue, K., Yao, A., and Sun, Y. (2024). CTRNet: An Automatic Modulation Recognition Based on Transformer-CNN Neural Network. Electronics, 13.10.3390/electronics13173408 ↗
18. Automatic modulation recognition of underwater acoustic signals using a two-stream transformer10.1109/JIOT.2024.3367852 ↗
19. Pang, C., Wang, F., Chen, M., Liu, Y., and Dong, Y. (2024, January 22–24). Modulation Recognition of Underwater Acoustic Signals Using Dynamic Dilated Convolutional Neural Network and Transformer. Proceedings of the 2024 IEEE International Conference on Signal, Information and Data Processing (ICSIDP), Zhuhai, China.10.1109/ICSIDP62679.2024.10868125 ↗
20. Shin, D.-M., Park, D.-H., and Kim, H.-N. (2025, January 15–17). Deep Learning-Based Modulation Recognition with Multi-Scale Temporal Feature Extraction. Proceedings of the 2025 International Conference on Information Networking (ICOIN), Chiang Mai, Thailand.10.1109/ICOIN63865.2025.10992754 ↗
21. Dong, Y., Zhai, R., Wang, B., Zhong, Y., Rong, Z., and Wang, Y. (2025). A Novel Distributed Solution for Automatic Modulation Classification Based on Federated Learning and Modified LSTM. IEEE Trans. Veh. Technol., 1–13.10.1109/TVT.2025.3551765 ↗
22. Leon, C. (1995). Time-Frequency Analysis: Theory and Applications, Pearson College Div.
23. Deep learning in digital modulation recognition using high order cumulants10.1109/ACCESS.2019.2916833 ↗
24. He, K., and Zhang, X. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
25. Chen, J., and Zhao, R. (2023, January 16–18). Wireless Signal Recognition Based on ResNet-Transformer. Proceedings of the 2023 11th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC), Chongqing, China.10.1109/ICWOC57905.2023.10200835 ↗